tools/run_3d_gaussian_splatting_on_colab.ipynb

{
  "nbformat": 4,
  "nbformat_minor": 0,
  "metadata": {
    "colab": {
      "provenance": [],
      "gpuType": "T4"
    },
    "kernelspec": {
      "name": "python3",
      "display_name": "Python 3"
    },
    "language_info": {
      "name": "python"
    },
    "accelerator": "GPU"
  },
  "cells": [
    {
      "cell_type": "markdown",
      "source": [
        "# Instructions to run the project in colab.\n",
        "\n",
        "1. Set the hardware accelerator: \"Runtime->Change Runtime Type->Hardware accelerator->select GPU->select T4\"\n",
        "2. Upload the code to corresponding folder in your google drive.\n",
        "3. Mount your google drive to this notebook (see following code).\n",
        "4. Install condacolab (see following code).\n",
        "5. Install requirement.txt with pip (see following code).\n",
        "6. Install pytorch, torchvision, pytorch-cuda etc. with conda (see following code).\n",
        "7. Prepare the dataset as instructed in https://github.com/wanmeihuali/taichi_3d_gaussian_splatting#dataset\n",
        "8. Run the trainer with correct config (see following code).\n",
        "9. Check out the training process through tensorboard (see following code)."
      ],
      "metadata": {
        "id": "vPqH__q5VD9s"
      }
    },
    {
      "cell_type": "code",
      "execution_count": 1,
      "metadata": {
        "id": "fuLOcVLlzceC",
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "outputId": "9a611bc8-952a-46fe-ef6e-caaa8dcd74fe"
      },
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "Drive already mounted at /content/drive/; to attempt to forcibly remount, call drive.mount(\"/content/drive/\", force_remount=True).\n"
          ]
        }
      ],
      "source": [
        "from google.colab import drive\n",
        "drive.mount('/content/drive/')"
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "import os\n",
        "os.chdir('/content/drive/My Drive/AI/taichi_3d_gaussian_splatting')"
      ],
      "metadata": {
        "id": "dz2HWwcLM1NT"
      },
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "code",
      "source": [
        "!pip install -q condacolab\n",
        "import condacolab\n",
        "condacolab.install()"
      ],
      "metadata": {
        "id": "BaO6qiKlU2yt"
      },
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "code",
      "source": [
        "!conda --version"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "ZNmUovivQRmW",
        "outputId": "c075c110-ecd4-4a0f-e49d-1aae8f06a882"
      },
      "execution_count": null,
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "conda 23.1.0\n"
          ]
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "%cd /content/drive/My Drive/AI/taichi_3d_gaussian_splatting"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "gnq0YMAMWnt_",
        "outputId": "5a9fdec0-baa8-4ba7-fe45-81446b73737e"
      },
      "execution_count": null,
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "/content/drive/My Drive/AI/taichi_3d_gaussian_splatting\n"
          ]
        }
      ]
    },
    {
      "cell_type": "markdown",
      "source": [
        "## Install requirements."
      ],
      "metadata": {
        "id": "FY4qwOnLaW1c"
      }
    },
    {
      "cell_type": "code",
      "source": [
        "!pip install -r requirements.txt\n",
        "!pip install -e ."
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 1000
        },
        "id": "MvAkWlhOZOPV",
        "outputId": "d0b80662-51a6-4858-c689-edb8487f2b05"
      },
      "execution_count": null,
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "Collecting taichi>=1.6.0\n",
            "  Downloading taichi-1.6.0-cp310-cp310-manylinux_2_27_x86_64.whl (54.2 MB)\n",
            "\u001b[2K     \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m54.2/54.2 MB\u001b[0m \u001b[31m15.3 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
            "\u001b[?25hCollecting matplotlib\n",
            "  Downloading matplotlib-3.7.1-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl (11.6 MB)\n",
            "\u001b[2K     \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m11.6/11.6 MB\u001b[0m \u001b[31m109.5 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
            "\u001b[?25hCollecting numpy\n",
            "  Downloading numpy-1.25.0-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl (17.6 MB)\n",
            "\u001b[2K     \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m17.6/17.6 MB\u001b[0m \u001b[31m92.2 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
            "\u001b[?25hCollecting pytorch_msssim\n",
            "  Downloading pytorch_msssim-1.0.0-py3-none-any.whl (7.7 kB)\n",
            "Collecting dataclass-wizard\n",
            "  Downloading dataclass_wizard-0.22.2-py2.py3-none-any.whl (90 kB)\n",
            "\u001b[2K     \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m90.4/90.4 kB\u001b[0m \u001b[31m13.6 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
            "\u001b[?25hCollecting pillow\n",
            "  Downloading Pillow-10.0.0-cp310-cp310-manylinux_2_28_x86_64.whl (3.4 MB)\n",
            "\u001b[2K     \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m3.4/3.4 MB\u001b[0m \u001b[31m75.4 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
            "\u001b[?25hCollecting pyyaml\n",
            "  Downloading PyYAML-6.0-cp310-cp310-manylinux_2_5_x86_64.manylinux1_x86_64.manylinux_2_12_x86_64.manylinux2010_x86_64.whl (682 kB)\n",
            "\u001b[2K     \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m682.2/682.2 kB\u001b[0m \u001b[31m52.7 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
            "\u001b[?25hCollecting pandas[parquet]>=2.0.0\n",
            "  Downloading pandas-2.0.3-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl (12.3 MB)\n",
            "\u001b[2K     \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m12.3/12.3 MB\u001b[0m \u001b[31m79.7 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
            "\u001b[?25hCollecting scipy\n",
            "  Downloading scipy-1.11.1-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl (36.3 MB)\n",
            "\u001b[2K     \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m36.3/36.3 MB\u001b[0m \u001b[31m11.1 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
            "\u001b[?25hCollecting argparse\n",
            "  Downloading argparse-1.4.0-py2.py3-none-any.whl (23 kB)\n",
            "Collecting tensorboard\n",
            "  Downloading tensorboard-2.13.0-py3-none-any.whl (5.6 MB)\n",
            "\u001b[2K     \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m5.6/5.6 MB\u001b[0m \u001b[31m83.0 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
            "\u001b[?25hCollecting dill\n",
            "  Downloading dill-0.3.6-py3-none-any.whl (110 kB)\n",
            "\u001b[2K     \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m110.5/110.5 kB\u001b[0m \u001b[31m14.7 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
            "\u001b[?25hCollecting rich\n",
            "  Downloading rich-13.4.2-py3-none-any.whl (239 kB)\n",
            "\u001b[2K     \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m239.4/239.4 kB\u001b[0m \u001b[31m26.1 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
            "\u001b[?25hRequirement already satisfied: colorama in /usr/local/lib/python3.10/site-packages (from taichi>=1.6.0->-r requirements.txt (line 1)) (0.4.6)\n",
            "Collecting contourpy>=1.0.1\n",
            "  Downloading contourpy-1.1.0-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl (300 kB)\n",
            "\u001b[2K     \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m300.7/300.7 kB\u001b[0m \u001b[31m33.0 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
            "\u001b[?25hCollecting pyparsing>=2.3.1\n",
            "  Downloading pyparsing-3.1.0-py3-none-any.whl (102 kB)\n",
            "\u001b[2K     \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m102.6/102.6 kB\u001b[0m \u001b[31m14.2 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
            "\u001b[?25hCollecting cycler>=0.10\n",
            "  Downloading cycler-0.11.0-py3-none-any.whl (6.4 kB)\n",
            "Collecting fonttools>=4.22.0\n",
            "  Downloading fonttools-4.40.0-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl (4.2 MB)\n",
            "\u001b[2K     \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m4.2/4.2 MB\u001b[0m \u001b[31m80.8 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
            "\u001b[?25hCollecting kiwisolver>=1.0.1\n",
            "  Downloading kiwisolver-1.4.4-cp310-cp310-manylinux_2_12_x86_64.manylinux2010_x86_64.whl (1.6 MB)\n",
            "\u001b[2K     \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m1.6/1.6 MB\u001b[0m \u001b[31m73.8 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
            "\u001b[?25hCollecting python-dateutil>=2.7\n",
            "  Downloading python_dateutil-2.8.2-py2.py3-none-any.whl (247 kB)\n",
            "\u001b[2K     \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m247.7/247.7 kB\u001b[0m \u001b[31m26.9 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
            "\u001b[?25hCollecting packaging>=20.0\n",
            "  Downloading packaging-23.1-py3-none-any.whl (48 kB)\n",
            "\u001b[2K     \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m48.9/48.9 kB\u001b[0m \u001b[31m5.9 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
            "\u001b[?25hCollecting torch\n",
            "  Downloading torch-2.0.1-cp310-cp310-manylinux1_x86_64.whl (619.9 MB)\n",
            "\u001b[2K     \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m619.9/619.9 MB\u001b[0m \u001b[31m2.7 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
            "\u001b[?25hCollecting tzdata>=2022.1\n",
            "  Downloading tzdata-2023.3-py2.py3-none-any.whl (341 kB)\n",
            "\u001b[2K     \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m341.8/341.8 kB\u001b[0m \u001b[31m39.5 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
            "\u001b[?25hCollecting pytz>=2020.1\n",
            "  Downloading pytz-2023.3-py2.py3-none-any.whl (502 kB)\n",
            "\u001b[2K     \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m502.3/502.3 kB\u001b[0m \u001b[31m46.1 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
            "\u001b[?25hCollecting pyarrow>=7.0.0\n",
            "  Downloading pyarrow-12.0.1-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl (38.9 MB)\n",
            "\u001b[2K     \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m38.9/38.9 MB\u001b[0m \u001b[31m16.2 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
            "\u001b[?25hCollecting werkzeug>=1.0.1\n",
            "  Downloading Werkzeug-2.3.6-py3-none-any.whl (242 kB)\n",
            "\u001b[2K     \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m242.5/242.5 kB\u001b[0m \u001b[31m27.2 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
            "\u001b[?25hRequirement already satisfied: wheel>=0.26 in /usr/local/lib/python3.10/site-packages (from tensorboard->-r requirements.txt (line 11)) (0.40.0)\n",
            "Collecting google-auth<3,>=1.6.3\n",
            "  Downloading google_auth-2.21.0-py2.py3-none-any.whl (182 kB)\n",
            "\u001b[2K     \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m182.1/182.1 kB\u001b[0m \u001b[31m22.5 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
            "\u001b[?25hCollecting tensorboard-data-server<0.8.0,>=0.7.0\n",
            "  Downloading tensorboard_data_server-0.7.1-py3-none-manylinux2014_x86_64.whl (6.6 MB)\n",
            "\u001b[2K     \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m6.6/6.6 MB\u001b[0m \u001b[31m88.0 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
            "\u001b[?25hCollecting markdown>=2.6.8\n",
            "  Downloading Markdown-3.4.3-py3-none-any.whl (93 kB)\n",
            "\u001b[2K     \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m93.9/93.9 kB\u001b[0m \u001b[31m13.1 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
            "\u001b[?25hRequirement already satisfied: requests<3,>=2.21.0 in /usr/local/lib/python3.10/site-packages (from tensorboard->-r requirements.txt (line 11)) (2.28.2)\n",
            "Collecting absl-py>=0.4\n",
            "  Downloading absl_py-1.4.0-py3-none-any.whl (126 kB)\n",
            "\u001b[2K     \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m126.5/126.5 kB\u001b[0m \u001b[31m16.8 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
            "\u001b[?25hRequirement already satisfied: setuptools>=41.0.0 in /usr/local/lib/python3.10/site-packages (from tensorboard->-r requirements.txt (line 11)) (65.6.3)\n",
            "Collecting grpcio>=1.48.2\n",
            "  Downloading grpcio-1.56.0-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl (5.2 MB)\n",
            "\u001b[2K     \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m5.2/5.2 MB\u001b[0m \u001b[31m89.5 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
            "\u001b[?25hCollecting google-auth-oauthlib<1.1,>=0.5\n",
            "  Downloading google_auth_oauthlib-1.0.0-py2.py3-none-any.whl (18 kB)\n",
            "Collecting protobuf>=3.19.6\n",
            "  Downloading protobuf-4.23.3-cp37-abi3-manylinux2014_x86_64.whl (304 kB)\n",
            "\u001b[2K     \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m304.5/304.5 kB\u001b[0m \u001b[31m31.9 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
            "\u001b[?25hCollecting pyasn1-modules>=0.2.1\n",
            "  Downloading pyasn1_modules-0.3.0-py2.py3-none-any.whl (181 kB)\n",
            "\u001b[2K     \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m181.3/181.3 kB\u001b[0m \u001b[31m17.2 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
            "\u001b[?25hCollecting rsa<5,>=3.1.4\n",
            "  Downloading rsa-4.9-py3-none-any.whl (34 kB)\n",
            "Collecting cachetools<6.0,>=2.0.0\n",
            "  Downloading cachetools-5.3.1-py3-none-any.whl (9.3 kB)\n",
            "Collecting six>=1.9.0\n",
            "  Downloading six-1.16.0-py2.py3-none-any.whl (11 kB)\n",
            "Requirement already satisfied: urllib3<2.0 in /usr/local/lib/python3.10/site-packages (from google-auth<3,>=1.6.3->tensorboard->-r requirements.txt (line 11)) (1.26.15)\n",
            "Collecting requests-oauthlib>=0.7.0\n",
            "  Downloading requests_oauthlib-1.3.1-py2.py3-none-any.whl (23 kB)\n",
            "Requirement already satisfied: charset-normalizer<4,>=2 in /usr/local/lib/python3.10/site-packages (from requests<3,>=2.21.0->tensorboard->-r requirements.txt (line 11)) (3.1.0)\n",
            "Requirement already satisfied: idna<4,>=2.5 in /usr/local/lib/python3.10/site-packages (from requests<3,>=2.21.0->tensorboard->-r requirements.txt (line 11)) (3.4)\n",
            "Requirement already satisfied: certifi>=2017.4.17 in /usr/local/lib/python3.10/site-packages (from requests<3,>=2.21.0->tensorboard->-r requirements.txt (line 11)) (2022.12.7)\n",
            "Collecting MarkupSafe>=2.1.1\n",
            "  Downloading MarkupSafe-2.1.3-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl (25 kB)\n",
            "Collecting markdown-it-py>=2.2.0\n",
            "  Downloading markdown_it_py-3.0.0-py3-none-any.whl (87 kB)\n",
            "\u001b[2K     \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m87.5/87.5 kB\u001b[0m \u001b[31m11.5 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
            "\u001b[?25hCollecting pygments<3.0.0,>=2.13.0\n",
            "  Downloading Pygments-2.15.1-py3-none-any.whl (1.1 MB)\n",
            "\u001b[2K     \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m1.1/1.1 MB\u001b[0m \u001b[31m63.0 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
            "\u001b[?25hCollecting jinja2\n",
            "  Downloading Jinja2-3.1.2-py3-none-any.whl (133 kB)\n",
            "\u001b[2K     \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m133.1/133.1 kB\u001b[0m \u001b[31m14.3 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
            "\u001b[?25hCollecting nvidia-cusolver-cu11==11.4.0.1\n",
            "  Downloading nvidia_cusolver_cu11-11.4.0.1-2-py3-none-manylinux1_x86_64.whl (102.6 MB)\n",
            "\u001b[2K     \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m102.6/102.6 MB\u001b[0m \u001b[31m9.2 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
            "\u001b[?25hCollecting triton==2.0.0\n",
            "  Downloading triton-2.0.0-1-cp310-cp310-manylinux2014_x86_64.manylinux_2_17_x86_64.whl (63.3 MB)\n",
            "\u001b[2K     \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m63.3/63.3 MB\u001b[0m \u001b[31m9.8 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
            "\u001b[?25hCollecting sympy\n",
            "  Downloading sympy-1.12-py3-none-any.whl (5.7 MB)\n",
            "\u001b[2K     \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m5.7/5.7 MB\u001b[0m \u001b[31m78.0 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
            "\u001b[?25hCollecting nvidia-cuda-cupti-cu11==11.7.101\n",
            "  Downloading nvidia_cuda_cupti_cu11-11.7.101-py3-none-manylinux1_x86_64.whl (11.8 MB)\n",
            "\u001b[2K     \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m11.8/11.8 MB\u001b[0m \u001b[31m78.3 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
            "\u001b[?25hCollecting nvidia-curand-cu11==10.2.10.91\n",
            "  Downloading nvidia_curand_cu11-10.2.10.91-py3-none-manylinux1_x86_64.whl (54.6 MB)\n",
            "\u001b[2K     \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m54.6/54.6 MB\u001b[0m \u001b[31m11.5 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
            "\u001b[?25hCollecting nvidia-cusparse-cu11==11.7.4.91\n",
            "  Downloading nvidia_cusparse_cu11-11.7.4.91-py3-none-manylinux1_x86_64.whl (173.2 MB)\n",
            "\u001b[2K     \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m173.2/173.2 MB\u001b[0m \u001b[31m6.7 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
            "\u001b[?25hCollecting filelock\n",
            "  Downloading filelock-3.12.2-py3-none-any.whl (10 kB)\n",
            "Collecting nvidia-nvtx-cu11==11.7.91\n",
            "  Downloading nvidia_nvtx_cu11-11.7.91-py3-none-manylinux1_x86_64.whl (98 kB)\n",
            "\u001b[2K     \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m98.6/98.6 kB\u001b[0m \u001b[31m14.4 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
            "\u001b[?25hCollecting networkx\n",
            "  Downloading networkx-3.1-py3-none-any.whl (2.1 MB)\n",
            "\u001b[2K     \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m2.1/2.1 MB\u001b[0m \u001b[31m93.7 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
            "\u001b[?25hCollecting nvidia-cufft-cu11==10.9.0.58\n",
            "  Downloading nvidia_cufft_cu11-10.9.0.58-py3-none-manylinux1_x86_64.whl (168.4 MB)\n",
            "\u001b[2K     \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m168.4/168.4 MB\u001b[0m \u001b[31m7.1 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
            "\u001b[?25hCollecting nvidia-cudnn-cu11==8.5.0.96\n",
            "  Downloading nvidia_cudnn_cu11-8.5.0.96-2-py3-none-manylinux1_x86_64.whl (557.1 MB)\n",
            "\u001b[2K     \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m557.1/557.1 MB\u001b[0m \u001b[31m2.7 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
            "\u001b[?25hCollecting nvidia-cublas-cu11==11.10.3.66\n",
            "  Downloading nvidia_cublas_cu11-11.10.3.66-py3-none-manylinux1_x86_64.whl (317.1 MB)\n",
            "\u001b[2K     \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m317.1/317.1 MB\u001b[0m \u001b[31m4.5 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
            "\u001b[?25hCollecting nvidia-cuda-runtime-cu11==11.7.99\n",
            "  Downloading nvidia_cuda_runtime_cu11-11.7.99-py3-none-manylinux1_x86_64.whl (849 kB)\n",
            "\u001b[2K     \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m849.3/849.3 kB\u001b[0m \u001b[31m51.3 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
            "\u001b[?25hCollecting nvidia-cuda-nvrtc-cu11==11.7.99\n",
            "  Downloading nvidia_cuda_nvrtc_cu11-11.7.99-2-py3-none-manylinux1_x86_64.whl (21.0 MB)\n",
            "\u001b[2K     \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m21.0/21.0 MB\u001b[0m \u001b[31m78.6 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
            "\u001b[?25hCollecting nvidia-nccl-cu11==2.14.3\n",
            "  Downloading nvidia_nccl_cu11-2.14.3-py3-none-manylinux1_x86_64.whl (177.1 MB)\n",
            "\u001b[2K     \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m177.1/177.1 MB\u001b[0m \u001b[31m6.9 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
            "\u001b[?25hCollecting typing-extensions\n",
            "  Downloading typing_extensions-4.7.0-py3-none-any.whl (33 kB)\n",
            "Collecting lit\n",
            "  Downloading lit-16.0.6.tar.gz (153 kB)\n",
            "\u001b[2K     \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m153.7/153.7 kB\u001b[0m \u001b[31m20.7 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
            "\u001b[?25h  Installing build dependencies ... \u001b[?25l\u001b[?25hdone\n",
            "  Getting requirements to build wheel ... \u001b[?25l\u001b[?25hdone\n",
            "  Installing backend dependencies ... \u001b[?25l\u001b[?25hdone\n",
            "  Preparing metadata (pyproject.toml) ... \u001b[?25l\u001b[?25hdone\n",
            "Collecting cmake\n",
            "  Downloading cmake-3.26.4-py2.py3-none-manylinux2014_x86_64.manylinux_2_17_x86_64.whl (24.0 MB)\n",
            "\u001b[2K     \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m24.0/24.0 MB\u001b[0m \u001b[31m46.9 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
            "\u001b[?25hCollecting mdurl~=0.1\n",
            "  Downloading mdurl-0.1.2-py3-none-any.whl (10.0 kB)\n",
            "Collecting pyasn1<0.6.0,>=0.4.6\n",
            "  Downloading pyasn1-0.5.0-py2.py3-none-any.whl (83 kB)\n",
            "\u001b[2K     \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m83.9/83.9 kB\u001b[0m \u001b[31m11.1 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
            "\u001b[?25hCollecting oauthlib>=3.0.0\n",
            "  Downloading oauthlib-3.2.2-py3-none-any.whl (151 kB)\n",
            "\u001b[2K     \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m151.7/151.7 kB\u001b[0m \u001b[31m20.1 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
            "\u001b[?25hCollecting mpmath>=0.19\n",
            "  Downloading mpmath-1.3.0-py3-none-any.whl (536 kB)\n",
            "\u001b[2K     \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m536.2/536.2 kB\u001b[0m \u001b[31m42.5 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
            "\u001b[?25hBuilding wheels for collected packages: lit\n",
            "  Building wheel for lit (pyproject.toml) ... \u001b[?25l\u001b[?25hdone\n",
            "  Created wheel for lit: filename=lit-16.0.6-py3-none-any.whl size=93582 sha256=c4989931ecad874978cf60b4bf7a4a8897fbe03137fa8a2d62ae58ebe63336a5\n",
            "  Stored in directory: /root/.cache/pip/wheels/14/f9/07/bb2308587bc2f57158f905a2325f6a89a2befa7437b2d7e137\n",
            "Successfully built lit\n",
            "Installing collected packages: pytz, mpmath, lit, dataclass-wizard, cmake, argparse, tzdata, typing-extensions, tensorboard-data-server, sympy, six, pyyaml, pyparsing, pygments, pyasn1, protobuf, pillow, packaging, oauthlib, nvidia-nvtx-cu11, nvidia-nccl-cu11, nvidia-cusparse-cu11, nvidia-curand-cu11, nvidia-cufft-cu11, nvidia-cuda-runtime-cu11, nvidia-cuda-nvrtc-cu11, nvidia-cuda-cupti-cu11, nvidia-cublas-cu11, numpy, networkx, mdurl, MarkupSafe, markdown, kiwisolver, grpcio, fonttools, filelock, dill, cycler, cachetools, absl-py, werkzeug, scipy, rsa, requests-oauthlib, python-dateutil, pyasn1-modules, pyarrow, nvidia-cusolver-cu11, nvidia-cudnn-cu11, markdown-it-py, jinja2, contourpy, rich, pandas, matplotlib, google-auth, taichi, google-auth-oauthlib, tensorboard, triton, torch, pytorch_msssim\n",
            "Successfully installed MarkupSafe-2.1.3 absl-py-1.4.0 argparse-1.4.0 cachetools-5.3.1 cmake-3.26.4 contourpy-1.1.0 cycler-0.11.0 dataclass-wizard-0.22.2 dill-0.3.6 filelock-3.12.2 fonttools-4.40.0 google-auth-2.21.0 google-auth-oauthlib-1.0.0 grpcio-1.56.0 jinja2-3.1.2 kiwisolver-1.4.4 lit-16.0.6 markdown-3.4.3 markdown-it-py-3.0.0 matplotlib-3.7.1 mdurl-0.1.2 mpmath-1.3.0 networkx-3.1 numpy-1.25.0 nvidia-cublas-cu11-11.10.3.66 nvidia-cuda-cupti-cu11-11.7.101 nvidia-cuda-nvrtc-cu11-11.7.99 nvidia-cuda-runtime-cu11-11.7.99 nvidia-cudnn-cu11-8.5.0.96 nvidia-cufft-cu11-10.9.0.58 nvidia-curand-cu11-10.2.10.91 nvidia-cusolver-cu11-11.4.0.1 nvidia-cusparse-cu11-11.7.4.91 nvidia-nccl-cu11-2.14.3 nvidia-nvtx-cu11-11.7.91 oauthlib-3.2.2 packaging-23.1 pandas-2.0.3 pillow-10.0.0 protobuf-4.23.3 pyarrow-12.0.1 pyasn1-0.5.0 pyasn1-modules-0.3.0 pygments-2.15.1 pyparsing-3.1.0 python-dateutil-2.8.2 pytorch_msssim-1.0.0 pytz-2023.3 pyyaml-6.0 requests-oauthlib-1.3.1 rich-13.4.2 rsa-4.9 scipy-1.11.1 six-1.16.0 sympy-1.12 taichi-1.6.0 tensorboard-2.13.0 tensorboard-data-server-0.7.1 torch-2.0.1 triton-2.0.0 typing-extensions-4.7.0 tzdata-2023.3 werkzeug-2.3.6\n",
            "\u001b[33mWARNING: Running pip as the 'root' user can result in broken permissions and conflicting behaviour with the system package manager. It is recommended to use a virtual environment instead: https://pip.pypa.io/warnings/venv\u001b[0m\u001b[33m\n",
            "\u001b[0m"
          ]
        },
        {
          "output_type": "display_data",
          "data": {
            "application/vnd.colab-display-data+json": {
              "pip_warning": {
                "packages": [
                  "cachetools",
                  "cycler",
                  "dateutil",
                  "grpc",
                  "kiwisolver",
                  "matplotlib",
                  "mpl_toolkits",
                  "six"
                ]
              }
            }
          },
          "metadata": {}
        },
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "Obtaining file:///content/drive/MyDrive/AI/taichi_3d_gaussian_splatting\n",
            "  Preparing metadata (setup.py) ... \u001b[?25l\u001b[?25hdone\n",
            "Installing collected packages: taichi-3d-gaussian-splatting\n",
            "  Running setup.py develop for taichi-3d-gaussian-splatting\n",
            "Successfully installed taichi-3d-gaussian-splatting-0.0.1\n",
            "\u001b[33mWARNING: Running pip as the 'root' user can result in broken permissions and conflicting behaviour with the system package manager. It is recommended to use a virtual environment instead: https://pip.pypa.io/warnings/venv\u001b[0m\u001b[33m\n",
            "\u001b[0m"
          ]
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "!conda install pytorch torchvision torchaudio pytorch-cuda=11.7 -c pytorch -c nvidia"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "5EfEQmGFaA47",
        "outputId": "08fb7a42-7089-450b-b583-d688888517cb"
      },
      "execution_count": null,
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "Collecting package metadata (current_repodata.json): - \b\b\\ \b\b| \b\b/ \b\b- \b\b\\ \b\b| \b\b/ \b\b- \b\b\\ \b\b| \b\b/ \b\b- \b\b\\ \b\b| \b\b/ \b\b- \b\b\\ \b\b| \b\b/ \b\b- \b\b\\ \b\b| \b\b/ \b\b- \b\b\\ \b\b| \b\b/ \b\b- \b\b\\ \b\b| \b\b/ \b\b- \b\b\\ \b\b| \b\b/ \b\b- \b\b\\ \b\b| \b\b/ \b\b- \b\b\\ \b\b| \b\b/ \b\b- \b\b\\ \b\b| \b\bdone\n",
            "Solving environment: - \b\b\\ \b\b| \b\b/ \b\b- \b\b\\ \b\b| \b\b/ \b\b- \b\b\\ \b\b| \b\b/ \b\b- \b\b\\ \b\b| \b\b/ \b\b- \b\b\\ \b\b| \b\b/ \b\b- \b\b\\ \b\b| \b\b/ \b\b- \b\b\\ \b\b| \b\b/ \b\b- \b\b\\ \b\b| \b\b/ \b\b- \b\b\\ \b\b| \b\b/ \b\b- \b\b\\ \b\b| \b\b/ \b\b- \b\b\\ \b\b| \b\b/ \b\b- \b\b\\ \b\b| \b\b/ \b\b- \b\b\\ \b\b| \b\b/ \b\b- \b\b\\ \b\b| \b\b/ \b\b- \b\b\\ \b\b| \b\b/ \b\b- \b\b\\ \b\b| \b\b/ \b\b- \b\b\\ \b\b| \b\b/ \b\b- \b\b\\ \b\b| \b\b/ \b\b- \b\b\\ \b\b| \b\b/ \b\b- \b\b\\ \b\b| \b\b/ \b\b- \b\b\\ \b\b| \b\b/ \b\b- \b\b\\ \b\b| \b\b/ \b\b- \b\b\\ \b\b| \b\b/ \b\b- \b\b\\ \b\b| \b\b/ \b\b- \b\b\\ \b\b| \b\b/ \b\b- \b\b\\ \b\b| \b\b/ \b\b- \b\b\\ \b\b| \b\b/ \b\b- \b\b\\ \b\b| \b\b/ \b\b- \b\b\\ \b\b| \b\b/ \b\b- \b\b\\ \b\b| \b\b/ \b\b- \b\b\\ \b\b| \b\b/ \b\b- \b\b\\ \b\b| \b\b/ \b\b- \b\b\\ \b\b| \b\b/ \b\b- \b\b\\ \b\b| \b\b/ \b\b- \b\b\\ \b\b| \b\b/ \b\b- \b\b\\ \b\b| \b\b/ \b\b- \b\b\\ \b\b| \b\b/ \b\b- \b\b\\ \b\b| \b\b/ \b\b- \b\b\\ \b\b| \b\b/ \b\b- \b\b\\ \b\b| \b\b/ \b\b- \b\b\\ \b\b| \b\b/ \b\b- \b\b\\ \b\b| \b\b/ \b\b- \b\bfailed with initial frozen solve. Retrying with flexible solve.\n",
            "Solving environment: | \b\b/ \b\b- \b\b\\ \b\b| \b\b/ \b\b- \b\b\\ \b\b| \b\b/ \b\b- \b\b\\ \b\b| \b\b/ \b\b- \b\b\\ \b\b| \b\b/ \b\b- \b\b\\ \b\b| \b\b/ \b\b- \b\b\\ \b\b| \b\b/ \b\b- \b\b\\ \b\b| \b\b/ \b\b- \b\b\\ \b\b| \b\b/ \b\b- \b\b\\ \b\b| \b\b/ \b\b- \b\b\\ \b\b| \b\b/ \b\b- \b\b\\ \b\b| \b\b/ \b\b- \b\b\\ \b\b| \b\b/ \b\b- \b\b\\ \b\b| \b\b/ \b\b- \b\b\\ \b\b| \b\b/ \b\b- \b\b\\ \b\b| \b\b/ \b\b- \b\b\\ \b\b| \b\b/ \b\b- \b\b\\ \b\b| \b\b/ \b\b- \b\b\\ \b\b| \b\b/ \b\b- \b\b\\ \b\b| \b\b/ \b\b- \b\b\\ \b\b| \b\b/ \b\b- \b\b\\ \b\b| \b\b/ \b\b- \b\b\\ \b\b| \b\b/ \b\b- \b\b\\ \b\b| \b\b/ \b\b- \b\b\\ \b\b| \b\b/ \b\b- \b\b\\ \b\b| \b\b/ \b\b- \b\b\\ \b\b| \b\b/ \b\b- \b\b\\ \b\b| \b\b/ \b\b- \b\b\\ \b\b| \b\b/ \b\b- \b\b\\ \b\b| \b\b/ \b\b- \b\b\\ \b\b| \b\b/ \b\b- \b\b\\ \b\b| \b\b/ \b\b- \b\b\\ \b\b| \b\b/ \b\b- \b\b\\ \b\b| \b\b/ \b\b- \b\b\\ \b\b| \b\b/ \b\b- \b\b\\ \b\b| \b\b/ \b\b- \b\b\\ \b\b| \b\b/ \b\b- \b\b\\ \b\b| \b\b/ \b\b- \b\b\\ \b\b| \b\b/ \b\b- \b\b\\ \b\b| \b\b/ \b\b- \b\b\\ \b\b| \b\b/ \b\b- \b\b\\ \b\b| \b\b/ \b\b- \b\b\\ \b\b| \b\b/ \b\b- \b\b\\ \b\b| \b\b/ \b\b- \b\b\\ \b\b| \b\b/ \b\b- \b\b\\ \b\b| \b\b/ \b\b- \b\b\\ \b\b| \b\b/ \b\b- \b\b\\ \b\bfailed with repodata from current_repodata.json, will retry with next repodata source.\n",
            "Collecting package metadata (repodata.json): / \b\b- \b\b\\ \b\b| \b\b/ \b\b- \b\b\\ \b\b| \b\b/ \b\b- \b\b\\ \b\b| \b\b/ \b\b- \b\b\\ \b\b| \b\b/ \b\b- \b\b\\ \b\b| \b\b/ \b\b- \b\b\\ \b\b| \b\b/ \b\b- \b\b\\ \b\b| \b\b/ \b\b- \b\b\\ \b\b| \b\b/ \b\b- \b\b\\ \b\b| \b\b/ \b\b- \b\b\\ \b\b| \b\b/ \b\b- \b\b\\ \b\b| \b\b/ \b\b- \b\b\\ \b\b| \b\b/ \b\b- \b\b\\ \b\b| \b\b/ \b\b- \b\b\\ \b\b| \b\b/ \b\b- \b\b\\ \b\b| \b\b/ \b\b- \b\b\\ \b\b| \b\b/ \b\b- \b\b\\ \b\b| \b\b/ \b\b- \b\b\\ \b\b| \b\b/ \b\b- \b\b\\ \b\b| \b\b/ \b\b- \b\b\\ \b\b| \b\b/ \b\b- \b\b\\ \b\b| \b\b/ \b\b- \b\b\\ \b\b| \b\b/ \b\b- \b\b\\ \b\b| \b\b/ \b\b- \b\b\\ \b\b| \b\b/ \b\b- \b\b\\ \b\b| \b\b/ \b\b- \b\b\\ \b\b| \b\b/ \b\b- \b\b\\ \b\b| \b\b/ \b\b- \b\b\\ \b\b| \b\b/ \b\b- \b\b\\ \b\b| \b\b/ \b\b- \b\b\\ \b\b| \b\b/ \b\b- \b\b\\ \b\bdone\n",
            "Solving environment: / \b\b- \b\b\\ \b\b| \b\b/ \b\b- \b\b\\ \b\b| \b\b/ \b\b- \b\b\\ \b\b| \b\b/ \b\b- \b\b\\ \b\b| \b\b/ \b\b- \b\b\\ \b\b| \b\b/ \b\b- \b\b\\ \b\b| \b\b/ \b\b- \b\b\\ \b\b| \b\b/ \b\b- \b\b\\ \b\b| \b\b/ \b\b- \b\b\\ \b\b| \b\b/ \b\b- \b\b\\ \b\b| \b\b/ \b\b- \b\b\\ \b\b| \b\b/ \b\b- \b\b\\ \b\b| \b\b/ \b\b- \b\b\\ \b\b| \b\b/ \b\b- \b\b\\ \b\b| \b\b/ \b\b- \b\b\\ \b\b| \b\b/ \b\b- \b\b\\ \b\b| \b\b/ \b\b- \b\b\\ \b\b| \b\b/ \b\b- \b\b\\ \b\b| \b\b/ \b\b- \b\b\\ \b\b| \b\b/ \b\b- \b\b\\ \b\b| \b\b/ \b\b- \b\b\\ \b\b| \b\b/ \b\b- \b\b\\ \b\b| \b\b/ \b\b- \b\b\\ \b\b| \b\b/ \b\b- \b\b\\ \b\b| \b\b/ \b\b- \b\b\\ \b\b| \b\b/ \b\b- \b\b\\ \b\b| \b\b/ \b\b- \b\b\\ \b\b| \b\b/ \b\b- \b\b\\ \b\b| \b\b/ \b\b- \b\b\\ \b\b| \b\b/ \b\b- \b\b\\ \b\b| \b\b/ \b\b- \b\b\\ \b\b| \b\b/ \b\b- \b\b\\ \b\b| \b\b/ \b\b- \b\b\\ \b\b| \b\b/ \b\b- \b\b\\ \b\b| \b\b/ \b\b- \b\b\\ \b\b| \b\b/ \b\b- \b\b\\ \b\b| \b\b/ \b\b- \b\b\\ \b\b| \b\b/ \b\b- \b\b\\ \b\b| \b\b/ \b\b- \b\b\\ \b\b| \b\b/ \b\b- \b\b\\ \b\b| \b\b/ \b\b- \b\b\\ \b\b| \b\b/ \b\b- \b\b\\ \b\b| \b\b/ \b\b- \b\b\\ \b\b| \b\b/ \b\b- \b\b\\ \b\b| \b\b/ \b\b- \b\b\\ \b\b| \b\b/ \b\b- \b\b\\ \b\b| \b\b/ \b\b- \b\b\\ \b\b| \b\b/ \b\b- \b\b\\ \b\b| \b\b/ \b\b- \b\b\\ \b\b| \b\b/ \b\b- \b\b\\ \b\b| \b\b/ \b\b- \b\b\\ \b\b| \b\b/ \b\b- \b\b\\ \b\b| \b\b/ \b\b- \b\b\\ \b\b| \b\b/ \b\b- \b\b\\ \b\b| \b\b/ \b\b- \b\b\\ \b\b| \b\b/ \b\b- \b\b\\ \b\b| \b\b/ \b\b- \b\b\\ \b\b| \b\b/ \b\b- \b\b\\ \b\b| \b\b/ \b\b- \b\b\\ \b\b| \b\b/ \b\b- \b\b\\ \b\b| \b\b/ \b\b- \b\b\\ \b\b| \b\b/ \b\b- \b\b\\ \b\b| \b\b/ \b\b- \b\b\\ \b\b| \b\b/ \b\b- \b\b\\ \b\b| \b\b/ \b\b- \b\b\\ \b\b| \b\b/ \b\b- \b\b\\ \b\b| \b\b/ \b\b- \b\b\\ \b\b| \b\b/ \b\b- \b\b\\ \b\b| \b\b/ \b\b- \b\b\\ \b\b| \b\b/ \b\b- \b\b\\ \b\b| \b\b/ \b\b- \b\b\\ \b\b| \b\b/ \b\b- \b\b\\ \b\b| \b\b/ \b\b- \b\b\\ \b\b| \b\b/ \b\b- \b\b\\ \b\b| \b\b/ \b\b- \b\b\\ \b\b| \b\b/ \b\b- \b\b\\ \b\b| \b\b/ \b\b- \b\b\\ \b\b| \b\b/ \b\b- \b\b\\ \b\b| \b\b/ \b\b- \b\b\\ \b\b| \b\b/ \b\b- \b\b\\ \b\b| \b\b/ \b\b- \b\b\\ \b\b| \b\b/ \b\b- \b\b\\ \b\b| \b\b/ \b\b- \b\b\\ \b\b| \b\b/ \b\b- \b\b\\ \b\b| \b\b/ \b\b- \b\b\\ \b\b| \b\b/ \b\b- \b\b\\ \b\b| \b\b/ \b\b- \b\b\\ \b\b| \b\b/ \b\b- \b\b\\ \b\b| \b\b/ \b\b- \b\b\\ \b\b| \b\b/ \b\b- \b\b\\ \b\b| \b\b/ \b\b- \b\b\\ \b\b| \b\b/ \b\b- \b\b\\ \b\b| \b\b/ \b\b- \b\b\\ \b\b| \b\b/ \b\b- \b\b\\ \b\b| \b\b/ \b\b- \b\b\\ \b\b| \b\b/ \b\b- \b\b\\ \b\b| \b\b/ \b\b- \b\b\\ \b\b| \b\b/ \b\b- \b\b\\ \b\b| \b\b/ \b\b- \b\b\\ \b\b| \b\b/ \b\b- \b\b\\ \b\b| \b\b/ \b\b- \b\b\\ \b\b| \b\b/ \b\b- \b\b\\ \b\b| \b\b/ \b\b- \b\b\\ \b\b| \b\b/ \b\b- \b\b\\ \b\b| \b\b/ \b\b- \b\b\\ \b\b| \b\b/ \b\b- \b\b\\ \b\b| \b\b/ \b\b- \b\b\\ \b\b| \b\b/ \b\b- \b\b\\ \b\b| \b\b/ \b\b- \b\b\\ \b\b| \b\b/ \b\b- \b\b\\ \b\b| \b\b/ \b\b- \b\b\\ \b\b| \b\b/ \b\b- \b\b\\ \b\b| \b\b/ \b\b- \b\b\\ \b\b| \b\b/ \b\b- \b\b\\ \b\b| \b\b/ \b\b- \b\b\\ \b\b| \b\b/ \b\b- \b\b\\ \b\b| \b\b/ \b\b- \b\b\\ \b\b| \b\b/ \b\b- \b\b\\ \b\b| \b\b/ \b\b- \b\b\\ \b\b| \b\b/ \b\b- \b\b\\ \b\b| \b\b/ \b\b- \b\b\\ \b\b| \b\b/ \b\b- \b\b\\ \b\b| \b\b/ \b\b- \b\b\\ \b\b| \b\b/ \b\b- \b\b\\ \b\b| \b\b/ \b\b- \b\b\\ \b\b| \b\b/ \b\b- \b\b\\ \b\b| \b\b/ \b\b- \b\b\\ \b\b| \b\b/ \b\b- \b\b\\ \b\b| \b\b/ \b\b- \b\b\\ \b\b| \b\b/ \b\b- \b\b\\ \b\b| \b\b/ \b\b- \b\b\\ \b\b| \b\b/ \b\b- \b\b\\ \b\b| \b\b/ \b\b- \b\b\\ \b\b| \b\b/ \b\b- \b\b\\ \b\b| \b\b/ \b\b- \b\b\\ \b\b| \b\b/ \b\b- \b\b\\ \b\b| \b\b/ \b\b- \b\b\\ \b\b| \b\b/ \b\b- \b\b\\ \b\b| \b\b/ \b\b- \b\b\\ \b\b| \b\b/ \b\b- \b\b\\ \b\b| \b\b/ \b\b- \b\b\\ \b\b| \b\b/ \b\b- \b\b\\ \b\b| \b\b/ \b\b- \b\b\\ \b\b| \b\b/ \b\b- \b\b\\ \b\b| \b\b/ \b\b- \b\b\\ \b\b| \b\b/ \b\b- \b\b\\ \b\b| \b\b/ \b\b- \b\b\\ \b\b| \b\b/ \b\b- \b\b\\ \b\b| \b\b/ \b\b- \b\b\\ \b\b| \b\b/ \b\b- \b\b\\ \b\b| \b\b/ \b\b- \b\b\\ \b\b| \b\b/ \b\b- \b\b\\ \b\b| \b\b/ \b\b- \b\b\\ \b\b| \b\b/ \b\b- \b\b\\ \b\b| \b\b/ \b\b- \b\b\\ \b\b| \b\b/ \b\b- \b\b\\ \b\b| \b\b/ \b\b- \b\b\\ \b\b| \b\b/ \b\b- \b\b\\ \b\b| \b\b/ \b\b- \b\b\\ \b\b| \b\b/ \b\b- \b\b\\ \b\b| \b\b/ \b\b- \b\b\\ \b\b| \b\b/ \b\b- \b\b\\ \b\b| \b\b/ \b\b- \b\b\\ \b\b| \b\b/ \b\b- \b\b\\ \b\b| \b\b/ \b\b- \b\b\\ \b\b| \b\b/ \b\b- \b\b\\ \b\b| \b\b/ \b\b- \b\b\\ \b\b| \b\b/ \b\b- \b\b\\ \b\b| \b\b/ \b\b- \b\b\\ \b\b| \b\b/ \b\b- \b\b\\ \b\b| \b\b/ \b\b- \b\b\\ \b\b| \b\b/ \b\b- \b\b\\ \b\b| \b\b/ \b\b- \b\b\\ \b\b| \b\b/ \b\b- \b\b\\ \b\b| \b\b/ \b\b- \b\b\\ \b\b| \b\b/ \b\b- \b\b\\ \b\b| \b\b/ \b\b- \b\b\\ \b\b| \b\b/ \b\b- \b\b\\ \b\b| \b\b/ \b\b- \b\b\\ \b\b| \b\b/ \b\b- \b\b\\ \b\b| \b\b/ \b\b- \b\b\\ \b\b| \b\b/ \b\b- \b\b\\ \b\b| \b\b/ \b\b- \b\b\\ \b\b| \b\b/ \b\b- \b\b\\ \b\b| \b\b/ \b\b- \b\b\\ \b\b| \b\b/ \b\b- \b\b\\ \b\b| \b\b/ \b\b- \b\b\\ \b\b| \b\b/ \b\b- \b\b\\ \b\b| \b\b/ \b\b- \b\b\\ \b\b| \b\b/ \b\b- \b\b\\ \b\b| \b\b/ \b\b- \b\b\\ \b\b| \b\b/ \b\b- \b\b\\ \b\b| \b\b/ \b\b- \b\b\\ \b\b| \b\b/ \b\b- \b\b\\ \b\b| \b\b/ \b\b- \b\b\\ \b\b| \b\b/ \b\b- \b\b\\ \b\b| \b\b/ \b\b- \b\b\\ \b\b| \b\b/ \b\b- \b\b\\ \b\b| \b\b/ \b\b- \b\b\\ \b\b| \b\b/ \b\b- \b\b\\ \b\b| \b\b/ \b\b- \b\b\\ \b\b| \b\b/ \b\b- \b\b\\ \b\b| \b\b/ \b\b- \b\b\\ \b\b| \b\b/ \b\b- \b\b\\ \b\b| \b\b/ \b\b- \b\b\\ \b\b| \b\b/ \b\b- \b\b\\ \b\b| \b\b/ \b\b- \b\b\\ \b\b| \b\b/ \b\b- \b\b\\ \b\b| \b\b/ \b\b- \b\b\\ \b\b| \b\b/ \b\b- \b\b\\ \b\b| \b\b/ \b\b- \b\b\\ \b\b| \b\b/ \b\b- \b\b\\ \b\b| \b\b/ \b\b- \b\b\\ \b\b| \b\b/ \b\b- \b\b\\ \b\b| \b\b/ \b\b- \b\b\\ \b\b| \b\b/ \b\b- \b\b\\ \b\b| \b\b/ \b\b- \b\b\\ \b\b| \b\b/ \b\b- \b\b\\ \b\b| \b\b/ \b\b- \b\b\\ \b\b| \b\b/ \b\b- \b\b\\ \b\b| \b\b/ \b\b- \b\b\\ \b\b| \b\b/ \b\b- \b\b\\ \b\b| \b\b/ \b\b- \b\b\\ \b\b| \b\b/ \b\b- \b\b\\ \b\b| \b\b/ \b\b- \b\b\\ \b\b| \b\b/ \b\b- \b\b\\ \b\b| \b\b/ \b\b- \b\b\\ \b\b| \b\b/ \b\b- \b\b\\ \b\b| \b\b/ \b\b- \b\b\\ \b\b| \b\b/ \b\b- \b\b\\ \b\b| \b\b/ \b\b- \b\b\\ \b\b| \b\b/ \b\b- \b\b\\ \b\b| \b\b/ \b\b- \b\b\\ \b\b| \b\b/ \b\b- \b\b\\ \b\b| \b\b/ \b\b- \b\b\\ \b\b| \b\b/ \b\b- \b\b\\ \b\b| \b\b/ \b\b- \b\b\\ \b\b| \b\b/ \b\b- \b\b\\ \b\b| \b\b/ \b\b- \b\b\\ \b\b| \b\b/ \b\b- \b\b\\ \b\b| \b\b/ \b\b- \b\b\\ \b\b| \b\b/ \b\b- \b\b\\ \b\b| \b\b/ \b\b- \b\b\\ \b\b| \b\b/ \b\b- \b\b\\ \b\b| \b\b/ \b\b- \b\b\\ \b\b| \b\b/ \b\b- \b\b\\ \b\b| \b\b/ \b\b- \b\b\\ \b\b| \b\b/ \b\b- \b\b\\ \b\b| \b\b/ \b\b- \b\b\\ \b\b| \b\b/ \b\b- \b\b\\ \b\b| \b\b/ \b\b- \b\b\\ \b\b| \b\b/ \b\b- \b\b\\ \b\b| \b\b/ \b\b- \b\b\\ \b\b| \b\b/ \b\b- \b\b\\ \b\b| \b\b/ \b\b- \b\b\\ \b\b| \b\b/ \b\b- \b\b\\ \b\b| \b\b/ \b\b- \b\b\\ \b\b| \b\b/ \b\b- \b\b\\ \b\b| \b\b/ \b\b- \b\b\\ \b\b| \b\b/ \b\b- \b\b\\ \b\b| \b\b/ \b\b- \b\b\\ \b\b| \b\b/ \b\b- \b\b\\ \b\b| \b\b/ \b\b- \b\b\\ \b\b| \b\b/ \b\b- \b\b\\ \b\b| \b\b/ \b\b- \b\b\\ \b\b| \b\b/ \b\b- \b\b\\ \b\b| \b\b/ \b\b- \b\b\\ \b\b| \b\b/ \b\b- \b\b\\ \b\b| \b\b/ \b\b- \b\b\\ \b\b| \b\b/ \b\b- \b\b\\ \b\b| \b\b/ \b\b- \b\b\\ \b\b| \b\b/ \b\b- \b\b\\ \b\b| \b\b/ \b\b- \b\b\\ \b\b| \b\b/ \b\b- \b\b\\ \b\b| \b\b/ \b\b- \b\b\\ \b\b| \b\b/ \b\b- \b\b\\ \b\b| \b\b/ \b\b- \b\b\\ \b\b| \b\b/ \b\b- \b\b\\ \b\b| \b\b/ \b\b- \b\b\\ \b\b| \b\b/ \b\b- \b\b\\ \b\b| \b\b/ \b\b- \b\b\\ \b\b| \b\b/ \b\b- \b\b\\ \b\b| \b\b/ \b\b- \b\b\\ \b\b| \b\b/ \b\b- \b\b\\ \b\b| \b\b/ \b\b- \b\b\\ \b\b| \b\b/ \b\b- \b\b\\ \b\b| \b\b/ \b\b- \b\b\\ \b\b| \b\b/ \b\b- \b\b\\ \b\b| \b\b/ \b\b- \b\b\\ \b\b| \b\b/ \b\b- \b\b\\ \b\b| \b\b/ \b\b- \b\b\\ \b\b| \b\b/ \b\b- \b\b\\ \b\b| \b\b/ \b\b- \b\b\\ \b\b| \b\b/ \b\b- \b\b\\ \b\b| \b\b/ \b\b- \b\b\\ \b\b| \b\b/ \b\b- \b\b\\ \b\b| \b\b/ \b\b- \b\b\\ \b\b| \b\b/ \b\b- \b\b\\ \b\b| \b\b/ \b\b- \b\b\\ \b\b| \b\b/ \b\b- \b\b\\ \b\b| \b\b/ \b\b- \b\b\\ \b\b| \b\b/ \b\b- \b\b\\ \b\b| \b\b/ \b\b- \b\b\\ \b\b| \b\b/ \b\b- \b\b\\ \b\b| \b\b/ \b\b- \b\b\\ \b\b| \b\b/ \b\b- \b\b\\ \b\b| \b\b/ \b\b- \b\b\\ \b\b| \b\b/ \b\b- \b\b\\ \b\b| \b\b/ \b\b- \b\b\\ \b\b| \b\b/ \b\b- \b\b\\ \b\b| \b\b/ \b\b- \b\b\\ \b\b| \b\b/ \b\b- \b\b\\ \b\b| \b\b/ \b\b- \b\b\\ \b\b| \b\b/ \b\b- \b\b\\ \b\b| \b\b/ \b\b- \b\b\\ \b\b| \b\b/ \b\b- \b\b\\ \b\b| \b\b/ \b\b- \b\b\\ \b\b| \b\b/ \b\b- \b\b\\ \b\b| \b\b/ \b\b- \b\b\\ \b\b| \b\b/ \b\b- \b\b\\ \b\b| \b\b/ \b\b- \b\b\\ \b\b| \b\b/ \b\b- \b\b\\ \b\b| \b\b/ \b\b- \b\b\\ \b\b| \b\b/ \b\b- \b\b\\ \b\b| \b\b/ \b\b- \b\b\\ \b\b| \b\b/ \b\b- \b\b\\ \b\b| \b\b/ \b\b- \b\b\\ \b\b| \b\b/ \b\b- \b\b\\ \b\b| \b\b/ \b\b- \b\b\\ \b\b| \b\b/ \b\b- \b\b\\ \b\b| \b\b/ \b\b- \b\b\\ \b\b| \b\b/ \b\b- \b\b\\ \b\b| \b\b/ \b\b- \b\b\\ \b\b| \b\b/ \b\b- \b\b\\ \b\b| \b\b/ \b\b- \b\b\\ \b\b| \b\b/ \b\b- \b\b\\ \b\b| \b\b/ \b\b- \b\b\\ \b\b| \b\b/ \b\b- \b\b\\ \b\b| \b\b/ \b\b- \b\b\\ \b\b| \b\b/ \b\b- \b\b\\ \b\b| \b\b/ \b\b- \b\b\\ \b\b| \b\b/ \b\b- \b\b\\ \b\b| \b\b/ \b\b- \b\b\\ \b\b| \b\b/ \b\b- \b\b\\ \b\b| \b\b/ \b\b- \b\b\\ \b\b| \b\b/ \b\b- \b\b\\ \b\b| \b\b/ \b\b- \b\b\\ \b\b| \b\b/ \b\b- \b\b\\ \b\b| \b\b/ \b\b- \b\b\\ \b\b| \b\b/ \b\b- \b\b\\ \b\b| \b\b/ \b\b- \b\b\\ \b\b| \b\b/ \b\b- \b\b\\ \b\b| \b\b/ \b\b- \b\b\\ \b\b| \b\b/ \b\b- \b\b\\ \b\b| \b\b/ \b\b- \b\b\\ \b\b| \b\b/ \b\b- \b\b\\ \b\b| \b\b/ \b\b- \b\b\\ \b\b| \b\b/ \b\b- \b\b\\ \b\b| \b\b/ \b\b- \b\b\\ \b\b| \b\b/ \b\b- \b\b\\ \b\b| \b\b/ \b\b- \b\b\\ \b\b| \b\b/ \b\b- \b\b\\ \b\b| \b\b/ \b\b- \b\b\\ \b\b| \b\b/ \b\b- \b\b\\ \b\b| \b\b/ \b\b- \b\b\\ \b\b| \b\b/ \b\b- \b\b\\ \b\b| \b\b/ \b\b- \b\b\\ \b\b| \b\b/ \b\b- \b\b\\ \b\b| \b\b/ \b\b- \b\b\\ \b\b| \b\b/ \b\b- \b\b\\ \b\b| \b\b/ \b\b- \b\b\\ \b\b| \b\b/ \b\b- \b\b\\ \b\b| \b\b/ \b\b- \b\b\\ \b\b| \b\b/ \b\b- \b\b\\ \b\b| \b\b/ \b\b- \b\b\\ \b\b| \b\b/ \b\b- \b\b\\ \b\b| \b\b/ \b\b- \b\b\\ \b\b| \b\b/ \b\b- \b\b\\ \b\b| \b\b/ \b\b- \b\b\\ \b\b| \b\b/ \b\b- \b\b\\ \b\b| \b\b/ \b\b- \b\b\\ \b\b| \b\b/ \b\b- \b\b\\ \b\b| \b\b/ \b\b- \b\b\\ \b\b| \b\b/ \b\b- \b\b\\ \b\b| \b\b/ \b\b- \b\b\\ \b\b| \b\b/ \b\b- \b\b\\ \b\b| \b\b/ \b\b- \b\b\\ \b\b| \b\b/ \b\b- \b\b\\ \b\b| \b\b/ \b\b- \b\b\\ \b\b| \b\b/ \b\b- \b\b\\ \b\b| \b\b/ \b\b- \b\b\\ \b\b| \b\b/ \b\b- \b\b\\ \b\b| \b\b/ \b\b- \b\b\\ \b\b| \b\b/ \b\b- \b\b\\ \b\b| \b\b/ \b\b- \b\b\\ \b\b| \b\b/ \b\b- \b\b\\ \b\b| \b\b/ \b\b- \b\b\\ \b\b| \b\b/ \b\b- \b\b\\ \b\b| \b\b/ \b\b- \b\b\\ \b\b| \b\b/ \b\b- \b\b\\ \b\b| \b\b/ \b\b- \b\b\\ \b\b| \b\b/ \b\b- \b\b\\ \b\b| \b\b/ \b\b- \b\b\\ \b\b| \b\b/ \b\b- \b\b\\ \b\b| \b\b/ \b\b- \b\b\\ \b\b| \b\b/ \b\b- \b\b\\ \b\b| \b\b/ \b\b- \b\b\\ \b\b| \b\b/ \b\b- \b\b\\ \b\b| \b\b/ \b\b- \b\b\\ \b\b| \b\b/ \b\b- \b\b\\ \b\b| \b\b/ \b\b- \b\b\\ \b\b| \b\b/ \b\b- \b\b\\ \b\b| \b\b/ \b\b- \b\b\\ \b\b| \b\b/ \b\b- \b\b\\ \b\b| \b\b/ \b\b- \b\b\\ \b\b| \b\b/ \b\b- \b\b\\ \b\b| \b\b/ \b\b- \b\b\\ \b\b| \b\b/ \b\b- \b\b\\ \b\b| \b\b/ \b\b- \b\b\\ \b\b| \b\b/ \b\b- \b\b\\ \b\b| \b\b/ \b\b- \b\b\\ \b\b| \b\b/ \b\b- \b\b\\ \b\b| \b\b/ \b\b- \b\b\\ \b\b| \b\b/ \b\b- \b\b\\ \b\b| \b\b/ \b\b- \b\b\\ \b\b| \b\b/ \b\b- \b\b\\ \b\b| \b\b/ \b\b- \b\b\\ \b\b| \b\b/ \b\b- \b\b\\ \b\b| \b\b/ \b\b- \b\b\\ \b\b| \b\b/ \b\b- \b\b\\ \b\b| \b\b/ \b\b- \b\bdone\n",
            "\n",
            "## Package Plan ##\n",
            "\n",
            "  environment location: /usr/local\n",
            "\n",
            "  added / updated specs:\n",
            "    - pytorch\n",
            "    - pytorch-cuda=11.7\n",
            "    - torchaudio\n",
            "    - torchvision\n",
            "\n",
            "\n",
            "The following packages will be downloaded:\n",
            "\n",
            "    package                    |            build\n",
            "    ---------------------------|-----------------\n",
            "    _openmp_mutex-4.5          |       2_kmp_llvm           6 KB  conda-forge\n",
            "    blas-2.116                 |              mkl          13 KB  conda-forge\n",
            "    blas-devel-3.9.0           |   16_linux64_mkl          12 KB  conda-forge\n",
            "    boltons-23.0.0             |     pyhd8ed1ab_0         296 KB  conda-forge\n",
            "    certifi-2023.5.7           |     pyhd8ed1ab_0         149 KB  conda-forge\n",
            "    conda-23.3.1               |  py310hff52083_0         941 KB  conda-forge\n",
            "    cuda-cudart-11.7.99        |                0         194 KB  nvidia\n",
            "    cuda-cupti-11.7.101        |                0        22.9 MB  nvidia\n",
            "    cuda-libraries-11.7.1      |                0           1 KB  nvidia\n",
            "    cuda-nvrtc-11.7.99         |                0        17.3 MB  nvidia\n",
            "    cuda-nvtx-11.7.91          |                0          57 KB  nvidia\n",
            "    cuda-runtime-11.7.1        |                0           1 KB  nvidia\n",
            "    cudatoolkit-11.8.0         |      h37601d7_11       635.9 MB  conda-forge\n",
            "    ffmpeg-4.3                 |       hf484d3e_0         9.9 MB  pytorch\n",
            "    filelock-3.12.2            |     pyhd8ed1ab_0          15 KB  conda-forge\n",
            "    freetype-2.12.1            |       hca18f0e_1         611 KB  conda-forge\n",
            "    gmp-6.2.1                  |       h58526e2_0         806 KB  conda-forge\n",
            "    gmpy2-2.1.2                |  py310h3ec546c_1         215 KB  conda-forge\n",
            "    gnutls-3.6.13              |       h85f3911_1         2.0 MB  conda-forge\n",
            "    jinja2-3.1.2               |     pyhd8ed1ab_1          99 KB  conda-forge\n",
            "    jpeg-9e                    |       h0b41bf4_3         235 KB  conda-forge\n",
            "    jsonpatch-1.32             |     pyhd8ed1ab_0          14 KB  conda-forge\n",
            "    jsonpointer-2.0            |             py_0           9 KB  conda-forge\n",
            "    lame-3.100                 |    h166bdaf_1003         496 KB  conda-forge\n",
            "    lcms2-2.15                 |       hfd0df8a_0         235 KB  conda-forge\n",
            "    lerc-4.0.0                 |       h27087fc_0         275 KB  conda-forge\n",
            "    libblas-3.9.0              |   16_linux64_mkl          13 KB  conda-forge\n",
            "    libcblas-3.9.0             |   16_linux64_mkl          12 KB  conda-forge\n",
            "    libcublas-11.10.3.66       |                0       286.1 MB  nvidia\n",
            "    libcufft-10.7.2.124        |       h4fbf590_0        93.6 MB  nvidia\n",
            "    libcufile-1.7.0.149        |                0        1021 KB  nvidia\n",
            "    libcurand-10.3.3.53        |                0        51.6 MB  nvidia\n",
            "    libcusolver-11.4.0.1       |                0        78.7 MB  nvidia\n",
            "    libcusparse-11.7.4.91      |                0       151.1 MB  nvidia\n",
            "    libdeflate-1.17            |       h0b41bf4_0          63 KB  conda-forge\n",
            "    libgfortran-ng-13.1.0      |       h69a702a_0          23 KB  conda-forge\n",
            "    libgfortran5-13.1.0        |       h15d22d2_0         1.4 MB  conda-forge\n",
            "    libhwloc-2.9.1             |       hd6dc26d_0         2.5 MB  conda-forge\n",
            "    liblapack-3.9.0            |   16_linux64_mkl          12 KB  conda-forge\n",
            "    liblapacke-3.9.0           |   16_linux64_mkl          12 KB  conda-forge\n",
            "    libnpp-11.7.4.75           |                0       129.3 MB  nvidia\n",
            "    libnvjpeg-11.8.0.2         |                0         2.2 MB  nvidia\n",
            "    libpng-1.6.39              |       h753d276_0         276 KB  conda-forge\n",
            "    libtiff-4.5.0              |       h6adf6a1_2         397 KB  conda-forge\n",
            "    libwebp-base-1.3.1         |       hd590300_0         391 KB  conda-forge\n",
            "    libxcb-1.13                |    h7f98852_1004         391 KB  conda-forge\n",
            "    llvm-openmp-16.0.6         |       h4dfa4b3_0        39.9 MB  conda-forge\n",
            "    markupsafe-2.1.3           |  py310h2372a71_0          23 KB  conda-forge\n",
            "    mkl-2022.1.0               |     h84fe81f_915       199.6 MB  conda-forge\n",
            "    mkl-devel-2022.1.0         |     ha770c72_916          25 KB  conda-forge\n",
            "    mkl-include-2022.1.0       |     h84fe81f_915         745 KB  conda-forge\n",
            "    mpc-1.3.1                  |       hfe3b2da_0         114 KB  conda-forge\n",
            "    mpfr-4.2.0                 |       hb012696_0         616 KB  conda-forge\n",
            "    mpmath-1.3.0               |     pyhd8ed1ab_0         428 KB  conda-forge\n",
            "    nettle-3.6                 |       he412f7d_0         6.5 MB  conda-forge\n",
            "    networkx-3.1               |     pyhd8ed1ab_0         1.4 MB  conda-forge\n",
            "    numpy-1.25.0               |  py310ha4c1d20_0         6.5 MB  conda-forge\n",
            "    openh264-2.1.1             |       h780b84a_0         1.5 MB  conda-forge\n",
            "    openjpeg-2.5.0             |       hfec8fc6_2         344 KB  conda-forge\n",
            "    packaging-23.1             |     pyhd8ed1ab_0          45 KB  conda-forge\n",
            "    pillow-9.4.0               |  py310h023d228_1        44.3 MB  conda-forge\n",
            "    pthread-stubs-0.4          |    h36c2ea0_1001           5 KB  conda-forge\n",
            "    pytorch-2.0.1              |py3.10_cuda11.7_cudnn8.5.0_0        1.19 GB  pytorch\n",
            "    pytorch-cuda-11.7          |       h778d358_5           3 KB  pytorch\n",
            "    pytorch-mutex-1.0          |             cuda           3 KB  pytorch\n",
            "    sympy-1.12                 | pypyh9d50eac_103         4.1 MB  conda-forge\n",
            "    tbb-2021.9.0               |       hf52228f_0         1.5 MB  conda-forge\n",
            "    torchaudio-2.0.2           |      py310_cu117         7.6 MB  pytorch\n",
            "    torchtriton-2.0.0          |            py310        62.6 MB  pytorch\n",
            "    torchvision-0.15.2         |      py310_cu117         8.0 MB  pytorch\n",
            "    typing_extensions-4.7.0    |     pyha770c72_0          35 KB  conda-forge\n",
            "    xorg-libxau-1.0.11         |       hd590300_0          14 KB  conda-forge\n",
            "    xorg-libxdmcp-1.1.3        |       h7f98852_0          19 KB  conda-forge\n",
            "    zlib-1.2.13                |       h166bdaf_4          92 KB  conda-forge\n",
            "    ------------------------------------------------------------\n",
            "                                           Total:        3.03 GB\n",
            "\n",
            "The following NEW packages will be INSTALLED:\n",
            "\n",
            "  blas               conda-forge/linux-64::blas-2.116-mkl \n",
            "  blas-devel         conda-forge/linux-64::blas-devel-3.9.0-16_linux64_mkl \n",
            "  boltons            conda-forge/noarch::boltons-23.0.0-pyhd8ed1ab_0 \n",
            "  cuda-cudart        nvidia/linux-64::cuda-cudart-11.7.99-0 \n",
            "  cuda-cupti         nvidia/linux-64::cuda-cupti-11.7.101-0 \n",
            "  cuda-libraries     nvidia/linux-64::cuda-libraries-11.7.1-0 \n",
            "  cuda-nvrtc         nvidia/linux-64::cuda-nvrtc-11.7.99-0 \n",
            "  cuda-nvtx          nvidia/linux-64::cuda-nvtx-11.7.91-0 \n",
            "  cuda-runtime       nvidia/linux-64::cuda-runtime-11.7.1-0 \n",
            "  cudatoolkit        conda-forge/linux-64::cudatoolkit-11.8.0-h37601d7_11 \n",
            "  ffmpeg             pytorch/linux-64::ffmpeg-4.3-hf484d3e_0 \n",
            "  filelock           conda-forge/noarch::filelock-3.12.2-pyhd8ed1ab_0 \n",
            "  freetype           conda-forge/linux-64::freetype-2.12.1-hca18f0e_1 \n",
            "  gmp                conda-forge/linux-64::gmp-6.2.1-h58526e2_0 \n",
            "  gmpy2              conda-forge/linux-64::gmpy2-2.1.2-py310h3ec546c_1 \n",
            "  gnutls             conda-forge/linux-64::gnutls-3.6.13-h85f3911_1 \n",
            "  jinja2             conda-forge/noarch::jinja2-3.1.2-pyhd8ed1ab_1 \n",
            "  jpeg               conda-forge/linux-64::jpeg-9e-h0b41bf4_3 \n",
            "  jsonpatch          conda-forge/noarch::jsonpatch-1.32-pyhd8ed1ab_0 \n",
            "  jsonpointer        conda-forge/noarch::jsonpointer-2.0-py_0 \n",
            "  lame               conda-forge/linux-64::lame-3.100-h166bdaf_1003 \n",
            "  lcms2              conda-forge/linux-64::lcms2-2.15-hfd0df8a_0 \n",
            "  lerc               conda-forge/linux-64::lerc-4.0.0-h27087fc_0 \n",
            "  libblas            conda-forge/linux-64::libblas-3.9.0-16_linux64_mkl \n",
            "  libcblas           conda-forge/linux-64::libcblas-3.9.0-16_linux64_mkl \n",
            "  libcublas          nvidia/linux-64::libcublas-11.10.3.66-0 \n",
            "  libcufft           nvidia/linux-64::libcufft-10.7.2.124-h4fbf590_0 \n",
            "  libcufile          nvidia/linux-64::libcufile-1.7.0.149-0 \n",
            "  libcurand          nvidia/linux-64::libcurand-10.3.3.53-0 \n",
            "  libcusolver        nvidia/linux-64::libcusolver-11.4.0.1-0 \n",
            "  libcusparse        nvidia/linux-64::libcusparse-11.7.4.91-0 \n",
            "  libdeflate         conda-forge/linux-64::libdeflate-1.17-h0b41bf4_0 \n",
            "  libgfortran-ng     conda-forge/linux-64::libgfortran-ng-13.1.0-h69a702a_0 \n",
            "  libgfortran5       conda-forge/linux-64::libgfortran5-13.1.0-h15d22d2_0 \n",
            "  libhwloc           conda-forge/linux-64::libhwloc-2.9.1-hd6dc26d_0 \n",
            "  liblapack          conda-forge/linux-64::liblapack-3.9.0-16_linux64_mkl \n",
            "  liblapacke         conda-forge/linux-64::liblapacke-3.9.0-16_linux64_mkl \n",
            "  libnpp             nvidia/linux-64::libnpp-11.7.4.75-0 \n",
            "  libnvjpeg          nvidia/linux-64::libnvjpeg-11.8.0.2-0 \n",
            "  libpng             conda-forge/linux-64::libpng-1.6.39-h753d276_0 \n",
            "  libtiff            conda-forge/linux-64::libtiff-4.5.0-h6adf6a1_2 \n",
            "  libwebp-base       conda-forge/linux-64::libwebp-base-1.3.1-hd590300_0 \n",
            "  libxcb             conda-forge/linux-64::libxcb-1.13-h7f98852_1004 \n",
            "  llvm-openmp        conda-forge/linux-64::llvm-openmp-16.0.6-h4dfa4b3_0 \n",
            "  markupsafe         conda-forge/linux-64::markupsafe-2.1.3-py310h2372a71_0 \n",
            "  mkl                conda-forge/linux-64::mkl-2022.1.0-h84fe81f_915 \n",
            "  mkl-devel          conda-forge/linux-64::mkl-devel-2022.1.0-ha770c72_916 \n",
            "  mkl-include        conda-forge/linux-64::mkl-include-2022.1.0-h84fe81f_915 \n",
            "  mpc                conda-forge/linux-64::mpc-1.3.1-hfe3b2da_0 \n",
            "  mpfr               conda-forge/linux-64::mpfr-4.2.0-hb012696_0 \n",
            "  mpmath             conda-forge/noarch::mpmath-1.3.0-pyhd8ed1ab_0 \n",
            "  nettle             conda-forge/linux-64::nettle-3.6-he412f7d_0 \n",
            "  networkx           conda-forge/noarch::networkx-3.1-pyhd8ed1ab_0 \n",
            "  numpy              conda-forge/linux-64::numpy-1.25.0-py310ha4c1d20_0 \n",
            "  openh264           conda-forge/linux-64::openh264-2.1.1-h780b84a_0 \n",
            "  openjpeg           conda-forge/linux-64::openjpeg-2.5.0-hfec8fc6_2 \n",
            "  packaging          conda-forge/noarch::packaging-23.1-pyhd8ed1ab_0 \n",
            "  pillow             conda-forge/linux-64::pillow-9.4.0-py310h023d228_1 \n",
            "  pthread-stubs      conda-forge/linux-64::pthread-stubs-0.4-h36c2ea0_1001 \n",
            "  pytorch            pytorch/linux-64::pytorch-2.0.1-py3.10_cuda11.7_cudnn8.5.0_0 \n",
            "  pytorch-cuda       pytorch/linux-64::pytorch-cuda-11.7-h778d358_5 \n",
            "  pytorch-mutex      pytorch/noarch::pytorch-mutex-1.0-cuda \n",
            "  sympy              conda-forge/noarch::sympy-1.12-pypyh9d50eac_103 \n",
            "  tbb                conda-forge/linux-64::tbb-2021.9.0-hf52228f_0 \n",
            "  torchaudio         pytorch/linux-64::torchaudio-2.0.2-py310_cu117 \n",
            "  torchtriton        pytorch/linux-64::torchtriton-2.0.0-py310 \n",
            "  torchvision        pytorch/linux-64::torchvision-0.15.2-py310_cu117 \n",
            "  typing_extensions  conda-forge/noarch::typing_extensions-4.7.0-pyha770c72_0 \n",
            "  xorg-libxau        conda-forge/linux-64::xorg-libxau-1.0.11-hd590300_0 \n",
            "  xorg-libxdmcp      conda-forge/linux-64::xorg-libxdmcp-1.1.3-h7f98852_0 \n",
            "  zlib               conda-forge/linux-64::zlib-1.2.13-h166bdaf_4 \n",
            "\n",
            "The following packages will be UPDATED:\n",
            "\n",
            "  ca-certificates                      2022.12.7-ha878542_0 --> 2023.5.7-hbcca054_0 \n",
            "  certifi                            2022.12.7-pyhd8ed1ab_0 --> 2023.5.7-pyhd8ed1ab_0 \n",
            "  conda                              23.1.0-py310hff52083_0 --> 23.3.1-py310hff52083_0 \n",
            "  openssl                                  3.1.0-h0b41bf4_0 --> 3.1.1-hd590300_1 \n",
            "\n",
            "The following packages will be DOWNGRADED:\n",
            "\n",
            "  _openmp_mutex                                   4.5-2_gnu --> 4.5-2_kmp_llvm \n",
            "\n",
            "\n",
            "\n",
            "Downloading and Extracting Packages\n",
            "libwebp-base-1.3.1   | 391 KB    | :   0% 0/1 [00:00<?, ?it/s]\n",
            "torchvision-0.15.2   | 8.0 MB    | :   0% 0/1 [00:00<?, ?it/s]\u001b[A\n",
            "\n",
            "libpng-1.6.39        | 276 KB    | :   0% 0/1 [00:00<?, ?it/s]\u001b[A\u001b[A\n",
            "\n",
            "\n",
            "libcurand-10.3.3.53  | 51.6 MB   | :   0% 0/1 [00:00<?, ?it/s]\u001b[A\u001b[A\u001b[A\n",
            "\n",
            "\n",
            "\n",
            "cuda-nvrtc-11.7.99   | 17.3 MB   | :   0% 0/1 [00:00<?, ?it/s]\u001b[A\u001b[A\u001b[A\u001b[A\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "libcublas-11.10.3.66 | 286.1 MB  | :   0% 0/1 [00:00<?, ?it/s]\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "gmp-6.2.1            | 806 KB    | :   0% 0/1 [00:00<?, ?it/s]\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "certifi-2023.5.7     | 149 KB    | :   0% 0/1 [00:00<?, ?it/s]\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "numpy-1.25.0         | 6.5 MB    | :   0% 0/1 [00:00<?, ?it/s]\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "gnutls-3.6.13        | 2.0 MB    | :   0% 0/1 [00:00<?, ?it/s]\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "filelock-3.12.2      | 15 KB     | :   0% 0/1 [00:00<?, ?it/s]\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "libcblas-3.9.0       | 12 KB     | :   0% 0/1 [00:00<?, ?it/s]\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "markupsafe-2.1.3     | 23 KB     | :   0% 0/1 [00:00<?, ?it/s]\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "mpfr-4.2.0           | 616 KB    | :   0% 0/1 [00:00<?, ?it/s]\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "_openmp_mutex-4.5    | 6 KB      | :   0% 0/1 [00:00<?, ?it/s]\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "tbb-2021.9.0         | 1.5 MB    | :   0% 0/1 [00:00<?, ?it/s]\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "libcusolver-11.4.0.1 | 78.7 MB   | :   0% 0/1 [00:00<?, ?it/s]\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "xorg-libxdmcp-1.1.3  | 19 KB     | :   0% 0/1 [00:00<?, ?it/s]\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "cuda-nvtx-11.7.91    | 57 KB     | :   0% 0/1 [00:00<?, ?it/s]\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "libwebp-base-1.3.1   | 391 KB    | :   4% 0.04096634978421655/1 [00:00<00:04,  4.77s/it]\n",
            "\n",
            "libpng-1.6.39        | 276 KB    | :   6% 0.05797614287382475/1 [00:00<00:03,  3.37s/it]\u001b[A\u001b[A\n",
            "\n",
            "\n",
            "\n",
            "cuda-nvrtc-11.7.99   | 17.3 MB   | :   0% 0.0009030257591074066/1 [00:00<03:47, 227.21s/it]\u001b[A\u001b[A\u001b[A\u001b[A\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "libcublas-11.10.3.66 | 286.1 MB  | :   0% 5.4615989490955573e-05/1 [00:00<1:12:40, 4360.77s/it]\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "gmp-6.2.1            | 806 KB    | :   2% 0.019840539414665338/1 [00:00<00:12, 12.43s/it]\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\n",
            "torchvision-0.15.2   | 8.0 MB    | :   0% 0.0019442291969018594/1 [00:00<02:22, 142.65s/it]\u001b[A\n",
            "\n",
            "\n",
            "libcurand-10.3.3.53  | 51.6 MB   | :   0% 0.0003025925704437314/1 [00:00<15:08, 909.20s/it]\u001b[A\u001b[A\u001b[A\n",
            "\n",
            "\n",
            "\n",
            "cuda-nvrtc-11.7.99   | 17.3 MB   | :  10% 0.10113888502002955/1 [00:00<00:02,  2.47s/it]   \u001b[A\u001b[A\u001b[A\u001b[A\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "libcublas-11.10.3.66 | 286.1 MB  | :   1% 0.006444686759932758/1 [00:00<00:41, 41.51s/it]      \u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "certifi-2023.5.7     | 149 KB    | :  11% 0.10751855521941424/1 [00:00<00:02,  3.34s/it]\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\n",
            "torchvision-0.15.2   | 8.0 MB    | :  15% 0.15164987735834504/1 [00:00<00:01,  2.05s/it]   \u001b[A\n",
            "\n",
            "\n",
            "libcurand-10.3.3.53  | 51.6 MB   | :   2% 0.024207405635498513/1 [00:00<00:13, 13.43s/it]  \u001b[A\u001b[A\u001b[A\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "numpy-1.25.0         | 6.5 MB    | :   0% 0.0024211937206198987/1 [00:00<02:42, 162.61s/it]\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\n",
            "\n",
            "\n",
            "\n",
            "cuda-nvrtc-11.7.99   | 17.3 MB   | :  18% 0.18060515182148132/1 [00:00<00:01,  1.89s/it]\u001b[A\u001b[A\u001b[A\u001b[A\n",
            "\n",
            "libpng-1.6.39        | 276 KB    | : 100% 1.0/1 [00:00<00:00,  2.63it/s]                \u001b[A\u001b[A\n",
            "\n",
            "libwebp-base-1.3.1   | 391 KB    | : 100% 1.0/1 [00:00<00:00,  2.47it/s]\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "libcublas-11.10.3.66 | 286.1 MB  | :   1% 0.010213190034808693/1 [00:00<00:35, 36.09s/it]\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\n",
            "torchvision-0.15.2   | 8.0 MB    | :  29% 0.28580169194457333/1 [00:00<00:00,  1.33s/it]\u001b[A\n",
            "\n",
            "\n",
            "libcurand-10.3.3.53  | 51.6 MB   | :   5% 0.04569147813700344/1 [00:00<00:08,  8.73s/it] \u001b[A\u001b[A\u001b[A\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "numpy-1.25.0         | 6.5 MB    | :  25% 0.2518041469444695/1 [00:00<00:01,  1.55s/it]    \u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\n",
            "\n",
            "\n",
            "\n",
            "cuda-nvrtc-11.7.99   | 17.3 MB   | :  24% 0.24471998071810722/1 [00:00<00:01,  1.79s/it]\u001b[A\u001b[A\u001b[A\u001b[A\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "libcublas-11.10.3.66 | 286.1 MB  | :   2% 0.01507401309950374/1 [00:00<00:29, 29.53s/it] \u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\n",
            "torchvision-0.15.2   | 8.0 MB    | :  46% 0.46272654886264253/1 [00:00<00:00,  1.04it/s]\u001b[A\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "certifi-2023.5.7     | 149 KB    | : 100% 1.0/1 [00:00<00:00,  1.97it/s]                \u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "certifi-2023.5.7     | 149 KB    | : 100% 1.0/1 [00:00<00:00,  1.97it/s]\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "numpy-1.25.0         | 6.5 MB    | :  49% 0.4890811315652196/1 [00:00<00:00,  1.11it/s]\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\n",
            "\n",
            "\n",
            "\n",
            "cuda-nvrtc-11.7.99   | 17.3 MB   | :  32% 0.31786506720580715/1 [00:00<00:01,  1.64s/it]\u001b[A\u001b[A\u001b[A\u001b[A\n",
            "\n",
            "\n",
            "libcurand-10.3.3.53  | 51.6 MB   | :   7% 0.07474036489960166/1 [00:00<00:05,  6.29s/it]\u001b[A\u001b[A\u001b[A\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "libcublas-11.10.3.66 | 286.1 MB  | :   2% 0.019825604185216873/1 [00:00<00:25, 26.48s/it]\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\n",
            "torchvision-0.15.2   | 8.0 MB    | :  67% 0.6727033021280433/1 [00:00<00:00,  1.32it/s] \u001b[A\n",
            "\n",
            "\n",
            "\n",
            "cuda-nvrtc-11.7.99   | 17.3 MB   | :  41% 0.41268277191208486/1 [00:00<00:00,  1.42s/it]\u001b[A\u001b[A\u001b[A\u001b[A\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "numpy-1.25.0         | 6.5 MB    | :  78% 0.7772031843189875/1 [00:00<00:00,  1.53it/s]\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\n",
            "\n",
            "\n",
            "libcurand-10.3.3.53  | 51.6 MB   | :  11% 0.10923591793018703/1 [00:00<00:04,  4.94s/it]\u001b[A\u001b[A\u001b[A\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "libcublas-11.10.3.66 | 286.1 MB  | :   3% 0.025997210997694854/1 [00:00<00:22, 22.78s/it]\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\n",
            "torchvision-0.15.2   | 8.0 MB    | :  88% 0.8768473678027385/1 [00:00<00:00,  1.53it/s]\u001b[A\n",
            "\n",
            "\n",
            "\n",
            "cuda-nvrtc-11.7.99   | 17.3 MB   | :  49% 0.49305206447264405/1 [00:00<00:00,  1.38s/it]\u001b[A\u001b[A\u001b[A\u001b[A\n",
            "\n",
            "\n",
            "libcurand-10.3.3.53  | 51.6 MB   | :  14% 0.13919258240411644/1 [00:00<00:03,  4.35s/it]\u001b[A\u001b[A\u001b[A\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "gnutls-3.6.13        | 2.0 MB    | :   1% 0.007814829000532786/1 [00:00<01:48, 109.41s/it]\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "libcublas-11.10.3.66 | 286.1 MB  | :   3% 0.031185729999335634/1 [00:00<00:21, 22.57s/it]\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "filelock-3.12.2      | 15 KB     | : 100% 1.0/1 [00:00<00:00,  1.11it/s]\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\n",
            "\n",
            "\n",
            "\n",
            "cuda-nvrtc-11.7.99   | 17.3 MB   | :  59% 0.5896758206971365/1 [00:00<00:00,  1.25s/it] \u001b[A\u001b[A\u001b[A\u001b[A\n",
            "\n",
            "\n",
            "libcurand-10.3.3.53  | 51.6 MB   | :  16% 0.16461035832138987/1 [00:00<00:03,  4.23s/it]\u001b[A\u001b[A\u001b[A\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "libcblas-3.9.0       | 12 KB     | : 100% 1.0/1 [00:00<00:00,  1.06it/s]\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "gnutls-3.6.13        | 2.0 MB    | :  91% 0.9065201640618031/1 [00:00<00:00,  1.28it/s]   \u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "libcublas-11.10.3.66 | 286.1 MB  | :   4% 0.036647328948431195/1 [00:00<00:20, 21.15s/it]\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "markupsafe-2.1.3     | 23 KB     | :  69% 0.6851789896286383/1 [00:00<00:00,  1.44s/it]\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "mpfr-4.2.0           | 616 KB    | :   3% 0.02596525815495161/1 [00:01<00:38, 39.06s/it]\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "_openmp_mutex-4.5    | 6 KB      | : 100% 1.0/1 [00:01<00:00,  1.03s/it]\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\n",
            "\n",
            "\n",
            "\n",
            "cuda-nvrtc-11.7.99   | 17.3 MB   | :  67% 0.6718511647759106/1 [00:01<00:00,  1.31s/it]\u001b[A\u001b[A\u001b[A\u001b[A\n",
            "\n",
            "\n",
            "libcurand-10.3.3.53  | 51.6 MB   | :  19% 0.19154109709088196/1 [00:01<00:03,  4.15s/it]\u001b[A\u001b[A\u001b[A\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "tbb-2021.9.0         | 1.5 MB    | :   1% 0.010723460515163315/1 [00:01<01:38, 99.93s/it]\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "libcusolver-11.4.0.1 | 78.7 MB   | :   0% 0.00019847179143347583/1 [00:01<1:30:17, 5418.31s/it]\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "libcublas-11.10.3.66 | 286.1 MB  | :   4% 0.04156276800261719/1 [00:01<00:20, 21.24s/it] \u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\n",
            "\n",
            "\n",
            "libcurand-10.3.3.53  | 51.6 MB   | :  22% 0.22089257642392393/1 [00:01<00:03,  3.91s/it]\u001b[A\u001b[A\u001b[A\n",
            "\n",
            "\n",
            "\n",
            "cuda-nvrtc-11.7.99   | 17.3 MB   | :  77% 0.7666688694821883/1 [00:01<00:00,  1.25s/it]\u001b[A\u001b[A\u001b[A\u001b[A\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "tbb-2021.9.0         | 1.5 MB    | :  97% 0.9651114463646985/1 [00:01<00:00,  1.13it/s]  \u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "libcusolver-11.4.0.1 | 78.7 MB   | :   2% 0.017267045854712396/1 [00:01<00:48, 49.57s/it]      \u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "libcublas-11.10.3.66 | 286.1 MB  | :   5% 0.04642359106731224/1 [00:01<00:20, 21.90s/it]\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "xorg-libxdmcp-1.1.3  | 19 KB     | :  86% 0.8566349471923037/1 [00:01<00:00,  1.44s/it]\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\n",
            "\n",
            "\n",
            "libcurand-10.3.3.53  | 51.6 MB   | :  25% 0.24752072262297228/1 [00:01<00:02,  3.95s/it]\u001b[A\u001b[A\u001b[A\n",
            "\n",
            "\n",
            "\n",
            "cuda-nvrtc-11.7.99   | 17.3 MB   | :  86% 0.8596805226702512/1 [00:01<00:00,  1.23s/it]\u001b[A\u001b[A\u001b[A\u001b[A\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "cuda-nvtx-11.7.91    | 57 KB     | :  28% 0.2808364758313336/1 [00:01<00:03,  4.54s/it]\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "libcusolver-11.4.0.1 | 78.7 MB   | :   4% 0.03671728141519303/1 [00:01<00:21, 22.26s/it] \u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            " ... (more hidden) ...\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "libcublas-11.10.3.66 | 286.1 MB  | :   5% 0.0513936461109892/1 [00:01<00:21, 22.65s/it] \u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\n",
            "\n",
            "\n",
            "libcurand-10.3.3.53  | 51.6 MB   | :  28% 0.2750566465333518/1 [00:01<00:02,  3.89s/it] \u001b[A\u001b[A\u001b[A\n",
            "\n",
            "\n",
            "\n",
            "cuda-nvrtc-11.7.99   | 17.3 MB   | :  95% 0.9544982273765288/1 [00:01<00:00,  1.21s/it]\u001b[A\u001b[A\u001b[A\u001b[A\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "libcusolver-11.4.0.1 | 78.7 MB   | :   5% 0.054579742644205856/1 [00:01<00:14, 14.93s/it]\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "libcublas-11.10.3.66 | 286.1 MB  | :   6% 0.056254469175684246/1 [00:01<00:20, 22.04s/it]\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\n",
            "\n",
            "\n",
            "libcurand-10.3.3.53  | 51.6 MB   | :  31% 0.30773664414127483/1 [00:01<00:02,  3.70s/it]\u001b[A\u001b[A\u001b[A\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "libcusolver-11.4.0.1 | 78.7 MB   | :   8% 0.07502233716185387/1 [00:01<00:09, 10.69s/it] \u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "libcublas-11.10.3.66 | 286.1 MB  | :   6% 0.06198914807223458/1 [00:01<00:19, 21.04s/it] \u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\n",
            "\n",
            "\n",
            "libcurand-10.3.3.53  | 51.6 MB   | :  34% 0.3352725680516544/1 [00:01<00:02,  4.08s/it] \u001b[A\u001b[A\u001b[A\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "libcublas-11.10.3.66 | 286.1 MB  | :   7% 0.06679535514743867/1 [00:01<00:20, 22.17s/it]\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "libcusolver-11.4.0.1 | 78.7 MB   | :   9% 0.09228938301656626/1 [00:01<00:09, 10.62s/it]\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\n",
            "\n",
            "\n",
            "libcurand-10.3.3.53  | 51.6 MB   | :  36% 0.361598121680259/1 [00:01<00:02,  4.00s/it] \u001b[A\u001b[A\u001b[A\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "libcublas-11.10.3.66 | 286.1 MB  | :   7% 0.07182002618060658/1 [00:01<00:20, 21.60s/it]\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "libcusolver-11.4.0.1 | 78.7 MB   | :  11% 0.10697629558264347/1 [00:01<00:08,  9.65s/it]\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\n",
            "\n",
            "\n",
            "libcurand-10.3.3.53  | 51.6 MB   | :  39% 0.3873184901679762/1 [00:01<00:02,  4.06s/it]\u001b[A\u001b[A\u001b[A\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "libcublas-11.10.3.66 | 286.1 MB  | :   8% 0.07673546523479259/1 [00:01<00:19, 21.23s/it]\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "libcusolver-11.4.0.1 | 78.7 MB   | :  12% 0.12444181322878935/1 [00:01<00:07,  8.52s/it]\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\n",
            "\n",
            "\n",
            "libcurand-10.3.3.53  | 51.6 MB   | :  41% 0.41243367351480587/1 [00:01<00:02,  4.20s/it]\u001b[A\u001b[A\u001b[A\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "libcublas-11.10.3.66 | 286.1 MB  | :   8% 0.08148705632050572/1 [00:01<00:20, 22.59s/it]\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "libcusolver-11.4.0.1 | 78.7 MB   | :  14% 0.14329663341496957/1 [00:01<00:06,  7.43s/it]\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\n",
            "\n",
            "\n",
            "libcurand-10.3.3.53  | 51.6 MB   | :  44% 0.4432981157000665/1 [00:02<00:02,  4.33s/it] \u001b[A\u001b[A\u001b[A\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "libcublas-11.10.3.66 | 286.1 MB  | :   9% 0.0861840314167279/1 [00:02<00:20, 22.70s/it] \u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "libcusolver-11.4.0.1 | 78.7 MB   | :  16% 0.1595713203125146/1 [00:02<00:06,  7.17s/it] \u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\n",
            "\n",
            "\n",
            "libcurand-10.3.3.53  | 51.6 MB   | :  47% 0.46901848418778364/1 [00:02<00:02,  4.21s/it]\u001b[A\u001b[A\u001b[A\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "libcublas-11.10.3.66 | 286.1 MB  | :   9% 0.09066254255498626/1 [00:02<00:20, 22.66s/it]\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "libcusolver-11.4.0.1 | 78.7 MB   | :  18% 0.17544906362719265/1 [00:02<00:06,  7.46s/it]\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\n",
            "\n",
            "\n",
            "libcurand-10.3.3.53  | 51.6 MB   | :  49% 0.4932258898232822/1 [00:02<00:02,  4.55s/it] \u001b[A\u001b[A\u001b[A\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "gmp-6.2.1            | 806 KB    | : 100% 1.0/1 [00:02<00:00,  2.24s/it]                 \u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "gmp-6.2.1            | 806 KB    | : 100% 1.0/1 [00:02<00:00,  2.24s/it]\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "libcublas-11.10.3.66 | 286.1 MB  | :  10% 0.09514105369324462/1 [00:02<00:21, 24.31s/it]\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "libcusolver-11.4.0.1 | 78.7 MB   | :  19% 0.19172375052473767/1 [00:02<00:05,  7.27s/it]\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\n",
            "\n",
            "\n",
            "libcurand-10.3.3.53  | 51.6 MB   | :  52% 0.515920332606562/1 [00:02<00:02,  4.51s/it] \u001b[A\u001b[A\u001b[A\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "libcublas-11.10.3.66 | 286.1 MB  | :  10% 0.0993464848840482/1 [00:02<00:21, 24.17s/it] \u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "libcusolver-11.4.0.1 | 78.7 MB   | :  21% 0.20938773996231702/1 [00:02<00:05,  6.91s/it]\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\n",
            "\n",
            "\n",
            "libcurand-10.3.3.53  | 51.6 MB   | :  54% 0.539522553101173/1 [00:02<00:02,  4.47s/it]\u001b[A\u001b[A\u001b[A\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "libcublas-11.10.3.66 | 286.1 MB  | :  10% 0.10355191607485177/1 [00:02<00:23, 25.96s/it]\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "libcusolver-11.4.0.1 | 78.7 MB   | :  22% 0.22467006790269464/1 [00:02<00:05,  6.81s/it]\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\n",
            "\n",
            "\n",
            "libcurand-10.3.3.53  | 51.6 MB   | :  56% 0.5625195884548967/1 [00:02<00:01,  4.47s/it]\u001b[A\u001b[A\u001b[A\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "libcublas-11.10.3.66 | 286.1 MB  | :  11% 0.10786657924463726/1 [00:02<00:22, 25.27s/it]\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "libcusolver-11.4.0.1 | 78.7 MB   | :  24% 0.2399523958430723/1 [00:02<00:05,  6.82s/it] \u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\n",
            "\n",
            "\n",
            "libcurand-10.3.3.53  | 51.6 MB   | :  59% 0.5918710677879386/1 [00:02<00:01,  4.29s/it]\u001b[A\u001b[A\u001b[A\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "libcusolver-11.4.0.1 | 78.7 MB   | :  26% 0.25503625199201646/1 [00:02<00:05,  6.92s/it]\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "libcublas-11.10.3.66 | 286.1 MB  | :  11% 0.11190816246696798/1 [00:02<00:23, 26.43s/it]\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\n",
            "\n",
            "\n",
            "libcurand-10.3.3.53  | 51.6 MB   | :  62% 0.6154732882825497/1 [00:02<00:01,  4.28s/it]\u001b[A\u001b[A\u001b[A\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "libcublas-11.10.3.66 | 286.1 MB  | :  12% 0.11578589772082583/1 [00:02<00:23, 26.60s/it]\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\n",
            "\n",
            "\n",
            "libcurand-10.3.3.53  | 51.6 MB   | :  65% 0.6451273601860353/1 [00:02<00:01,  3.97s/it]\u001b[A\u001b[A\u001b[A\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "libcusolver-11.4.0.1 | 78.7 MB   | :  27% 0.26992163634952715/1 [00:02<00:05,  8.05s/it]\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "libcublas-11.10.3.66 | 286.1 MB  | :  12% 0.12064672078552087/1 [00:02<00:22, 25.07s/it]\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "libcusolver-11.4.0.1 | 78.7 MB   | :  28% 0.2844100771241709/1 [00:03<00:05,  7.90s/it] \u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\n",
            "\n",
            "\n",
            "libcurand-10.3.3.53  | 51.6 MB   | :  67% 0.6705451361033088/1 [00:03<00:01,  4.17s/it]\u001b[A\u001b[A\u001b[A\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "libcublas-11.10.3.66 | 286.1 MB  | :  12% 0.12468830400785158/1 [00:03<00:21, 25.11s/it]\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "libcusolver-11.4.0.1 | 78.7 MB   | :  30% 0.2981046307330807/1 [00:03<00:05,  7.83s/it]\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\n",
            "\n",
            "\n",
            "libcurand-10.3.3.53  | 51.6 MB   | :  69% 0.6947525417388073/1 [00:03<00:01,  4.20s/it]\u001b[A\u001b[A\u001b[A\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "libcublas-11.10.3.66 | 286.1 MB  | :  13% 0.13031375092542/1 [00:03<00:20, 23.18s/it]   \u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "libcusolver-11.4.0.1 | 78.7 MB   | :  31% 0.31338695867345834/1 [00:03<00:05,  7.47s/it]\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\n",
            "\n",
            "\n",
            "libcurand-10.3.3.53  | 51.6 MB   | :  72% 0.7189599473743058/1 [00:03<00:01,  4.19s/it]\u001b[A\u001b[A\u001b[A\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "libcublas-11.10.3.66 | 286.1 MB  | :  13% 0.13468303008469645/1 [00:03<00:20, 23.16s/it]\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "libcusolver-11.4.0.1 | 78.7 MB   | :  33% 0.3316463634853381/1 [00:03<00:04,  7.01s/it] \u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\n",
            "\n",
            "\n",
            "libcurand-10.3.3.53  | 51.6 MB   | :  74% 0.7431673530098043/1 [00:03<00:01,  4.26s/it]\u001b[A\u001b[A\u001b[A\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "libcublas-11.10.3.66 | 286.1 MB  | :  14% 0.1390523092439729/1 [00:03<00:20, 23.92s/it] \u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "libcusolver-11.4.0.1 | 78.7 MB   | :  35% 0.3479210503828831/1 [00:03<00:04,  6.78s/it]\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\n",
            "\n",
            "\n",
            "libcurand-10.3.3.53  | 51.6 MB   | :  77% 0.7667695735044153/1 [00:03<00:01,  4.40s/it]\u001b[A\u001b[A\u001b[A\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "libcublas-11.10.3.66 | 286.1 MB  | :  14% 0.1432577404347765/1 [00:03<00:20, 24.36s/it]\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "libcusolver-11.4.0.1 | 78.7 MB   | :  37% 0.36598198340332944/1 [00:03<00:04,  6.64s/it]\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\n",
            "\n",
            "\n",
            "libcurand-10.3.3.53  | 51.6 MB   | :  79% 0.7921873494216888/1 [00:03<00:00,  4.36s/it]\u001b[A\u001b[A\u001b[A\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "libcublas-11.10.3.66 | 286.1 MB  | :  15% 0.1474085556360891/1 [00:03<00:20, 24.35s/it]\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "libcusolver-11.4.0.1 | 78.7 MB   | :  38% 0.3812643113437071/1 [00:03<00:04,  6.64s/it] \u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\n",
            "\n",
            "\n",
            "libcurand-10.3.3.53  | 51.6 MB   | :  82% 0.8154869773458561/1 [00:03<00:00,  4.40s/it]\u001b[A\u001b[A\u001b[A\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "libcublas-11.10.3.66 | 286.1 MB  | :  15% 0.15155937083740173/1 [00:03<00:22, 26.84s/it]\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "libcusolver-11.4.0.1 | 78.7 MB   | :  40% 0.3975389982412521/1 [00:03<00:03,  6.49s/it]\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\n",
            "\n",
            "\n",
            "libcurand-10.3.3.53  | 51.6 MB   | :  84% 0.8406021606926858/1 [00:03<00:00,  4.33s/it]\u001b[A\u001b[A\u001b[A\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "libcublas-11.10.3.66 | 286.1 MB  | :  16% 0.15658404187056965/1 [00:03<00:21, 25.63s/it]\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "libcusolver-11.4.0.1 | 78.7 MB   | :  41% 0.4140121569302306/1 [00:03<00:03,  6.61s/it]\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\n",
            "\n",
            "\n",
            "libcurand-10.3.3.53  | 51.6 MB   | :  87% 0.8684406771735091/1 [00:03<00:00,  4.17s/it]\u001b[A\u001b[A\u001b[A\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "libcublas-11.10.3.66 | 286.1 MB  | :  16% 0.1620456408196652/1 [00:03<00:19, 23.47s/it] \u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "libcusolver-11.4.0.1 | 78.7 MB   | :  43% 0.42929448487060823/1 [00:03<00:03,  6.68s/it]\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\n",
            "\n",
            "\n",
            "libcurand-10.3.3.53  | 51.6 MB   | :  89% 0.8926480828090076/1 [00:04<00:00,  4.42s/it]\u001b[A\u001b[A\u001b[A\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "libcublas-11.10.3.66 | 286.1 MB  | :  17% 0.1666879999263964/1 [00:04<00:19, 23.09s/it]\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "libcusolver-11.4.0.1 | 78.7 MB   | :  45% 0.4493401358053893/1 [00:04<00:03,  6.09s/it] \u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\n",
            "\n",
            "\n",
            "libcurand-10.3.3.53  | 51.6 MB   | :  92% 0.9198814141489434/1 [00:04<00:00,  4.24s/it]\u001b[A\u001b[A\u001b[A\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "libcublas-11.10.3.66 | 286.1 MB  | :  17% 0.17111189507516383/1 [00:04<00:19, 23.31s/it]\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "libcusolver-11.4.0.1 | 78.7 MB   | :  47% 0.46879037136586993/1 [00:04<00:03,  5.93s/it]\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\n",
            "\n",
            "\n",
            "libcurand-10.3.3.53  | 51.6 MB   | :  95% 0.9501406711933166/1 [00:04<00:00,  4.06s/it]\u001b[A\u001b[A\u001b[A\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "libcublas-11.10.3.66 | 286.1 MB  | :  18% 0.17548117423444026/1 [00:04<00:19, 23.66s/it]\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "libcusolver-11.4.0.1 | 78.7 MB   | :  49% 0.48863755050921753/1 [00:04<00:02,  5.81s/it]\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\n",
            "\n",
            "\n",
            "libcurand-10.3.3.53  | 51.6 MB   | :  98% 0.9782817802445836/1 [00:04<00:00,  4.01s/it]\u001b[A\u001b[A\u001b[A\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "libcublas-11.10.3.66 | 286.1 MB  | :  18% 0.18094277318353583/1 [00:04<00:18, 22.16s/it]\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "libcusolver-11.4.0.1 | 78.7 MB   | :  51% 0.5106679193583333/1 [00:04<00:02,  5.59s/it] \u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "libcublas-11.10.3.66 | 286.1 MB  | :  19% 0.18547590031128514/1 [00:04<00:18, 23.29s/it]\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "libcusolver-11.4.0.1 | 78.7 MB   | :  53% 0.5291257959616466/1 [00:04<00:02,  5.69s/it]\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "libcublas-11.10.3.66 | 286.1 MB  | :  19% 0.19050057134445306/1 [00:04<00:18, 22.41s/it]\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "libcusolver-11.4.0.1 | 78.7 MB   | :  55% 0.546789785399226/1 [00:04<00:02,  5.70s/it] \u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "libcublas-11.10.3.66 | 286.1 MB  | :  20% 0.19618063425151244/1 [00:04<00:17, 21.41s/it]\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "libcusolver-11.4.0.1 | 78.7 MB   | :  56% 0.5648507184196723/1 [00:04<00:02,  5.82s/it]\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "libcublas-11.10.3.66 | 286.1 MB  | :  20% 0.2008776093477346/1 [00:04<00:20, 25.26s/it] \u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "libcusolver-11.4.0.1 | 78.7 MB   | :  58% 0.5821177642743847/1 [00:04<00:02,  6.65s/it]\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "libcublas-11.10.3.66 | 286.1 MB  | :  21% 0.20633920829683017/1 [00:04<00:18, 23.04s/it]\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "libcusolver-11.4.0.1 | 78.7 MB   | :  60% 0.5975985640061957/1 [00:04<00:02,  6.62s/it]\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "libcusolver-11.4.0.1 | 78.7 MB   | :  62% 0.6150640816523416/1 [00:05<00:02,  6.36s/it]\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "libcublas-11.10.3.66 | 286.1 MB  | :  21% 0.21092695141407045/1 [00:05<00:19, 24.37s/it]\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "libcusolver-11.4.0.1 | 78.7 MB   | :  63% 0.6311402967584532/1 [00:05<00:02,  6.92s/it]\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "libcublas-11.10.3.66 | 286.1 MB  | :  22% 0.21518699859436496/1 [00:05<00:19, 24.87s/it]\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "libcusolver-11.4.0.1 | 78.7 MB   | :  65% 0.6505905323189338/1 [00:05<00:02,  6.37s/it]\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "libcublas-11.10.3.66 | 286.1 MB  | :  22% 0.2193378137956776/1 [00:05<00:19, 24.87s/it] \u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "libcublas-11.10.3.66 | 286.1 MB  | :  22% 0.22430786883935455/1 [00:05<00:18, 24.28s/it]\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "libcusolver-11.4.0.1 | 78.7 MB   | :  67% 0.6692468807136805/1 [00:05<00:02,  6.39s/it]\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "libcublas-11.10.3.66 | 286.1 MB  | :  23% 0.22933253987252247/1 [00:05<00:17, 22.96s/it]\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "libcusolver-11.4.0.1 | 78.7 MB   | :  69% 0.6859185111940925/1 [00:05<00:01,  6.28s/it]\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "libcublas-11.10.3.66 | 286.1 MB  | :  24% 0.23659646647481955/1 [00:05<00:14, 19.34s/it]\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "libcusolver-11.4.0.1 | 78.7 MB   | :  70% 0.7029870852573714/1 [00:05<00:01,  6.19s/it]\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "libcublas-11.10.3.66 | 286.1 MB  | :  24% 0.24244037735035182/1 [00:05<00:14, 18.65s/it]\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "libcusolver-11.4.0.1 | 78.7 MB   | :  73% 0.731170079640925/1 [00:05<00:01,  5.12s/it] \u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "libcublas-11.10.3.66 | 286.1 MB  | :  25% 0.24790197629944735/1 [00:05<00:14, 18.80s/it]\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "libcusolver-11.4.0.1 | 78.7 MB   | :  75% 0.7510172587842726/1 [00:05<00:01,  5.11s/it]\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "libcublas-11.10.3.66 | 286.1 MB  | :  25% 0.25385511915396153/1 [00:05<00:13, 18.18s/it]\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "libcusolver-11.4.0.1 | 78.7 MB   | :  77% 0.7710629097190537/1 [00:05<00:01,  5.08s/it]\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "libcublas-11.10.3.66 | 286.1 MB  | :  26% 0.2619382855986229/1 [00:06<00:11, 15.98s/it] \u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "libcusolver-11.4.0.1 | 78.7 MB   | :  79% 0.7913070324452681/1 [00:06<00:01,  5.05s/it]\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "libcusolver-11.4.0.1 | 78.7 MB   | :  81% 0.8113526833800492/1 [00:06<00:00,  5.04s/it]\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "libcublas-11.10.3.66 | 286.1 MB  | :  27% 0.2682737403795738/1 [00:06<00:12, 16.67s/it]\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "libcusolver-11.4.0.1 | 78.7 MB   | :  83% 0.8313983343148302/1 [00:06<00:00,  5.18s/it]\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "libcublas-11.10.3.66 | 286.1 MB  | :  28% 0.27581074692932567/1 [00:06<00:11, 16.11s/it]\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "libcusolver-11.4.0.1 | 78.7 MB   | :  85% 0.8532302313725126/1 [00:06<00:00,  5.06s/it]\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "libcublas-11.10.3.66 | 286.1 MB  | :  28% 0.2831292895211137/1 [00:06<00:11, 15.50s/it] \u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "libcusolver-11.4.0.1 | 78.7 MB   | :  88% 0.875459072013062/1 [00:06<00:00,  4.99s/it] \u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "libcublas-11.10.3.66 | 286.1 MB  | :  29% 0.29050244810239273/1 [00:06<00:10, 14.90s/it]\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "libcusolver-11.4.0.1 | 78.7 MB   | :  90% 0.8957031947392765/1 [00:06<00:00,  5.07s/it]\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "libcublas-11.10.3.66 | 286.1 MB  | :  30% 0.2972748307992712/1 [00:06<00:12, 17.22s/it] \u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "libcusolver-11.4.0.1 | 78.7 MB   | :  92% 0.9155503738826241/1 [00:06<00:00,  5.20s/it]\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "libcublas-11.10.3.66 | 286.1 MB  | :  30% 0.30350105360124013/1 [00:06<00:11, 17.22s/it]\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "libcusolver-11.4.0.1 | 78.7 MB   | :  94% 0.9417486503518429/1 [00:06<00:00,  4.71s/it]\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "libcublas-11.10.3.66 | 286.1 MB  | :  31% 0.30950881244524525/1 [00:06<00:12, 17.59s/it]\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "libcusolver-11.4.0.1 | 78.7 MB   | :  97% 0.9673515114467612/1 [00:06<00:00,  4.52s/it]\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "libcublas-11.10.3.66 | 286.1 MB  | :  32% 0.3156804192577232/1 [00:06<00:11, 17.29s/it] \u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "libcusolver-11.4.0.1 | 78.7 MB   | :  99% 0.9895803520873105/1 [00:06<00:00,  4.58s/it]\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "libcublas-11.10.3.66 | 286.1 MB  | :  32% 0.32190664205969216/1 [00:07<00:11, 16.93s/it]\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "libcublas-11.10.3.66 | 286.1 MB  | :  33% 0.3279144009036973/1 [00:07<00:11, 17.51s/it] \u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "libcublas-11.10.3.66 | 286.1 MB  | :  33% 0.3337036957897386/1 [00:07<00:12, 19.10s/it]\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "libcublas-11.10.3.66 | 286.1 MB  | :  34% 0.33927452671781605/1 [00:07<00:12, 18.94s/it]\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "libcublas-11.10.3.66 | 286.1 MB  | :  35% 0.3471938451940046/1 [00:07<00:10, 16.73s/it] \u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "numpy-1.25.0         | 6.5 MB    | : 100% 1.0/1 [00:07<00:00, 11.40s/it]               \u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "numpy-1.25.0         | 6.5 MB    | : 100% 1.0/1 [00:07<00:00, 11.40s/it]\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "libcublas-11.10.3.66 | 286.1 MB  | :  35% 0.35331083601699165/1 [00:07<00:11, 17.49s/it]\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "filelock-3.12.2      | 15 KB     | : 100% 1.0/1 [00:07<00:00,  1.11it/s]\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "libcublas-11.10.3.66 | 286.1 MB  | :  36% 0.35915474689252386/1 [00:07<00:12, 19.31s/it]\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "libcblas-3.9.0       | 12 KB     | : 100% 1.0/1 [00:07<00:00,  1.06it/s]\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "libcublas-11.10.3.66 | 286.1 MB  | :  36% 0.3645071138626375/1 [00:07<00:12, 19.99s/it] \u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "libcublas-11.10.3.66 | 286.1 MB  | :  37% 0.36964101687478734/1 [00:08<00:21, 34.49s/it]\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "libcublas-11.10.3.66 | 286.1 MB  | :  37% 0.37379183207609995/1 [00:08<00:20, 32.10s/it]\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "libcublas-11.10.3.66 | 286.1 MB  | :  38% 0.3804003668045056/1 [00:08<00:16, 26.23s/it] \u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "libcublas-11.10.3.66 | 286.1 MB  | :  39% 0.386080429711565/1 [00:08<00:14, 23.65s/it] \u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "libcublas-11.10.3.66 | 286.1 MB  | :  39% 0.3942728281352083/1 [00:08<00:11, 19.31s/it]\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "libcublas-11.10.3.66 | 286.1 MB  | :  40% 0.40071751489514107/1 [00:08<00:10, 18.24s/it]\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "libcublas-11.10.3.66 | 286.1 MB  | :  41% 0.4086914493608206/1 [00:08<00:09, 16.65s/it] \u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "libcublas-11.10.3.66 | 286.1 MB  | :  42% 0.4151907521102443/1 [00:08<00:09, 17.05s/it]\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "libcublas-11.10.3.66 | 286.1 MB  | :  42% 0.42141697491221325/1 [00:09<00:10, 17.36s/it]\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "libcublas-11.10.3.66 | 286.1 MB  | :  43% 0.42742473375621837/1 [00:09<00:11, 19.41s/it]\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "libcublas-11.10.3.66 | 286.1 MB  | :  43% 0.43332326062124155/1 [00:09<00:11, 19.64s/it]\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "libcublas-11.10.3.66 | 286.1 MB  | :  44% 0.44031410727608383/1 [00:09<00:10, 18.12s/it]\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "libcublas-11.10.3.66 | 286.1 MB  | :  45% 0.4460487861726342/1 [00:09<00:10, 18.11s/it] \u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "libcublas-11.10.3.66 | 286.1 MB  | :  45% 0.45200192902714836/1 [00:09<00:09, 17.79s/it]\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "libcublas-11.10.3.66 | 286.1 MB  | :  46% 0.4577366079236987/1 [00:09<00:09, 17.76s/it] \u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "libcublas-11.10.3.66 | 286.1 MB  | :  46% 0.4640720627046495/1 [00:09<00:09, 17.22s/it]\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "libcublas-11.10.3.66 | 286.1 MB  | :  47% 0.46997058956967275/1 [00:09<00:09, 17.35s/it]\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "libcublas-11.10.3.66 | 286.1 MB  | :  48% 0.47581450044520496/1 [00:10<00:09, 18.29s/it]\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "libcublas-11.10.3.66 | 286.1 MB  | :  48% 0.48138533137328243/1 [00:10<00:10, 19.94s/it]\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "libcublas-11.10.3.66 | 286.1 MB  | :  49% 0.48651923438543226/1 [00:10<00:10, 21.20s/it]\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "libcublas-11.10.3.66 | 286.1 MB  | :  49% 0.4919262173450369/1 [00:10<00:10, 20.42s/it] \u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "libcublas-11.10.3.66 | 286.1 MB  | :  50% 0.49777012822056915/1 [00:10<00:09, 19.44s/it]\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "libcublas-11.10.3.66 | 286.1 MB  | :  50% 0.504050967012029/1 [00:10<00:09, 18.81s/it]  \u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "libcublas-11.10.3.66 | 286.1 MB  | :  51% 0.5094579499716336/1 [00:10<00:09, 19.26s/it]\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "libcublas-11.10.3.66 | 286.1 MB  | :  52% 0.5154657088156387/1 [00:10<00:08, 18.45s/it]\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "libcublas-11.10.3.66 | 286.1 MB  | :  52% 0.5218011635965896/1 [00:10<00:08, 17.72s/it]\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "libcublas-11.10.3.66 | 286.1 MB  | :  53% 0.5284096983249952/1 [00:11<00:08, 17.07s/it]\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "libcublas-11.10.3.66 | 286.1 MB  | :  53% 0.5343082251900184/1 [00:11<00:08, 17.70s/it]\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "libcublas-11.10.3.66 | 286.1 MB  | :  54% 0.5411352238763879/1 [00:11<00:07, 16.75s/it]\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "libcublas-11.10.3.66 | 286.1 MB  | :  55% 0.547142982720393/1 [00:11<00:07, 17.42s/it] \u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "libcublas-11.10.3.66 | 286.1 MB  | :  55% 0.5529322776064343/1 [00:11<00:07, 17.63s/it]\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "libcublas-11.10.3.66 | 286.1 MB  | :  56% 0.5597046603033128/1 [00:11<00:07, 16.75s/it]\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "libcublas-11.10.3.66 | 286.1 MB  | :  57% 0.5657124191473178/1 [00:11<00:08, 19.42s/it]\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "libcublas-11.10.3.66 | 286.1 MB  | :  57% 0.5713924820543772/1 [00:11<00:08, 19.17s/it]\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "libcublas-11.10.3.66 | 286.1 MB  | :  58% 0.5769633129824547/1 [00:11<00:07, 18.89s/it]\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "libcublas-11.10.3.66 | 286.1 MB  | :  58% 0.5829164558369688/1 [00:12<00:07, 18.53s/it]\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "libcublas-11.10.3.66 | 286.1 MB  | :  59% 0.5892519106179197/1 [00:12<00:07, 17.80s/it]\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "libcublas-11.10.3.66 | 286.1 MB  | :  59% 0.59498658951447/1 [00:12<00:07, 17.79s/it]  \u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\n",
            "torchvision-0.15.2   | 8.0 MB    | : 100% 1.0/1 [00:12<00:00,  1.53it/s]               \u001b[A\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "libcublas-11.10.3.66 | 286.1 MB  | :  60% 0.6006666524215294/1 [00:12<00:07, 18.45s/it]\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "markupsafe-2.1.3     | 23 KB     | : 100% 1.0/1 [00:12<00:00, 15.26s/it]               \u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "markupsafe-2.1.3     | 23 KB     | : 100% 1.0/1 [00:12<00:00, 15.26s/it]\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "_openmp_mutex-4.5    | 6 KB      | : 100% 1.0/1 [00:12<00:00,  1.03s/it]\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "libcublas-11.10.3.66 | 286.1 MB  | :  61% 0.6075482670973898/1 [00:12<00:06, 17.18s/it]\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "libcublas-11.10.3.66 | 286.1 MB  | :  61% 0.6134467939624131/1 [00:12<00:07, 18.31s/it]\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "libcublas-11.10.3.66 | 286.1 MB  | :  62% 0.6203830246277644/1 [00:12<00:06, 17.28s/it]\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "mpfr-4.2.0           | 616 KB    | : 100% 1.0/1 [00:12<00:00, 12.55s/it]                \u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "mpfr-4.2.0           | 616 KB    | : 100% 1.0/1 [00:12<00:00, 12.55s/it]\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "libcublas-11.10.3.66 | 286.1 MB  | :  63% 0.6262815514927876/1 [00:12<00:06, 17.59s/it]\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "libcublas-11.10.3.66 | 286.1 MB  | :  63% 0.632016230389338/1 [00:13<00:07, 20.41s/it] \u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "libcublas-11.10.3.66 | 286.1 MB  | :  64% 0.6394440049601079/1 [00:13<00:06, 18.12s/it]\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "tbb-2021.9.0         | 1.5 MB    | : 100% 1.0/1 [00:13<00:00,  1.13it/s]               \u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "libcublas-11.10.3.66 | 286.1 MB  | :  65% 0.6452332998461492/1 [00:13<00:06, 18.19s/it]\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "xorg-libxdmcp-1.1.3  | 19 KB     | : 100% 1.0/1 [00:13<00:00, 17.34s/it]               \u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "xorg-libxdmcp-1.1.3  | 19 KB     | : 100% 1.0/1 [00:13<00:00, 17.34s/it]\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "gnutls-3.6.13        | 2.0 MB    | : 100% 1.0/1 [00:13<00:00,  1.28it/s]               \u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "libcublas-11.10.3.66 | 286.1 MB  | :  65% 0.6509133627532085/1 [00:13<00:06, 18.62s/it]\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "cuda-nvtx-11.7.91    | 57 KB     | : 100% 1.0/1 [00:13<00:00, 14.26s/it]               \u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "cuda-nvtx-11.7.91    | 57 KB     | : 100% 1.0/1 [00:13<00:00, 14.26s/it]\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "libcublas-11.10.3.66 | 286.1 MB  | :  66% 0.6564295776917951/1 [00:13<00:06, 19.47s/it]\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            " ... (more hidden) ...\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            " ... (more hidden) ...\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "libcublas-11.10.3.66 | 286.1 MB  | :  66% 0.6616727126829268/1 [00:13<00:06, 19.85s/it]\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "libcublas-11.10.3.66 | 286.1 MB  | :  67% 0.6684450953798053/1 [00:13<00:06, 18.18s/it]\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "libcublas-11.10.3.66 | 286.1 MB  | :  68% 0.675053630108211/1 [00:13<00:05, 17.26s/it] \u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "libcublas-11.10.3.66 | 286.1 MB  | :  68% 0.6814437008786527/1 [00:13<00:05, 17.00s/it]\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "libcublas-11.10.3.66 | 286.1 MB  | :  69% 0.6887076274809498/1 [00:13<00:04, 15.93s/it]\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "libcublas-11.10.3.66 | 286.1 MB  | :  70% 0.6961900180412107/1 [00:14<00:04, 15.10s/it]\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "libcublas-11.10.3.66 | 286.1 MB  | :  70% 0.7040547205279083/1 [00:14<00:04, 14.41s/it]\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "libcublas-11.10.3.66 | 286.1 MB  | :  71% 0.7110455671827507/1 [00:14<00:04, 16.00s/it]\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "libcublas-11.10.3.66 | 286.1 MB  | :  72% 0.7176541019111563/1 [00:14<00:04, 16.03s/it]\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "libcublas-11.10.3.66 | 286.1 MB  | :  72% 0.724044172681598/1 [00:14<00:04, 16.60s/it] \u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "libcublas-11.10.3.66 | 286.1 MB  | :  73% 0.7304888594415309/1 [00:14<00:04, 16.39s/it]\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "libcublas-11.10.3.66 | 286.1 MB  | :  74% 0.7374250901068822/1 [00:14<00:04, 16.59s/it]\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "libcublas-11.10.3.66 | 286.1 MB  | :  74% 0.7435420809298692/1 [00:14<00:04, 17.82s/it]\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "libcublas-11.10.3.66 | 286.1 MB  | :  75% 0.749932151700311/1 [00:14<00:04, 17.20s/it] \u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "libcublas-11.10.3.66 | 286.1 MB  | :  76% 0.7558306785653343/1 [00:15<00:04, 17.65s/it]\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "libcublas-11.10.3.66 | 286.1 MB  | :  76% 0.7615653574618846/1 [00:15<00:04, 20.17s/it]\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "libcublas-11.10.3.66 | 286.1 MB  | :  77% 0.7668084924530163/1 [00:15<00:04, 20.22s/it]\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "libcublas-11.10.3.66 | 286.1 MB  | :  77% 0.7729800992654943/1 [00:15<00:04, 19.27s/it]\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "libcublas-11.10.3.66 | 286.1 MB  | :  78% 0.7785509301935718/1 [00:15<00:04, 19.00s/it]\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "libcublas-11.10.3.66 | 286.1 MB  | :  78% 0.7839032971636853/1 [00:15<00:04, 19.11s/it]\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "libcublas-11.10.3.66 | 286.1 MB  | :  79% 0.7892010481443081/1 [00:15<00:04, 20.04s/it]\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "libcublas-11.10.3.66 | 286.1 MB  | :  79% 0.7942803351669669/1 [00:15<00:04, 21.41s/it]\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "libcublas-11.10.3.66 | 286.1 MB  | :  80% 0.79903192625268/1 [00:16<00:04, 21.89s/it]  \u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "libcublas-11.10.3.66 | 286.1 MB  | :  80% 0.8036742853594113/1 [00:16<00:04, 22.28s/it]\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "libcublas-11.10.3.66 | 286.1 MB  | :  81% 0.8082074124871607/1 [00:16<00:04, 22.44s/it]\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "libcublas-11.10.3.66 | 286.1 MB  | :  81% 0.812685923625419/1 [00:16<00:04, 23.66s/it] \u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "libcublas-11.10.3.66 | 286.1 MB  | :  82% 0.8177652106480778/1 [00:16<00:04, 23.22s/it]\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "libcublas-11.10.3.66 | 286.1 MB  | :  82% 0.823718353502592/1 [00:16<00:03, 22.29s/it] \u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "libcublas-11.10.3.66 | 286.1 MB  | :  83% 0.829835344325579/1 [00:16<00:03, 21.96s/it]\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "libcublas-11.10.3.66 | 286.1 MB  | :  83% 0.834914631348238/1 [00:16<00:03, 21.63s/it]\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "libcublas-11.10.3.66 | 286.1 MB  | :  84% 0.8395569904549691/1 [00:16<00:03, 22.15s/it]\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "libcublas-11.10.3.66 | 286.1 MB  | :  84% 0.8441447335722094/1 [00:17<00:03, 22.71s/it]\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "libcublas-11.10.3.66 | 286.1 MB  | :  85% 0.8485686287209768/1 [00:17<00:03, 23.78s/it]\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "libcublas-11.10.3.66 | 286.1 MB  | :  86% 0.8556140913653101/1 [00:17<00:02, 20.31s/it]\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "libcublas-11.10.3.66 | 286.1 MB  | :  86% 0.8609664583354237/1 [00:17<00:02, 20.60s/it]\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "libcublas-11.10.3.66 | 286.1 MB  | :  87% 0.8658818973896097/1 [00:17<00:02, 21.20s/it]\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "libcublas-11.10.3.66 | 286.1 MB  | :  87% 0.8706334884753228/1 [00:17<00:03, 28.20s/it]\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "libcublas-11.10.3.66 | 286.1 MB  | :  87% 0.8746204557081626/1 [00:18<00:06, 54.48s/it]\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "libcublas-11.10.3.66 | 286.1 MB  | :  88% 0.8797543587203124/1 [00:18<00:05, 44.04s/it]\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "libcublas-11.10.3.66 | 286.1 MB  | :  88% 0.8848336457429713/1 [00:18<00:04, 36.60s/it]\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "libcublas-11.10.3.66 | 286.1 MB  | :  89% 0.8890936929232658/1 [00:18<00:03, 33.07s/it]\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "libcublas-11.10.3.66 | 286.1 MB  | :  89% 0.8931898921350875/1 [00:18<00:03, 30.73s/it]\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "libcublas-11.10.3.66 | 286.1 MB  | :  90% 0.8972860913469092/1 [00:18<00:03, 30.11s/it]\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "libcublas-11.10.3.66 | 286.1 MB  | :  90% 0.9018738344641495/1 [00:18<00:02, 28.57s/it]\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "libcublas-11.10.3.66 | 286.1 MB  | :  91% 0.9058061857074983/1 [00:18<00:02, 27.88s/it]\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "libcublas-11.10.3.66 | 286.1 MB  | :  91% 0.9113224006460847/1 [00:19<00:02, 25.25s/it]\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "libcublas-11.10.3.66 | 286.1 MB  | :  92% 0.9173847754795809/1 [00:19<00:01, 22.62s/it]\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "libcublas-11.10.3.66 | 286.1 MB  | :  92% 0.9228463744286763/1 [00:19<00:01, 21.44s/it]\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "libcublas-11.10.3.66 | 286.1 MB  | :  93% 0.9277071974933714/1 [00:19<00:01, 21.62s/it]\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "libcublas-11.10.3.66 | 286.1 MB  | :  93% 0.9324587885790846/1 [00:19<00:01, 22.13s/it]\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "libcublas-11.10.3.66 | 286.1 MB  | :  94% 0.9374834596122524/1 [00:19<00:01, 22.02s/it]\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "libcublas-11.10.3.66 | 286.1 MB  | :  94% 0.9422896666874566/1 [00:19<00:01, 22.22s/it]\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "libcublas-11.10.3.66 | 286.1 MB  | :  95% 0.947969729594516/1 [00:19<00:01, 21.74s/it] \u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "libcublas-11.10.3.66 | 286.1 MB  | :  95% 0.9538136404700482/1 [00:19<00:00, 20.87s/it]\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "libcublas-11.10.3.66 | 286.1 MB  | :  96% 0.9592206234296528/1 [00:20<00:00, 20.68s/it]\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "libcublas-11.10.3.66 | 286.1 MB  | :  96% 0.9640814464943478/1 [00:20<00:00, 20.73s/it]\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "libcublas-11.10.3.66 | 286.1 MB  | :  97% 0.9689422695590428/1 [00:20<00:00, 20.93s/it]\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "libcublas-11.10.3.66 | 286.1 MB  | :  97% 0.973748476634247/1 [00:20<00:00, 21.05s/it] \u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "libcublas-11.10.3.66 | 286.1 MB  | :  98% 0.9785000677199601/1 [00:20<00:00, 22.65s/it]\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "libcublas-11.10.3.66 | 286.1 MB  | :  98% 0.9829785788582185/1 [00:20<00:00, 23.32s/it]\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "libcublas-11.10.3.66 | 286.1 MB  | :  99% 0.9873478580174949/1 [00:20<00:00, 24.34s/it]\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "libcublas-11.10.3.66 | 286.1 MB  | :  99% 0.9914986732188076/1 [00:20<00:00, 24.98s/it]\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "libcublas-11.10.3.66 | 286.1 MB  | : 100% 0.9956494884201201/1 [00:20<00:00, 25.88s/it]\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "libcublas-11.10.3.66 | 286.1 MB  | : 100% 0.9995818396634689/1 [00:21<00:00, 27.61s/it]\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\n",
            "\n",
            "\n",
            "\n",
            "cuda-nvrtc-11.7.99   | 17.3 MB   | : 100% 1.0/1 [00:34<00:00,  1.21s/it]               \u001b[A\u001b[A\u001b[A\u001b[A\n",
            "\n",
            "\n",
            "libcurand-10.3.3.53  | 51.6 MB   | : 100% 1.0/1 [00:46<00:00,  4.01s/it]               \u001b[A\u001b[A\u001b[A\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "libcusolver-11.4.0.1 | 78.7 MB   | : 100% 1.0/1 [01:15<00:00,  4.58s/it]               \u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "libcublas-11.10.3.66 | 286.1 MB  | : 100% 1.0/1 [03:04<00:00, 27.61s/it]               \u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "                                                                        \n",
            "                                                                        \u001b[A\n",
            "\n",
            "                                                                        \u001b[A\u001b[A\n",
            "\n",
            "\n",
            "                                                                        \u001b[A\u001b[A\u001b[A\n",
            "\n",
            "\n",
            "\n",
            "                                                                        \u001b[A\u001b[A\u001b[A\u001b[A\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "                                                                        \u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "                                                                        \u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "                                                                        \u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "                                                                        \u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "                                                                        \u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "                                                                        \u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "                                                                        \u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "                                                                        \u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "                                                                        \u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "                                                                        \u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "                                                                        \u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "                                                                        \u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "                                                                        \u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "                                                                        \u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\n",
            "\u001b[A\n",
            "\n",
            "\u001b[A\u001b[A\n",
            "\n",
            "\n",
            "\u001b[A\u001b[A\u001b[A\n",
            "\n",
            "\n",
            "\n",
            "\u001b[A\u001b[A\u001b[A\u001b[A\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\n",
            "\u001b[A\n",
            "\n",
            "\u001b[A\u001b[A\n",
            "\n",
            "\n",
            "\u001b[A\u001b[A\u001b[A\n",
            "\n",
            "\n",
            "\n",
            "\u001b[A\u001b[A\u001b[A\u001b[A\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\n",
            "\u001b[A\n",
            "\n",
            "\u001b[A\u001b[A\n",
            "\n",
            "\n",
            "\u001b[A\u001b[A\u001b[A\n",
            "\n",
            "\n",
            "\n",
            "\u001b[A\u001b[A\u001b[A\u001b[A\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\n",
            "\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\u001b[A\n",
            "Preparing transaction: | \b\b/ \b\b- \b\b\\ \b\b| \b\b/ \b\b- \b\b\\ \b\b| \b\b/ \b\b- \b\b\\ \b\b| \b\b/ \b\bdone\n",
            "Verifying transaction: \\ \b\b| \b\b/ \b\b- \b\b\\ \b\b| \b\b/ \b\b- \b\b\\ \b\b| \b\b/ \b\b- \b\b\\ \b\b| \b\b/ \b\b- \b\b\\ \b\b| \b\b/ \b\b- \b\b\\ \b\b| \b\b/ \b\b- \b\b\\ \b\b| \b\b/ \b\b- \b\b\\ \b\b| \b\b/ \b\b- \b\b\\ \b\b| \b\b/ \b\b- \b\b\\ \b\b| \b\b/ \b\b- \b\b\\ \b\b| \b\b/ \b\b- \b\b\\ \b\b| \b\b/ \b\b- \b\b\\ \b\b| \b\b/ \b\b- \b\b\\ \b\b| \b\b/ \b\b- \b\b\\ \b\b| \b\b/ \b\b- \b\b\\ \b\b| \b\b/ \b\b- \b\b\\ \b\b| \b\b/ \b\b- \b\b\\ \b\b| \b\b/ \b\b- \b\b\\ \b\b| \b\b/ \b\b- \b\b\\ \b\b| \b\b/ \b\b- \b\b\\ \b\b| \b\b/ \b\b- \b\b\\ \b\b| \b\b/ \b\b- \b\b\\ \b\b| \b\b/ \b\b- \b\b\\ \b\b| \b\b/ \b\b- \b\b\\ \b\b| \b\b/ \b\b- \b\b\\ \b\b| \b\b/ \b\b- \b\b\\ \b\b| \b\b/ \b\b- \b\b\\ \b\b| \b\b/ \b\b- \b\b\\ \b\b| \b\bdone\n",
            "Executing transaction: - \b\b\\ \b\b| \b\b/ \b\b- \b\b\\ \b\b| \b\b/ \b\b- \b\b\\ \b\b| \b\b/ \b\b- \b\b\\ \b\b| \b\b/ \b\b- \b\b\\ \b\b| \b\b/ \b\b- \b\b\\ \b\b| \b\b/ \b\b- \b\b\\ \b\b| \b\b/ \b\b- \b\b\\ \b\b| \b\b/ \b\b- \b\b\\ \b\b| \b\b/ \b\b- \b\b\\ \b\b| \b\b/ \b\b- \b\b\\ \b\b| \b\b/ \b\b- \b\b\\ \b\b| \b\b/ \b\b- \b\b\\ \b\b| \b\b/ \b\b- \b\b\\ \b\b| \b\b/ \b\b- \b\b\\ \b\b| \b\b/ \b\b- \b\b\\ \b\b| \b\b/ \b\b- \b\b\\ By downloading and using the CUDA Toolkit conda packages, you accept the terms and conditions of the CUDA End User License Agreement (EULA): https://docs.nvidia.com/cuda/eula/index.html\n",
            "\n",
            "\b\b| \b\b/ \b\b- \b\b\\ \b\b| \b\b/ \b\b- \b\b\\ \b\b| \b\b/ \b\b- \b\b\\ \b\b| \b\b/ \b\b- \b\b\\ \b\b| \b\b/ \b\b- \b\b\\ \b\b| \b\b/ \b\b- \b\b\\ \b\b| \b\b/ \b\b- \b\b\\ \b\b| \b\b/ \b\b- \b\b\\ \b\b| \b\b/ \b\b- \b\b\\ \b\b| \b\b/ \b\b- \b\b\\ \b\b| \b\b/ \b\b- \b\b\\ \b\b| \b\b/ \b\b- \b\b\\ \b\b| \b\b/ \b\b- \b\b\\ \b\b| \b\b/ \b\b- \b\b\\ \b\b| \b\b/ \b\b- \b\b\\ \b\b| \b\b/ \b\b- \b\b\\ \b\b| \b\b/ \b\b- \b\b\\ \b\b| \b\b/ \b\b- \b\b\\ \b\b| \b\b/ \b\b- \b\b\\ \b\b| \b\b/ \b\b- \b\b\\ \b\b| \b\b/ \b\b- \b\b\\ \b\b| \b\b/ \b\b- \b\b\\ \b\b| \b\b/ \b\b- \b\b\\ \b\b| \b\b/ \b\b- \b\b\\ \b\b| \b\b/ \b\b- \b\b\\ \b\b| \b\b/ \b\b- \b\b\\ \b\b| \b\b/ \b\b- \b\b\\ \b\b| \b\b/ \b\b- \b\b\\ \b\b| \b\b/ \b\b- \b\b\\ \b\b| \b\b/ \b\b- \b\b\\ \b\b| \b\b/ \b\b- \b\b\\ \b\b| \b\b/ \b\b- \b\b\\ \b\b| \b\b/ \b\b- \b\b\\ \b\b| \b\b/ \b\b- \b\b\\ \b\b| \b\b/ \b\b- \b\bdone\n"
          ]
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "!python gaussian_point_train.py --train_config /content/drive/MyDrive/AI/taichi_3d_gaussian_splatting/config/boots_super_sparse_config.yaml"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "QI0Z9KZJaJwl",
        "outputId": "45fe6e68-b32c-4756-ddd2-54dfbd0f7464"
      },
      "execution_count": null,
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "[Taichi] version 1.6.0, llvm 15.0.4, commit f1c6fbbd, linux, python 3.10.10\n",
            "[Taichi] Starting on arch=cuda\n",
            "/usr/local/lib/python3.10/site-packages/torch/utils/data/dataloader.py:560: UserWarning: This DataLoader will create 4 worker processes in total. Our suggested max number of worker in current system is 2, which is smaller than what this DataLoader is going to create. Please be aware that excessive worker creation might get DataLoader running slow or even freeze, lower the worker number to avoid potential slowness/freeze if necessary.\n",
            "  warnings.warn(_create_warning_msg(\n",
            "  0% 0/30001 [00:00<?, ?it/s]/usr/local/lib/python3.10/site-packages/torchvision/transforms/functional.py:1603: UserWarning: The default value of the antialias parameter of all the resizing transforms (Resize(), RandomResizedCrop(), etc.) will change from None to True in v0.17, in order to be consistent across the PIL and Tensor backends. To suppress this warning, directly pass antialias=True (recommended, future default), antialias=None (current default, which means False for Tensors and True for PIL), or antialias=False (only works on Tensors - PIL will still use antialiasing). This also applies if you are using the inference transforms from the models weights: update the call to weights.transforms(antialias=True).\n",
            "  warnings.warn(\n",
            "  2% 500/30001 [01:50<1:14:42,  6.58it/s]num_valid_points=10500;\n",
            "num_over_reconstructed: 422, num_under_reconstructed: 0\n",
            "total valid points: 10500 -> 10922, num_densify_points: 422, num_fillable_densify_points: 422\n",
            "num_transparent_points: 0, num_floaters_points: 0\n",
            "  2% 600/30001 [02:10<1:14:20,  6.59it/s]1072 1920\n",
            "num_valid_points=10922;\n",
            "num_over_reconstructed: 415, num_under_reconstructed: 0\n",
            "total valid points: 10922 -> 11337, num_densify_points: 415, num_fillable_densify_points: 415\n",
            "num_transparent_points: 0, num_floaters_points: 0\n",
            "  2% 700/30001 [02:35<1:12:06,  6.77it/s]num_valid_points=11337;\n",
            "num_over_reconstructed: 287, num_under_reconstructed: 0\n",
            "total valid points: 11337 -> 11624, num_densify_points: 287, num_fillable_densify_points: 287\n",
            "num_transparent_points: 0, num_floaters_points: 0\n",
            "  3% 800/30001 [02:55<2:44:59,  2.95it/s]1072 1920\n",
            "num_valid_points=11624;\n",
            "num_over_reconstructed: 389, num_under_reconstructed: 0\n",
            "total valid points: 11624 -> 12013, num_densify_points: 389, num_fillable_densify_points: 389\n",
            "num_transparent_points: 0, num_floaters_points: 0\n",
            "  3% 900/30001 [03:26<1:04:12,  7.55it/s]num_valid_points=12013;\n",
            "num_over_reconstructed: 395, num_under_reconstructed: 0\n",
            "total valid points: 12013 -> 12407, num_densify_points: 395, num_fillable_densify_points: 395\n",
            "num_transparent_points: 1, num_floaters_points: 0\n",
            "  3% 1000/30001 [03:46<1:08:19,  7.07it/s]1072 1920\n",
            "num_valid_points=12407;\n",
            "num_over_reconstructed: 488, num_under_reconstructed: 0\n",
            "total valid points: 12407 -> 12894, num_densify_points: 488, num_fillable_densify_points: 488\n",
            "num_transparent_points: 1, num_floaters_points: 0\n",
            "=========================================================================\n",
            "Kernel Profiler(count, default) @ CUDA on Tesla T4\n",
            "=========================================================================\n",
            "[      %     total   count |      min       avg       max   ] Kernel name\n",
            "-------------------------------------------------------------------------\n",
            "[ 83.28%  19.308 s   1001x |    0.561    19.288    84.959 ms] gaussian_point_rasterisation_backward_c96_0_kernel_1_range_for\n",
            "[  7.06%   1.637 s   1001x |    1.578     1.636     5.534 ms] gaussian_point_rasterisation_backward_c96_0_kernel_3_range_for\n",
            "[  2.86%   0.664 s   1001x |    0.020     0.663    11.080 ms] generate_point_sort_key_by_num_overlap_tiles_c88_0_kernel_1_range_for\n",
            "[  2.61%   0.604 s   1001x |    0.014     0.604    20.268 ms] generate_num_overlap_tiles_c86_0_kernel_1_range_for\n",
            "[  2.12%   0.492 s   1001x |    0.095     0.492    13.033 ms] gaussian_point_rasterisation_c94_0_kernel_1_range_for\n",
            "[  0.26%   0.061 s   1001x |    0.008     0.061    14.055 ms] generate_point_attributes_in_camera_plane_c92_0_kernel_0_serial\n",
            "[  0.25%   0.057 s   1001x |    0.010     0.057    15.062 ms] filter_point_in_camera_c82_0_kernel_0_serial\n",
            "[  0.21%   0.048 s   1001x |    0.007     0.048    13.025 ms] find_tile_start_and_end_c90_0_kernel_0_serial\n",
            "[  0.21%   0.048 s   1001x |    0.008     0.048     7.221 ms] generate_point_sort_key_by_num_overlap_tiles_c88_0_kernel_0_serial\n",
            "[  0.20%   0.047 s   1001x |    0.019     0.047     7.201 ms] filter_point_in_camera_c82_0_kernel_1_range_for\n",
            "[  0.20%   0.046 s   1001x |    0.004     0.046    18.239 ms] find_tile_start_and_end_c90_0_kernel_2_serial\n",
            "[  0.18%   0.043 s   1001x |    0.006     0.043     8.196 ms] find_tile_start_and_end_c90_0_kernel_1_range_for\n",
            "[  0.15%   0.034 s   1001x |    0.005     0.034     9.064 ms] gaussian_point_rasterisation_backward_c96_0_kernel_2_serial\n",
            "[  0.14%   0.031 s   1001x |    0.017     0.031     4.931 ms] generate_point_attributes_in_camera_plane_c92_0_kernel_1_range_for\n",
            "[  0.12%   0.027 s   1001x |    0.007     0.027     7.069 ms] generate_num_overlap_tiles_c86_0_kernel_0_serial\n",
            "[  0.10%   0.022 s   1001x |    0.008     0.022     5.995 ms] gaussian_point_rasterisation_c94_0_kernel_0_serial\n",
            "[  0.06%   0.013 s   1001x |    0.004     0.013     3.105 ms] gaussian_point_rasterisation_backward_c96_0_kernel_0_serial\n",
            "[  0.00%   0.001 s      1x |    0.895     0.895     0.895 ms] runtime_initialize\n",
            "[  0.00%   0.000 s      1x |    0.447     0.447     0.447 ms] runtime_initialize_rand_states_cuda\n",
            "[  0.00%   0.000 s     12x |    0.010     0.014     0.021 ms] sample_from_point_c100_0_kernel_0_serial\n",
            "[  0.00%   0.000 s     12x |    0.008     0.013     0.021 ms] sample_from_point_c100_0_kernel_1_range_for\n",
            "[  0.00%   0.000 s      1x |    0.030     0.030     0.030 ms] runtime_memory_allocate_aligned\n",
            "[  0.00%   0.000 s      1x |    0.016     0.016     0.016 ms] runtime_initialize_runtime_context_buffer\n",
            "[  0.00%   0.000 s      1x |    0.014     0.014     0.014 ms] runtime_initialize_snodes\n",
            "-------------------------------------------------------------------------\n",
            "[100.00%] Total execution time:  23.185 s   number of results: 24\n",
            "=========================================================================\n",
            "=========================================================================\n",
            "Kernel Profiler(count, default) @ CUDA on Tesla T4\n",
            "=========================================================================\n",
            "[      %     total   count |      min       avg       max   ] Kernel name\n",
            "-------------------------------------------------------------------------\n",
            "-------------------------------------------------------------------------\n",
            "[100.00%] Total execution time:   0.000 s   number of results: 0\n",
            "=========================================================================\n",
            "\n",
            "  0% 0/22 [00:00<?, ?it/s]\u001b[A\n",
            "  5% 1/22 [00:09<03:19,  9.50s/it]\u001b[A\n",
            "  9% 2/22 [00:16<02:42,  8.12s/it]\u001b[A\n",
            " 14% 3/22 [00:22<02:14,  7.07s/it]\u001b[A\n",
            " 18% 4/22 [00:27<01:49,  6.07s/it]\u001b[A\n",
            " 23% 5/22 [00:32<01:40,  5.91s/it]\u001b[A\n",
            " 27% 6/22 [00:39<01:37,  6.10s/it]\u001b[A\n",
            " 32% 7/22 [00:45<01:34,  6.28s/it]\u001b[A\n",
            " 36% 8/22 [00:50<01:19,  5.65s/it]\u001b[A\n",
            " 41% 9/22 [00:53<01:06,  5.08s/it]\u001b[A\n",
            " 45% 10/22 [01:01<01:08,  5.74s/it]\u001b[A\n",
            " 50% 11/22 [01:07<01:05,  5.98s/it]\u001b[A\n",
            " 55% 12/22 [01:12<00:56,  5.60s/it]\u001b[A\n",
            " 59% 13/22 [01:17<00:48,  5.38s/it]\u001b[A\n",
            " 64% 14/22 [01:23<00:46,  5.78s/it]\u001b[A\n",
            " 68% 15/22 [01:30<00:41,  5.92s/it]\u001b[A\n",
            " 73% 16/22 [01:35<00:34,  5.83s/it]\u001b[A\n",
            " 77% 17/22 [01:40<00:26,  5.39s/it]\u001b[A\n",
            " 82% 18/22 [01:44<00:20,  5.07s/it]\u001b[A\n",
            " 86% 19/22 [01:50<00:15,  5.28s/it]\u001b[A\n",
            " 91% 20/22 [01:57<00:11,  5.87s/it]\u001b[A\n",
            " 95% 21/22 [02:04<00:06,  6.08s/it]\u001b[A\n",
            "100% 22/22 [02:08<00:00,  5.85s/it]\n",
            "=========================================================================\n",
            "Kernel Profiler(count, default) @ CUDA on Tesla T4\n",
            "=========================================================================\n",
            "[      %     total   count |      min       avg       max   ] Kernel name\n",
            "-------------------------------------------------------------------------\n",
            "[ 36.10%   0.065 s     22x |    2.294     2.976     4.302 ms] generate_point_sort_key_by_num_overlap_tiles_c88_0_kernel_1_range_for\n",
            "[ 34.30%   0.062 s     22x |    1.987     2.828     8.696 ms] generate_num_overlap_tiles_c86_0_kernel_1_range_for\n",
            "[ 27.09%   0.049 s     22x |    1.734     2.234     2.680 ms] gaussian_point_rasterisation_c94_0_kernel_1_range_for\n",
            "[  0.55%   0.001 s     22x |    0.038     0.046     0.066 ms] generate_point_attributes_in_camera_plane_c92_0_kernel_1_range_for\n",
            "[  0.47%   0.001 s     22x |    0.033     0.039     0.077 ms] filter_point_in_camera_c82_0_kernel_1_range_for\n",
            "[  0.23%   0.000 s     22x |    0.014     0.019     0.040 ms] filter_point_in_camera_c82_0_kernel_0_serial\n",
            "[  0.22%   0.000 s     22x |    0.013     0.018     0.036 ms] find_tile_start_and_end_c90_0_kernel_1_range_for\n",
            "[  0.21%   0.000 s     22x |    0.014     0.017     0.056 ms] generate_point_attributes_in_camera_plane_c92_0_kernel_0_serial\n",
            "[  0.18%   0.000 s     22x |    0.011     0.015     0.031 ms] generate_num_overlap_tiles_c86_0_kernel_0_serial\n",
            "[  0.18%   0.000 s     22x |    0.012     0.015     0.027 ms] generate_point_sort_key_by_num_overlap_tiles_c88_0_kernel_0_serial\n",
            "[  0.18%   0.000 s     22x |    0.012     0.015     0.030 ms] gaussian_point_rasterisation_c94_0_kernel_0_serial\n",
            "[  0.17%   0.000 s     22x |    0.006     0.014     0.024 ms] find_tile_start_and_end_c90_0_kernel_0_serial\n",
            "[  0.12%   0.000 s     22x |    0.008     0.010     0.024 ms] find_tile_start_and_end_c90_0_kernel_2_serial\n",
            "-------------------------------------------------------------------------\n",
            "[100.00%] Total execution time:   0.181 s   number of results: 13\n",
            "=========================================================================\n",
            "  3% 1008/30001 [06:06<32:01:43,  3.98s/it]/usr/local/lib/python3.10/site-packages/torch/utils/data/dataloader.py:560: UserWarning: This DataLoader will create 4 worker processes in total. Our suggested max number of worker in current system is 2, which is smaller than what this DataLoader is going to create. Please be aware that excessive worker creation might get DataLoader running slow or even freeze, lower the worker number to avoid potential slowness/freeze if necessary.\n",
            "  warnings.warn(_create_warning_msg(\n",
            "  4% 1100/30001 [06:26<1:22:20,  5.85it/s]num_valid_points=12894;\n",
            "num_over_reconstructed: 379, num_under_reconstructed: 0\n",
            "total valid points: 12894 -> 13272, num_densify_points: 379, num_fillable_densify_points: 379\n",
            "num_transparent_points: 1, num_floaters_points: 0\n",
            "  4% 1200/30001 [06:50<1:05:18,  7.35it/s]1072 1920\n",
            "num_valid_points=13272;\n",
            "num_over_reconstructed: 336, num_under_reconstructed: 0\n",
            "total valid points: 13272 -> 13608, num_densify_points: 336, num_fillable_densify_points: 336\n",
            "num_transparent_points: 0, num_floaters_points: 0\n",
            "  4% 1300/30001 [07:23<1:09:55,  6.84it/s]num_valid_points=13608;\n",
            "num_over_reconstructed: 472, num_under_reconstructed: 0\n",
            "total valid points: 13608 -> 14080, num_densify_points: 472, num_fillable_densify_points: 472\n",
            "num_transparent_points: 0, num_floaters_points: 0\n",
            "  5% 1400/30001 [07:48<1:44:54,  4.54it/s]1072 1920\n",
            "num_valid_points=14080;\n",
            "num_over_reconstructed: 498, num_under_reconstructed: 0\n",
            "total valid points: 14080 -> 14577, num_densify_points: 498, num_fillable_densify_points: 498\n",
            "num_transparent_points: 1, num_floaters_points: 0\n",
            "  5% 1500/30001 [08:23<1:27:21,  5.44it/s]num_valid_points=14577;\n",
            "num_over_reconstructed: 405, num_under_reconstructed: 0\n",
            "total valid points: 14577 -> 14978, num_densify_points: 405, num_fillable_densify_points: 405\n",
            "num_transparent_points: 4, num_floaters_points: 0\n",
            "  5% 1600/30001 [08:48<2:32:05,  3.11it/s]1072 1920\n",
            "num_valid_points=14978;\n",
            "num_over_reconstructed: 414, num_under_reconstructed: 3\n",
            "total valid points: 14978 -> 15388, num_densify_points: 417, num_fillable_densify_points: 417\n",
            "num_transparent_points: 7, num_floaters_points: 0\n",
            "  6% 1700/30001 [09:16<1:22:09,  5.74it/s]num_valid_points=15388;\n",
            "num_over_reconstructed: 381, num_under_reconstructed: 2\n",
            "total valid points: 15388 -> 15770, num_densify_points: 383, num_fillable_densify_points: 383\n",
            "num_transparent_points: 1, num_floaters_points: 0\n",
            "  6% 1800/30001 [09:40<1:23:04,  5.66it/s]1072 1920\n",
            "num_valid_points=15770;\n",
            "num_over_reconstructed: 561, num_under_reconstructed: 2\n",
            "total valid points: 15770 -> 16330, num_densify_points: 563, num_fillable_densify_points: 563\n",
            "num_transparent_points: 3, num_floaters_points: 0\n",
            "  6% 1900/30001 [10:11<1:18:11,  5.99it/s]num_valid_points=16330;\n",
            "num_over_reconstructed: 459, num_under_reconstructed: 5\n",
            "total valid points: 16330 -> 16780, num_densify_points: 464, num_fillable_densify_points: 464\n",
            "num_transparent_points: 14, num_floaters_points: 0\n",
            "  7% 2000/30001 [10:31<1:26:53,  5.37it/s]1072 1920\n",
            "num_valid_points=16780;\n",
            "num_over_reconstructed: 403, num_under_reconstructed: 6\n",
            "total valid points: 16780 -> 17174, num_densify_points: 409, num_fillable_densify_points: 409\n",
            "num_transparent_points: 15, num_floaters_points: 0\n",
            "=========================================================================\n",
            "Kernel Profiler(count, default) @ CUDA on Tesla T4\n",
            "=========================================================================\n",
            "[      %     total   count |      min       avg       max   ] Kernel name\n",
            "-------------------------------------------------------------------------\n",
            "[ 88.12%  41.647 s   1000x |   20.939    41.647   115.292 ms] gaussian_point_rasterisation_backward_c96_0_kernel_1_range_for\n",
            "[  3.52%   1.663 s   1000x |    1.615     1.663    12.415 ms] gaussian_point_rasterisation_backward_c96_0_kernel_3_range_for\n",
            "[  2.52%   1.191 s   1000x |    0.760     1.191    10.222 ms] generate_point_sort_key_by_num_overlap_tiles_c88_0_kernel_1_range_for\n",
            "[  2.48%   1.173 s   1000x |    0.664     1.173    10.148 ms] gaussian_point_rasterisation_c94_0_kernel_1_range_for\n",
            "[  2.20%   1.042 s   1000x |    0.662     1.042     9.939 ms] generate_num_overlap_tiles_c86_0_kernel_1_range_for\n",
            "[  0.16%   0.073 s   1000x |    0.006     0.073    12.861 ms] generate_num_overlap_tiles_c86_0_kernel_0_serial\n",
            "[  0.15%   0.070 s   1000x |    0.008     0.070    11.032 ms] generate_point_sort_key_by_num_overlap_tiles_c88_0_kernel_0_serial\n",
            "[  0.14%   0.064 s   1000x |    0.020     0.064    20.402 ms] filter_point_in_camera_c82_0_kernel_1_range_for\n",
            "[  0.13%   0.063 s   1000x |    0.008     0.063    20.185 ms] generate_point_attributes_in_camera_plane_c92_0_kernel_0_serial\n",
            "[  0.10%   0.048 s   1000x |    0.019     0.048    11.059 ms] generate_point_attributes_in_camera_plane_c92_0_kernel_1_range_for\n",
            "[  0.10%   0.045 s   1000x |    0.009     0.045     9.358 ms] filter_point_in_camera_c82_0_kernel_0_serial\n",
            "[  0.09%   0.044 s   1000x |    0.010     0.044     8.409 ms] gaussian_point_rasterisation_backward_c96_0_kernel_2_serial\n",
            "[  0.09%   0.041 s   1000x |    0.008     0.041     7.037 ms] find_tile_start_and_end_c90_0_kernel_1_range_for\n",
            "[  0.08%   0.040 s   1000x |    0.004     0.040    11.049 ms] find_tile_start_and_end_c90_0_kernel_0_serial\n",
            "[  0.06%   0.030 s   1000x |    0.007     0.030     5.546 ms] gaussian_point_rasterisation_c94_0_kernel_0_serial\n",
            "[  0.04%   0.021 s   1000x |    0.004     0.021     6.728 ms] find_tile_start_and_end_c90_0_kernel_2_serial\n",
            "[  0.01%   0.005 s   1000x |    0.004     0.005     0.049 ms] gaussian_point_rasterisation_backward_c96_0_kernel_0_serial\n",
            "[  0.00%   0.000 s     20x |    0.009     0.015     0.026 ms] sample_from_point_c100_0_kernel_0_serial\n",
            "[  0.00%   0.000 s     20x |    0.008     0.014     0.022 ms] sample_from_point_c100_0_kernel_1_range_for\n",
            "-------------------------------------------------------------------------\n",
            "[100.00%] Total execution time:  47.262 s   number of results: 19\n",
            "=========================================================================\n",
            "=========================================================================\n",
            "Kernel Profiler(count, default) @ CUDA on Tesla T4\n",
            "=========================================================================\n",
            "[      %     total   count |      min       avg       max   ] Kernel name\n",
            "-------------------------------------------------------------------------\n",
            "-------------------------------------------------------------------------\n",
            "[100.00%] Total execution time:   0.000 s   number of results: 0\n",
            "=========================================================================\n",
            "\n",
            "  0% 0/22 [00:00<?, ?it/s]\u001b[A\n",
            "  5% 1/22 [00:05<01:58,  5.62s/it]\u001b[A\n",
            "  9% 2/22 [00:12<02:06,  6.33s/it]\u001b[A\n",
            " 14% 3/22 [00:19<02:04,  6.57s/it]\u001b[A\n",
            " 18% 4/22 [00:23<01:42,  5.71s/it]\u001b[A\n",
            " 23% 5/22 [00:28<01:29,  5.24s/it]\u001b[A\n",
            " 27% 6/22 [00:33<01:24,  5.26s/it]\u001b[A\n",
            " 32% 7/22 [00:41<01:31,  6.13s/it]\u001b[A\n",
            " 36% 8/22 [00:49<01:32,  6.63s/it]\u001b[A\n",
            " 41% 9/22 [00:52<01:12,  5.61s/it]\u001b[A\n",
            " 45% 10/22 [00:56<01:01,  5.12s/it]\u001b[A\n",
            " 50% 11/22 [01:02<00:58,  5.34s/it]\u001b[A\n",
            " 55% 12/22 [01:08<00:54,  5.47s/it]\u001b[A\n",
            " 59% 13/22 [01:14<00:52,  5.84s/it]\u001b[A\n",
            " 64% 14/22 [01:19<00:43,  5.41s/it]\u001b[A\n",
            " 68% 15/22 [01:22<00:34,  4.90s/it]\u001b[A\n",
            " 73% 16/22 [01:27<00:29,  4.95s/it]\u001b[A\n",
            " 77% 17/22 [01:33<00:25,  5.02s/it]\u001b[A\n",
            " 82% 18/22 [01:39<00:21,  5.34s/it]\u001b[A\n",
            " 86% 19/22 [01:43<00:15,  5.07s/it]\u001b[A\n",
            " 91% 20/22 [01:48<00:09,  4.90s/it]\u001b[A\n",
            " 95% 21/22 [01:53<00:05,  5.05s/it]\u001b[A\n",
            "100% 22/22 [01:59<00:00,  5.43s/it]\n",
            "=========================================================================\n",
            "Kernel Profiler(count, default) @ CUDA on Tesla T4\n",
            "=========================================================================\n",
            "[      %     total   count |      min       avg       max   ] Kernel name\n",
            "-------------------------------------------------------------------------\n",
            "[ 37.19%   0.078 s     22x |    2.953     3.535     4.130 ms] gaussian_point_rasterisation_c94_0_kernel_1_range_for\n",
            "[ 31.37%   0.066 s     22x |    2.116     2.982     4.125 ms] generate_point_sort_key_by_num_overlap_tiles_c88_0_kernel_1_range_for\n",
            "[ 26.83%   0.056 s     22x |    1.802     2.550     3.620 ms] generate_num_overlap_tiles_c86_0_kernel_1_range_for\n",
            "[  2.36%   0.005 s     22x |    0.010     0.224     4.602 ms] generate_num_overlap_tiles_c86_0_kernel_0_serial\n",
            "[  0.66%   0.001 s     22x |    0.054     0.062     0.087 ms] generate_point_attributes_in_camera_plane_c92_0_kernel_1_range_for\n",
            "[  0.39%   0.001 s     22x |    0.035     0.037     0.050 ms] filter_point_in_camera_c82_0_kernel_1_range_for\n",
            "[  0.24%   0.001 s     22x |    0.018     0.023     0.043 ms] find_tile_start_and_end_c90_0_kernel_1_range_for\n",
            "[  0.20%   0.000 s     22x |    0.015     0.019     0.041 ms] filter_point_in_camera_c82_0_kernel_0_serial\n",
            "[  0.19%   0.000 s     22x |    0.014     0.018     0.073 ms] generate_point_attributes_in_camera_plane_c92_0_kernel_0_serial\n",
            "[  0.17%   0.000 s     22x |    0.012     0.016     0.042 ms] generate_point_sort_key_by_num_overlap_tiles_c88_0_kernel_0_serial\n",
            "[  0.16%   0.000 s     22x |    0.012     0.015     0.040 ms] gaussian_point_rasterisation_c94_0_kernel_0_serial\n",
            "[  0.12%   0.000 s     22x |    0.006     0.012     0.048 ms] find_tile_start_and_end_c90_0_kernel_0_serial\n",
            "[  0.12%   0.000 s     22x |    0.008     0.012     0.039 ms] find_tile_start_and_end_c90_0_kernel_2_serial\n",
            "-------------------------------------------------------------------------\n",
            "[100.00%] Total execution time:   0.209 s   number of results: 13\n",
            "=========================================================================\n",
            "  7% 2016/30001 [12:44<7:59:00,  1.03s/it] /usr/local/lib/python3.10/site-packages/torch/utils/data/dataloader.py:560: UserWarning: This DataLoader will create 4 worker processes in total. Our suggested max number of worker in current system is 2, which is smaller than what this DataLoader is going to create. Please be aware that excessive worker creation might get DataLoader running slow or even freeze, lower the worker number to avoid potential slowness/freeze if necessary.\n",
            "  warnings.warn(_create_warning_msg(\n",
            "  7% 2100/30001 [13:00<1:03:33,  7.32it/s]num_valid_points=17174;\n",
            "num_over_reconstructed: 377, num_under_reconstructed: 26\n",
            "total valid points: 17174 -> 17562, num_densify_points: 403, num_fillable_densify_points: 403\n",
            "num_transparent_points: 15, num_floaters_points: 0\n",
            "  7% 2200/30001 [13:21<1:35:39,  4.84it/s]1072 1920\n",
            "num_valid_points=17562;\n",
            "num_over_reconstructed: 328, num_under_reconstructed: 21\n",
            "total valid points: 17562 -> 17892, num_densify_points: 349, num_fillable_densify_points: 349\n",
            "num_transparent_points: 19, num_floaters_points: 0\n",
            "  8% 2300/30001 [13:49<1:29:07,  5.18it/s]num_valid_points=17892;\n",
            "num_over_reconstructed: 429, num_under_reconstructed: 20\n",
            "total valid points: 17892 -> 18329, num_densify_points: 449, num_fillable_densify_points: 449\n",
            "num_transparent_points: 12, num_floaters_points: 0\n",
            "  8% 2400/30001 [14:09<2:01:59,  3.77it/s]1072 1920\n",
            "num_valid_points=18329;\n",
            "num_over_reconstructed: 477, num_under_reconstructed: 18\n",
            "total valid points: 18329 -> 18811, num_densify_points: 495, num_fillable_densify_points: 495\n",
            "num_transparent_points: 13, num_floaters_points: 0\n",
            "  8% 2500/30001 [14:37<1:57:00,  3.92it/s]num_valid_points=18811;\n",
            "num_over_reconstructed: 236, num_under_reconstructed: 34\n",
            "total valid points: 18811 -> 19070, num_densify_points: 270, num_fillable_densify_points: 270\n",
            "num_transparent_points: 11, num_floaters_points: 0\n",
            "  9% 2600/30001 [14:57<1:01:46,  7.39it/s]1072 1920\n",
            "num_valid_points=19070;\n",
            "num_over_reconstructed: 213, num_under_reconstructed: 35\n",
            "total valid points: 19070 -> 19308, num_densify_points: 248, num_fillable_densify_points: 248\n",
            "num_transparent_points: 10, num_floaters_points: 0\n",
            "  9% 2700/30001 [15:27<1:39:53,  4.56it/s]num_valid_points=19308;\n",
            "num_over_reconstructed: 256, num_under_reconstructed: 30\n",
            "total valid points: 19308 -> 19580, num_densify_points: 286, num_fillable_densify_points: 286\n",
            "num_transparent_points: 14, num_floaters_points: 0\n",
            "  9% 2800/30001 [15:47<1:08:05,  6.66it/s]1072 1920\n",
            "num_valid_points=19580;\n",
            "num_over_reconstructed: 427, num_under_reconstructed: 32\n",
            "total valid points: 19580 -> 20022, num_densify_points: 459, num_fillable_densify_points: 459\n",
            "num_transparent_points: 17, num_floaters_points: 0\n",
            " 10% 2900/30001 [16:15<3:11:19,  2.36it/s]num_valid_points=20022;\n",
            "num_over_reconstructed: 307, num_under_reconstructed: 21\n",
            "total valid points: 20022 -> 20342, num_densify_points: 328, num_fillable_densify_points: 328\n",
            "num_transparent_points: 8, num_floaters_points: 0\n",
            " 10% 3000/30001 [16:36<1:04:03,  7.03it/s]1072 1920\n",
            "num_valid_points=20342;\n",
            "num_over_reconstructed: 201, num_under_reconstructed: 46\n",
            "total valid points: 20342 -> 20575, num_densify_points: 247, num_fillable_densify_points: 247\n",
            "num_transparent_points: 14, num_floaters_points: 0\n",
            "=========================================================================\n",
            "Kernel Profiler(count, default) @ CUDA on Tesla T4\n",
            "=========================================================================\n",
            "[      %     total   count |      min       avg       max   ] Kernel name\n",
            "-------------------------------------------------------------------------\n",
            "[ 87.87%  43.459 s   1000x |   22.173    43.459   137.347 ms] gaussian_point_rasterisation_backward_c96_0_kernel_1_range_for\n",
            "[  3.34%   1.652 s   1000x |    1.619     1.652     4.453 ms] gaussian_point_rasterisation_backward_c96_0_kernel_3_range_for\n",
            "[  3.19%   1.576 s   1000x |    1.077     1.576    14.471 ms] gaussian_point_rasterisation_c94_0_kernel_1_range_for\n",
            "[  2.35%   1.160 s   1000x |    0.731     1.160     9.128 ms] generate_point_sort_key_by_num_overlap_tiles_c88_0_kernel_1_range_for\n",
            "[  2.07%   1.025 s   1000x |    0.627     1.025    10.940 ms] generate_num_overlap_tiles_c86_0_kernel_1_range_for\n",
            "[  0.18%   0.087 s   1000x |    0.007     0.087    19.069 ms] generate_num_overlap_tiles_c86_0_kernel_0_serial\n",
            "[  0.17%   0.082 s   1000x |    0.008     0.082    35.130 ms] gaussian_point_rasterisation_c94_0_kernel_0_serial\n",
            "[  0.13%   0.062 s   1000x |    0.009     0.062    17.470 ms] filter_point_in_camera_c82_0_kernel_0_serial\n",
            "[  0.12%   0.059 s   1000x |    0.027     0.059    13.216 ms] generate_point_attributes_in_camera_plane_c92_0_kernel_1_range_for\n",
            "[  0.12%   0.058 s   1000x |    0.020     0.058    15.583 ms] filter_point_in_camera_c82_0_kernel_1_range_for\n",
            "[  0.12%   0.058 s   1000x |    0.010     0.058    10.146 ms] gaussian_point_rasterisation_backward_c96_0_kernel_2_serial\n",
            "[  0.09%   0.044 s   1000x |    0.012     0.044    11.781 ms] find_tile_start_and_end_c90_0_kernel_1_range_for\n",
            "[  0.07%   0.036 s   1000x |    0.004     0.036    13.340 ms] find_tile_start_and_end_c90_0_kernel_2_serial\n",
            "[  0.06%   0.032 s   1000x |    0.004     0.032     9.337 ms] find_tile_start_and_end_c90_0_kernel_0_serial\n",
            "[  0.06%   0.030 s   1000x |    0.008     0.030     6.092 ms] generate_point_attributes_in_camera_plane_c92_0_kernel_0_serial\n",
            "[  0.04%   0.020 s   1000x |    0.008     0.020     4.157 ms] generate_point_sort_key_by_num_overlap_tiles_c88_0_kernel_0_serial\n",
            "[  0.03%   0.017 s   1000x |    0.004     0.017    12.100 ms] gaussian_point_rasterisation_backward_c96_0_kernel_0_serial\n",
            "[  0.00%   0.000 s     20x |    0.010     0.017     0.037 ms] sample_from_point_c100_0_kernel_0_serial\n",
            "[  0.00%   0.000 s     20x |    0.008     0.014     0.025 ms] sample_from_point_c100_0_kernel_1_range_for\n",
            "-------------------------------------------------------------------------\n",
            "[100.00%] Total execution time:  49.458 s   number of results: 19\n",
            "=========================================================================\n",
            "=========================================================================\n",
            "Kernel Profiler(count, default) @ CUDA on Tesla T4\n",
            "=========================================================================\n",
            "[      %     total   count |      min       avg       max   ] Kernel name\n",
            "-------------------------------------------------------------------------\n",
            "-------------------------------------------------------------------------\n",
            "[100.00%] Total execution time:   0.000 s   number of results: 0\n",
            "=========================================================================\n",
            "\n",
            "  0% 0/22 [00:00<?, ?it/s]\u001b[A\n",
            "  5% 1/22 [00:08<02:52,  8.24s/it]\u001b[A\n",
            "  9% 2/22 [00:13<02:13,  6.66s/it]\u001b[A\n",
            " 14% 3/22 [00:17<01:39,  5.25s/it]\u001b[A\n",
            " 18% 4/22 [00:20<01:20,  4.47s/it]\u001b[A\n",
            " 23% 5/22 [00:24<01:14,  4.38s/it]\u001b[A\n",
            " 27% 6/22 [00:32<01:27,  5.45s/it]\u001b[A\n",
            " 32% 7/22 [00:39<01:31,  6.08s/it]\u001b[A\n",
            " 36% 8/22 [00:45<01:22,  5.92s/it]\u001b[A\n",
            " 41% 9/22 [00:50<01:14,  5.76s/it]\u001b[A\n",
            " 45% 10/22 [00:57<01:12,  6.05s/it]\u001b[A\n",
            " 50% 11/22 [01:05<01:13,  6.67s/it]\u001b[A\n",
            " 55% 12/22 [01:11<01:04,  6.49s/it]\u001b[A\n",
            " 59% 13/22 [01:19<01:01,  6.81s/it]\u001b[A\n",
            " 64% 14/22 [01:26<00:56,  7.08s/it]\u001b[A\n",
            " 68% 15/22 [01:33<00:49,  7.03s/it]\u001b[A\n",
            " 73% 16/22 [01:37<00:36,  6.01s/it]\u001b[A\n",
            " 77% 17/22 [01:41<00:27,  5.49s/it]\u001b[A\n",
            " 82% 18/22 [01:47<00:22,  5.69s/it]\u001b[A\n",
            " 86% 19/22 [01:55<00:18,  6.21s/it]\u001b[A\n",
            " 91% 20/22 [01:59<00:11,  5.56s/it]\u001b[A\n",
            " 95% 21/22 [02:04<00:05,  5.31s/it]\u001b[A\n",
            "100% 22/22 [02:09<00:00,  5.88s/it]\n",
            "=========================================================================\n",
            "Kernel Profiler(count, default) @ CUDA on Tesla T4\n",
            "=========================================================================\n",
            "[      %     total   count |      min       avg       max   ] Kernel name\n",
            "-------------------------------------------------------------------------\n",
            "[ 42.94%   0.096 s     22x |    3.695     4.371     5.248 ms] gaussian_point_rasterisation_c94_0_kernel_1_range_for\n",
            "[ 28.62%   0.064 s     22x |    2.148     2.914     3.885 ms] generate_point_sort_key_by_num_overlap_tiles_c88_0_kernel_1_range_for\n",
            "[ 26.15%   0.059 s     22x |    1.838     2.662     4.499 ms] generate_num_overlap_tiles_c86_0_kernel_1_range_for\n",
            "[  0.68%   0.002 s     22x |    0.057     0.070     0.086 ms] generate_point_attributes_in_camera_plane_c92_0_kernel_1_range_for\n",
            "[  0.36%   0.001 s     22x |    0.035     0.037     0.047 ms] filter_point_in_camera_c82_0_kernel_1_range_for\n",
            "[  0.24%   0.001 s     22x |    0.020     0.025     0.047 ms] find_tile_start_and_end_c90_0_kernel_1_range_for\n",
            "[  0.18%   0.000 s     22x |    0.015     0.019     0.040 ms] filter_point_in_camera_c82_0_kernel_0_serial\n",
            "[  0.17%   0.000 s     22x |    0.014     0.017     0.030 ms] generate_point_attributes_in_camera_plane_c92_0_kernel_0_serial\n",
            "[  0.15%   0.000 s     22x |    0.012     0.016     0.045 ms] generate_num_overlap_tiles_c86_0_kernel_0_serial\n",
            "[  0.15%   0.000 s     22x |    0.012     0.015     0.027 ms] gaussian_point_rasterisation_c94_0_kernel_0_serial\n",
            "[  0.14%   0.000 s     22x |    0.012     0.015     0.025 ms] generate_point_sort_key_by_num_overlap_tiles_c88_0_kernel_0_serial\n",
            "[  0.10%   0.000 s     22x |    0.006     0.010     0.029 ms] find_tile_start_and_end_c90_0_kernel_0_serial\n",
            "[  0.10%   0.000 s     22x |    0.008     0.010     0.018 ms] find_tile_start_and_end_c90_0_kernel_2_serial\n",
            "-------------------------------------------------------------------------\n",
            "[100.00%] Total execution time:   0.224 s   number of results: 13\n",
            "=========================================================================\n",
            " 10% 3024/30001 [18:57<1:08:50,  6.53it/s]/usr/local/lib/python3.10/site-packages/torch/utils/data/dataloader.py:560: UserWarning: This DataLoader will create 4 worker processes in total. Our suggested max number of worker in current system is 2, which is smaller than what this DataLoader is going to create. Please be aware that excessive worker creation might get DataLoader running slow or even freeze, lower the worker number to avoid potential slowness/freeze if necessary.\n",
            "  warnings.warn(_create_warning_msg(\n",
            " 10% 3100/30001 [19:11<1:04:23,  6.96it/s]num_valid_points=20575;\n",
            "num_over_reconstructed: 158, num_under_reconstructed: 48\n",
            "total valid points: 20575 -> 20776, num_densify_points: 206, num_fillable_densify_points: 206\n",
            "num_transparent_points: 5, num_floaters_points: 0\n",
            " 11% 3200/30001 [19:33<1:16:51,  5.81it/s]1072 1920\n",
            "num_valid_points=20776;\n",
            "num_over_reconstructed: 148, num_under_reconstructed: 48\n",
            "total valid points: 20776 -> 20970, num_densify_points: 196, num_fillable_densify_points: 196\n",
            "num_transparent_points: 2, num_floaters_points: 0\n",
            " 11% 3300/30001 [20:00<1:06:30,  6.69it/s]num_valid_points=20970;\n",
            "num_over_reconstructed: 325, num_under_reconstructed: 46\n",
            "total valid points: 20970 -> 21339, num_densify_points: 371, num_fillable_densify_points: 371\n",
            "num_transparent_points: 2, num_floaters_points: 0\n",
            " 11% 3400/30001 [20:21<1:04:51,  6.83it/s]1072 1920\n",
            "num_valid_points=21339;\n",
            "num_over_reconstructed: 221, num_under_reconstructed: 63\n",
            "total valid points: 21339 -> 21622, num_densify_points: 284, num_fillable_densify_points: 284\n",
            "num_transparent_points: 1, num_floaters_points: 0\n",
            " 12% 3500/30001 [20:47<1:09:05,  6.39it/s]num_valid_points=21622;\n",
            "num_over_reconstructed: 205, num_under_reconstructed: 74\n",
            "total valid points: 21622 -> 21899, num_densify_points: 279, num_fillable_densify_points: 279\n",
            "num_transparent_points: 2, num_floaters_points: 0\n",
            " 12% 3600/30001 [21:08<1:18:50,  5.58it/s]1072 1920\n",
            "num_valid_points=21899;\n",
            "num_over_reconstructed: 171, num_under_reconstructed: 77\n",
            "total valid points: 21899 -> 22145, num_densify_points: 248, num_fillable_densify_points: 248\n",
            "num_transparent_points: 2, num_floaters_points: 0\n",
            " 12% 3700/30001 [21:33<2:22:44,  3.07it/s]num_valid_points=22145;\n",
            "num_over_reconstructed: 188, num_under_reconstructed: 47\n",
            "total valid points: 22145 -> 22379, num_densify_points: 235, num_fillable_densify_points: 235\n",
            "num_transparent_points: 1, num_floaters_points: 0\n",
            " 13% 3800/30001 [21:52<1:21:36,  5.35it/s]1072 1920\n",
            "num_valid_points=22379;\n",
            "num_over_reconstructed: 136, num_under_reconstructed: 50\n",
            "total valid points: 22379 -> 22565, num_densify_points: 186, num_fillable_densify_points: 186\n",
            "num_transparent_points: 0, num_floaters_points: 0\n",
            " 13% 3900/30001 [22:18<1:15:03,  5.80it/s]num_valid_points=22565;\n",
            "num_over_reconstructed: 115, num_under_reconstructed: 64\n",
            "total valid points: 22565 -> 22744, num_densify_points: 179, num_fillable_densify_points: 179\n",
            "num_transparent_points: 0, num_floaters_points: 0\n",
            " 13% 4000/30001 [22:38<1:38:02,  4.42it/s]1072 1920\n",
            "num_valid_points=22744;\n",
            "num_over_reconstructed: 120, num_under_reconstructed: 66\n",
            "total valid points: 22744 -> 22928, num_densify_points: 186, num_fillable_densify_points: 186\n",
            "num_transparent_points: 2, num_floaters_points: 0\n",
            "=========================================================================\n",
            "Kernel Profiler(count, default) @ CUDA on Tesla T4\n",
            "=========================================================================\n",
            "[      %     total   count |      min       avg       max   ] Kernel name\n",
            "-------------------------------------------------------------------------\n",
            "[ 87.66%  43.651 s   1000x |   22.125    43.651    99.703 ms] gaussian_point_rasterisation_backward_c96_0_kernel_1_range_for\n",
            "[  3.62%   1.804 s   1000x |    1.384     1.804    11.088 ms] gaussian_point_rasterisation_c94_0_kernel_1_range_for\n",
            "[  3.35%   1.667 s   1000x |    1.621     1.667     3.755 ms] gaussian_point_rasterisation_backward_c96_0_kernel_3_range_for\n",
            "[  2.33%   1.158 s   1000x |    0.770     1.158    13.044 ms] generate_point_sort_key_by_num_overlap_tiles_c88_0_kernel_1_range_for\n",
            "[  2.08%   1.034 s   1000x |    0.682     1.034     8.894 ms] generate_num_overlap_tiles_c86_0_kernel_1_range_for\n",
            "[  0.17%   0.083 s   1000x |    0.003     0.083    17.034 ms] find_tile_start_and_end_c90_0_kernel_0_serial\n",
            "[  0.14%   0.069 s   1000x |    0.033     0.069    15.130 ms] generate_point_attributes_in_camera_plane_c92_0_kernel_1_range_for\n",
            "[  0.11%   0.057 s   1000x |    0.020     0.057     8.140 ms] filter_point_in_camera_c82_0_kernel_1_range_for\n",
            "[  0.11%   0.053 s   1000x |    0.007     0.053    14.119 ms] generate_num_overlap_tiles_c86_0_kernel_0_serial\n",
            "[  0.10%   0.048 s   1000x |    0.013     0.048    12.022 ms] find_tile_start_and_end_c90_0_kernel_1_range_for\n",
            "[  0.07%   0.034 s   1000x |    0.008     0.034     6.058 ms] generate_point_sort_key_by_num_overlap_tiles_c88_0_kernel_0_serial\n",
            "[  0.06%   0.031 s   1000x |    0.010     0.031     1.004 ms] gaussian_point_rasterisation_backward_c96_0_kernel_2_serial\n",
            "[  0.06%   0.029 s   1000x |    0.008     0.029    11.043 ms] gaussian_point_rasterisation_c94_0_kernel_0_serial\n",
            "[  0.06%   0.028 s   1000x |    0.008     0.028     6.377 ms] generate_point_attributes_in_camera_plane_c92_0_kernel_0_serial\n",
            "[  0.05%   0.027 s   1000x |    0.009     0.027     2.748 ms] filter_point_in_camera_c82_0_kernel_0_serial\n",
            "[  0.04%   0.019 s   1000x |    0.004     0.019     7.142 ms] find_tile_start_and_end_c90_0_kernel_2_serial\n",
            "[  0.01%   0.006 s   1000x |    0.004     0.006     0.945 ms] gaussian_point_rasterisation_backward_c96_0_kernel_0_serial\n",
            "[  0.00%   0.000 s     20x |    0.008     0.016     0.036 ms] sample_from_point_c100_0_kernel_0_serial\n",
            "[  0.00%   0.000 s     20x |    0.007     0.014     0.025 ms] sample_from_point_c100_0_kernel_1_range_for\n",
            "-------------------------------------------------------------------------\n",
            "[100.00%] Total execution time:  49.796 s   number of results: 19\n",
            "=========================================================================\n",
            "=========================================================================\n",
            "Kernel Profiler(count, default) @ CUDA on Tesla T4\n",
            "=========================================================================\n",
            "[      %     total   count |      min       avg       max   ] Kernel name\n",
            "-------------------------------------------------------------------------\n",
            "-------------------------------------------------------------------------\n",
            "[100.00%] Total execution time:   0.000 s   number of results: 0\n",
            "=========================================================================\n",
            "\n",
            "  0% 0/22 [00:00<?, ?it/s]\u001b[A\n",
            "  5% 1/22 [00:07<02:29,  7.14s/it]\u001b[A\n",
            "  9% 2/22 [00:11<01:44,  5.24s/it]\u001b[A\n",
            " 14% 3/22 [00:15<01:32,  4.85s/it]\u001b[A\n",
            " 18% 4/22 [00:21<01:33,  5.21s/it]\u001b[A\n",
            " 23% 5/22 [00:27<01:32,  5.46s/it]\u001b[A\n",
            " 27% 6/22 [00:32<01:25,  5.37s/it]\u001b[A\n",
            " 32% 7/22 [00:36<01:17,  5.15s/it]\u001b[A\n",
            " 36% 8/22 [00:40<01:06,  4.73s/it]\u001b[A\n",
            " 41% 9/22 [00:46<01:06,  5.08s/it]\u001b[A\n",
            " 45% 10/22 [00:52<01:02,  5.21s/it]\u001b[A\n",
            " 50% 11/22 [00:57<00:57,  5.19s/it]\u001b[A\n",
            " 55% 12/22 [01:00<00:47,  4.73s/it]\u001b[A\n",
            " 59% 13/22 [01:05<00:41,  4.62s/it]\u001b[A\n",
            " 64% 14/22 [01:12<00:44,  5.53s/it]\u001b[A\n",
            " 68% 15/22 [01:18<00:39,  5.58s/it]\u001b[A\n",
            " 73% 16/22 [01:22<00:30,  5.10s/it]\u001b[A\n",
            " 77% 17/22 [01:26<00:23,  4.66s/it]\u001b[A\n",
            " 82% 18/22 [01:30<00:18,  4.60s/it]\u001b[A\n",
            " 86% 19/22 [01:37<00:15,  5.25s/it]\u001b[A\n",
            " 91% 20/22 [01:43<00:11,  5.58s/it]\u001b[A\n",
            " 95% 21/22 [01:48<00:05,  5.31s/it]\u001b[A\n",
            "100% 22/22 [01:52<00:00,  5.13s/it]\n",
            "=========================================================================\n",
            "Kernel Profiler(count, default) @ CUDA on Tesla T4\n",
            "=========================================================================\n",
            "[      %     total   count |      min       avg       max   ] Kernel name\n",
            "-------------------------------------------------------------------------\n",
            "[ 45.91%   0.109 s     22x |    4.444     4.937     5.853 ms] gaussian_point_rasterisation_c94_0_kernel_1_range_for\n",
            "[ 25.64%   0.061 s     22x |    2.089     2.757     3.663 ms] generate_point_sort_key_by_num_overlap_tiles_c88_0_kernel_1_range_for\n",
            "[ 23.29%   0.055 s     22x |    1.886     2.504     3.361 ms] generate_num_overlap_tiles_c86_0_kernel_1_range_for\n",
            "[  3.25%   0.008 s     22x |    0.035     0.349     6.892 ms] filter_point_in_camera_c82_0_kernel_1_range_for\n",
            "[  0.71%   0.002 s     22x |    0.067     0.076     0.098 ms] generate_point_attributes_in_camera_plane_c92_0_kernel_1_range_for\n",
            "[  0.22%   0.001 s     22x |    0.019     0.023     0.047 ms] find_tile_start_and_end_c90_0_kernel_1_range_for\n",
            "[  0.18%   0.000 s     22x |    0.014     0.020     0.049 ms] filter_point_in_camera_c82_0_kernel_0_serial\n",
            "[  0.17%   0.000 s     22x |    0.012     0.018     0.037 ms] generate_point_attributes_in_camera_plane_c92_0_kernel_0_serial\n",
            "[  0.15%   0.000 s     22x |    0.012     0.016     0.027 ms] generate_point_sort_key_by_num_overlap_tiles_c88_0_kernel_0_serial\n",
            "[  0.15%   0.000 s     22x |    0.012     0.016     0.030 ms] gaussian_point_rasterisation_c94_0_kernel_0_serial\n",
            "[  0.15%   0.000 s     22x |    0.010     0.016     0.032 ms] generate_num_overlap_tiles_c86_0_kernel_0_serial\n",
            "[  0.11%   0.000 s     22x |    0.006     0.012     0.031 ms] find_tile_start_and_end_c90_0_kernel_0_serial\n",
            "[  0.09%   0.000 s     22x |    0.008     0.010     0.022 ms] find_tile_start_and_end_c90_0_kernel_2_serial\n",
            "-------------------------------------------------------------------------\n",
            "[100.00%] Total execution time:   0.237 s   number of results: 13\n",
            "=========================================================================\n",
            " 13% 4032/30001 [24:50<1:11:19,  6.07it/s]/usr/local/lib/python3.10/site-packages/torch/utils/data/dataloader.py:560: UserWarning: This DataLoader will create 4 worker processes in total. Our suggested max number of worker in current system is 2, which is smaller than what this DataLoader is going to create. Please be aware that excessive worker creation might get DataLoader running slow or even freeze, lower the worker number to avoid potential slowness/freeze if necessary.\n",
            "  warnings.warn(_create_warning_msg(\n",
            " 14% 4100/30001 [25:05<1:31:06,  4.74it/s]num_valid_points=22928;\n",
            "num_over_reconstructed: 104, num_under_reconstructed: 0\n",
            "total valid points: 22928 -> 22746, num_densify_points: 104, num_fillable_densify_points: 104\n",
            "num_transparent_points: 286, num_floaters_points: 0\n",
            " 14% 4200/30001 [25:27<1:13:22,  5.86it/s]1072 1920\n",
            "num_valid_points=22746;\n",
            "num_over_reconstructed: 160, num_under_reconstructed: 0\n",
            "total valid points: 22746 -> 22869, num_densify_points: 160, num_fillable_densify_points: 160\n",
            "num_transparent_points: 36, num_floaters_points: 1\n",
            " 14% 4300/30001 [25:59<1:34:05,  4.55it/s]num_valid_points=22869;\n",
            "num_over_reconstructed: 220, num_under_reconstructed: 0\n",
            "total valid points: 22869 -> 23069, num_densify_points: 220, num_fillable_densify_points: 220\n",
            "num_transparent_points: 20, num_floaters_points: 0\n",
            " 15% 4400/30001 [26:23<1:33:31,  4.56it/s]1072 1920\n",
            "num_valid_points=23069;\n",
            "num_over_reconstructed: 112, num_under_reconstructed: 4\n",
            "total valid points: 23069 -> 23160, num_densify_points: 116, num_fillable_densify_points: 116\n",
            "num_transparent_points: 24, num_floaters_points: 1\n",
            " 15% 4500/30001 [26:56<2:02:23,  3.47it/s]num_valid_points=23160;\n",
            "num_over_reconstructed: 117, num_under_reconstructed: 14\n",
            "total valid points: 23160 -> 23255, num_densify_points: 131, num_fillable_densify_points: 131\n",
            "num_transparent_points: 34, num_floaters_points: 2\n",
            " 15% 4600/30001 [27:19<1:26:28,  4.90it/s]1072 1920\n",
            "num_valid_points=23255;\n",
            "num_over_reconstructed: 122, num_under_reconstructed: 17\n",
            "total valid points: 23255 -> 23360, num_densify_points: 139, num_fillable_densify_points: 139\n",
            "num_transparent_points: 34, num_floaters_points: 0\n",
            " 16% 4700/30001 [27:47<1:08:01,  6.20it/s]num_valid_points=23360;\n",
            "num_over_reconstructed: 209, num_under_reconstructed: 13\n",
            "total valid points: 23360 -> 23549, num_densify_points: 222, num_fillable_densify_points: 222\n",
            "num_transparent_points: 32, num_floaters_points: 1\n",
            " 16% 4800/30001 [28:11<1:19:33,  5.28it/s]1072 1920\n",
            "num_valid_points=23549;\n",
            "num_over_reconstructed: 242, num_under_reconstructed: 11\n",
            "total valid points: 23549 -> 23758, num_densify_points: 253, num_fillable_densify_points: 253\n",
            "num_transparent_points: 42, num_floaters_points: 2\n",
            " 16% 4900/30001 [28:39<1:11:59,  5.81it/s]num_valid_points=23758;\n",
            "num_over_reconstructed: 252, num_under_reconstructed: 22\n",
            "total valid points: 23758 -> 23973, num_densify_points: 274, num_fillable_densify_points: 274\n",
            "num_transparent_points: 59, num_floaters_points: 0\n",
            " 17% 5000/30001 [29:04<2:57:50,  2.34it/s]1072 1920\n",
            "num_valid_points=23973;\n",
            "num_over_reconstructed: 109, num_under_reconstructed: 25\n",
            "total valid points: 23973 -> 24064, num_densify_points: 134, num_fillable_densify_points: 134\n",
            "num_transparent_points: 43, num_floaters_points: 0\n",
            "=========================================================================\n",
            "Kernel Profiler(count, default) @ CUDA on Tesla T4\n",
            "=========================================================================\n",
            "[      %     total   count |      min       avg       max   ] Kernel name\n",
            "-------------------------------------------------------------------------\n",
            "[ 83.37%  86.599 s   1000x |   37.296    86.599   189.908 ms] gaussian_point_rasterisation_backward_c96_0_kernel_1_range_for\n",
            "[  6.02%   6.255 s   1000x |    0.883     6.255   103.023 ms] generate_point_sort_key_by_num_overlap_tiles_c88_0_kernel_1_range_for\n",
            "[  5.85%   6.077 s   1000x |    0.887     6.077   101.706 ms] generate_num_overlap_tiles_c86_0_kernel_1_range_for\n",
            "[  2.73%   2.838 s   1000x |    1.837     2.838    18.780 ms] gaussian_point_rasterisation_c94_0_kernel_1_range_for\n",
            "[  1.62%   1.683 s   1000x |    1.659     1.683     2.726 ms] gaussian_point_rasterisation_backward_c96_0_kernel_3_range_for\n",
            "[  0.06%   0.062 s   1000x |    0.010     0.062    12.075 ms] filter_point_in_camera_c82_0_kernel_0_serial\n",
            "[  0.05%   0.054 s   1000x |    0.008     0.054     7.624 ms] generate_point_attributes_in_camera_plane_c92_0_kernel_0_serial\n",
            "[  0.05%   0.048 s   1000x |    0.013     0.048     4.407 ms] gaussian_point_rasterisation_backward_c96_0_kernel_2_serial\n",
            "[  0.05%   0.048 s   1000x |    0.035     0.048     2.466 ms] generate_point_attributes_in_camera_plane_c92_0_kernel_1_range_for\n",
            "[  0.04%   0.041 s   1000x |    0.020     0.041     7.356 ms] filter_point_in_camera_c82_0_kernel_1_range_for\n",
            "[  0.04%   0.040 s   1000x |    0.008     0.040     6.267 ms] gaussian_point_rasterisation_c94_0_kernel_0_serial\n",
            "[  0.04%   0.037 s   1000x |    0.007     0.037     9.634 ms] generate_num_overlap_tiles_c86_0_kernel_0_serial\n",
            "[  0.02%   0.026 s   1000x |    0.016     0.026     1.411 ms] find_tile_start_and_end_c90_0_kernel_1_range_for\n",
            "[  0.02%   0.024 s   1000x |    0.008     0.024     4.242 ms] generate_point_sort_key_by_num_overlap_tiles_c88_0_kernel_0_serial\n",
            "[  0.02%   0.020 s   1000x |    0.003     0.020     4.949 ms] find_tile_start_and_end_c90_0_kernel_0_serial\n",
            "[  0.02%   0.016 s   1000x |    0.004     0.016     6.338 ms] find_tile_start_and_end_c90_0_kernel_2_serial\n",
            "[  0.00%   0.005 s   1000x |    0.004     0.005     0.043 ms] gaussian_point_rasterisation_backward_c96_0_kernel_0_serial\n",
            "[  0.00%   0.000 s     20x |    0.009     0.018     0.046 ms] sample_from_point_c100_0_kernel_0_serial\n",
            "[  0.00%   0.000 s     20x |    0.008     0.014     0.025 ms] sample_from_point_c100_0_kernel_1_range_for\n",
            "-------------------------------------------------------------------------\n",
            "[100.00%] Total execution time: 103.875 s   number of results: 19\n",
            "=========================================================================\n",
            "=========================================================================\n",
            "Kernel Profiler(count, default) @ CUDA on Tesla T4\n",
            "=========================================================================\n",
            "[      %     total   count |      min       avg       max   ] Kernel name\n",
            "-------------------------------------------------------------------------\n",
            "-------------------------------------------------------------------------\n",
            "[100.00%] Total execution time:   0.000 s   number of results: 0\n",
            "=========================================================================\n",
            "\n",
            "  0% 0/22 [00:00<?, ?it/s]\u001b[A\n",
            "  5% 1/22 [00:08<02:54,  8.30s/it]\u001b[A\n",
            "  9% 2/22 [00:13<02:13,  6.69s/it]\u001b[A\n",
            " 14% 3/22 [00:18<01:50,  5.84s/it]\u001b[A\n",
            " 18% 4/22 [00:21<01:27,  4.84s/it]\u001b[A\n",
            " 23% 5/22 [00:27<01:25,  5.05s/it]\u001b[A\n",
            " 27% 6/22 [00:34<01:34,  5.88s/it]\u001b[A\n",
            " 32% 7/22 [00:40<01:26,  5.79s/it]\u001b[A\n",
            " 36% 8/22 [00:45<01:15,  5.39s/it]\u001b[A\n",
            " 41% 9/22 [00:50<01:09,  5.32s/it]\u001b[A\n",
            " 45% 10/22 [00:56<01:05,  5.48s/it]\u001b[A\n",
            " 50% 11/22 [01:02<01:03,  5.77s/it]\u001b[A\n",
            " 55% 12/22 [01:06<00:51,  5.18s/it]\u001b[A\n",
            " 59% 13/22 [01:10<00:43,  4.84s/it]\u001b[A\n",
            " 64% 14/22 [01:15<00:39,  4.96s/it]\u001b[A\n",
            " 68% 15/22 [01:21<00:36,  5.15s/it]\u001b[A\n",
            " 73% 16/22 [01:26<00:31,  5.18s/it]\u001b[A\n",
            " 77% 17/22 [01:30<00:24,  4.82s/it]\u001b[A\n",
            " 82% 18/22 [01:35<00:19,  4.77s/it]\u001b[A\n",
            " 86% 19/22 [01:40<00:14,  4.95s/it]\u001b[A\n",
            " 91% 20/22 [01:47<00:11,  5.54s/it]\u001b[A\n",
            " 95% 21/22 [01:53<00:05,  5.69s/it]\u001b[A\n",
            "100% 22/22 [01:57<00:00,  5.34s/it]\n",
            "=========================================================================\n",
            "Kernel Profiler(count, default) @ CUDA on Tesla T4\n",
            "=========================================================================\n",
            "[      %     total   count |      min       avg       max   ] Kernel name\n",
            "-------------------------------------------------------------------------\n",
            "[ 43.91%   0.541 s     22x |    3.486    24.583    93.320 ms] generate_num_overlap_tiles_c86_0_kernel_1_range_for\n",
            "[ 42.64%   0.525 s     22x |    4.011    23.872    92.832 ms] generate_point_sort_key_by_num_overlap_tiles_c88_0_kernel_1_range_for\n",
            "[ 12.98%   0.160 s     22x |    4.474     7.269     8.792 ms] gaussian_point_rasterisation_c94_0_kernel_1_range_for\n",
            "[  0.15%   0.002 s     22x |    0.070     0.084     0.125 ms] generate_point_attributes_in_camera_plane_c92_0_kernel_1_range_for\n",
            "[  0.07%   0.001 s     22x |    0.035     0.038     0.063 ms] filter_point_in_camera_c82_0_kernel_1_range_for\n",
            "[  0.05%   0.001 s     22x |    0.023     0.030     0.047 ms] find_tile_start_and_end_c90_0_kernel_1_range_for\n",
            "[  0.04%   0.000 s     22x |    0.016     0.020     0.057 ms] filter_point_in_camera_c82_0_kernel_0_serial\n",
            "[  0.03%   0.000 s     22x |    0.014     0.019     0.043 ms] generate_point_attributes_in_camera_plane_c92_0_kernel_0_serial\n",
            "[  0.03%   0.000 s     22x |    0.012     0.016     0.030 ms] generate_point_sort_key_by_num_overlap_tiles_c88_0_kernel_0_serial\n",
            "[  0.03%   0.000 s     22x |    0.012     0.016     0.033 ms] gaussian_point_rasterisation_c94_0_kernel_0_serial\n",
            "[  0.03%   0.000 s     22x |    0.012     0.015     0.028 ms] generate_num_overlap_tiles_c86_0_kernel_0_serial\n",
            "[  0.02%   0.000 s     22x |    0.008     0.011     0.023 ms] find_tile_start_and_end_c90_0_kernel_2_serial\n",
            "[  0.02%   0.000 s     22x |    0.006     0.009     0.021 ms] find_tile_start_and_end_c90_0_kernel_0_serial\n",
            "-------------------------------------------------------------------------\n",
            "[100.00%] Total execution time:   1.232 s   number of results: 13\n",
            "=========================================================================\n",
            " 17% 5040/30001 [31:16<1:24:07,  4.95it/s]/usr/local/lib/python3.10/site-packages/torch/utils/data/dataloader.py:560: UserWarning: This DataLoader will create 4 worker processes in total. Our suggested max number of worker in current system is 2, which is smaller than what this DataLoader is going to create. Please be aware that excessive worker creation might get DataLoader running slow or even freeze, lower the worker number to avoid potential slowness/freeze if necessary.\n",
            "  warnings.warn(_create_warning_msg(\n",
            " 17% 5100/30001 [31:32<1:35:24,  4.35it/s]num_valid_points=24064;\n",
            "num_over_reconstructed: 249, num_under_reconstructed: 13\n",
            "total valid points: 24064 -> 24281, num_densify_points: 262, num_fillable_densify_points: 262\n",
            "num_transparent_points: 45, num_floaters_points: 0\n",
            " 17% 5200/30001 [31:58<1:30:00,  4.59it/s]1072 1920\n",
            "num_valid_points=24281;\n",
            "num_over_reconstructed: 145, num_under_reconstructed: 18\n",
            "total valid points: 24281 -> 24396, num_densify_points: 163, num_fillable_densify_points: 163\n",
            "num_transparent_points: 47, num_floaters_points: 1\n",
            " 18% 5300/30001 [32:33<2:06:58,  3.24it/s]num_valid_points=24396;\n",
            "num_over_reconstructed: 74, num_under_reconstructed: 38\n",
            "total valid points: 24396 -> 24458, num_densify_points: 112, num_fillable_densify_points: 112\n",
            "num_transparent_points: 49, num_floaters_points: 1\n",
            " 18% 5400/30001 [32:57<1:33:04,  4.41it/s]1072 1920\n",
            "num_valid_points=24458;\n",
            "num_over_reconstructed: 71, num_under_reconstructed: 40\n",
            "total valid points: 24458 -> 24536, num_densify_points: 111, num_fillable_densify_points: 111\n",
            "num_transparent_points: 33, num_floaters_points: 0\n",
            " 18% 5500/30001 [33:27<1:19:34,  5.13it/s]num_valid_points=24536;\n",
            "num_over_reconstructed: 79, num_under_reconstructed: 48\n",
            "total valid points: 24536 -> 24618, num_densify_points: 127, num_fillable_densify_points: 127\n",
            "num_transparent_points: 44, num_floaters_points: 1\n",
            " 19% 5600/30001 [33:53<1:27:49,  4.63it/s]1072 1920\n",
            "num_valid_points=24618;\n",
            "num_over_reconstructed: 51, num_under_reconstructed: 57\n",
            "total valid points: 24618 -> 24675, num_densify_points: 108, num_fillable_densify_points: 108\n",
            "num_transparent_points: 49, num_floaters_points: 2\n",
            " 19% 5700/30001 [34:23<1:21:16,  4.98it/s]num_valid_points=24675;\n",
            "num_over_reconstructed: 126, num_under_reconstructed: 20\n",
            "total valid points: 24675 -> 24772, num_densify_points: 146, num_fillable_densify_points: 146\n",
            "num_transparent_points: 44, num_floaters_points: 5\n",
            " 19% 5800/30001 [34:49<2:14:06,  3.01it/s]1072 1920\n",
            "num_valid_points=24772;\n",
            "num_over_reconstructed: 51, num_under_reconstructed: 63\n",
            "total valid points: 24772 -> 24844, num_densify_points: 114, num_fillable_densify_points: 114\n",
            "num_transparent_points: 38, num_floaters_points: 4\n",
            " 20% 5900/30001 [35:19<1:27:22,  4.60it/s]num_valid_points=24844;\n",
            "num_over_reconstructed: 148, num_under_reconstructed: 32\n",
            "total valid points: 24844 -> 24965, num_densify_points: 180, num_fillable_densify_points: 180\n",
            "num_transparent_points: 57, num_floaters_points: 2\n",
            " 20% 6000/30001 [35:45<1:35:03,  4.21it/s]1072 1920\n",
            "num_valid_points=24965;\n",
            "num_over_reconstructed: 124, num_under_reconstructed: 45\n",
            "total valid points: 24965 -> 25069, num_densify_points: 169, num_fillable_densify_points: 169\n",
            "num_transparent_points: 55, num_floaters_points: 10\n",
            "=========================================================================\n",
            "Kernel Profiler(count, default) @ CUDA on Tesla T4\n",
            "=========================================================================\n",
            "[      %     total   count |      min       avg       max   ] Kernel name\n",
            "-------------------------------------------------------------------------\n",
            "[ 73.89%  91.808 s   1000x |   48.026    91.808   185.519 ms] gaussian_point_rasterisation_backward_c96_0_kernel_1_range_for\n",
            "[ 11.12%  13.813 s   1000x |    1.282    13.813    76.394 ms] generate_point_sort_key_by_num_overlap_tiles_c88_0_kernel_1_range_for\n",
            "[ 10.88%  13.520 s   1000x |    1.163    13.520    75.903 ms] generate_num_overlap_tiles_c86_0_kernel_1_range_for\n",
            "[  2.40%   2.977 s   1000x |    2.556     2.977     8.438 ms] gaussian_point_rasterisation_c94_0_kernel_1_range_for\n",
            "[  1.36%   1.686 s   1000x |    1.664     1.686     2.713 ms] gaussian_point_rasterisation_backward_c96_0_kernel_3_range_for\n",
            "[  0.06%   0.070 s   1000x |    0.009     0.070    11.536 ms] filter_point_in_camera_c82_0_kernel_0_serial\n",
            "[  0.06%   0.069 s   1000x |    0.039     0.069    10.084 ms] generate_point_attributes_in_camera_plane_c92_0_kernel_1_range_for\n",
            "[  0.05%   0.066 s   1000x |    0.013     0.066    12.646 ms] gaussian_point_rasterisation_backward_c96_0_kernel_2_serial\n",
            "[  0.05%   0.057 s   1000x |    0.020     0.057     9.013 ms] filter_point_in_camera_c82_0_kernel_1_range_for\n",
            "[  0.03%   0.037 s   1000x |    0.008     0.037    11.018 ms] generate_point_attributes_in_camera_plane_c92_0_kernel_0_serial\n",
            "[  0.03%   0.033 s   1000x |    0.007     0.033     7.954 ms] generate_num_overlap_tiles_c86_0_kernel_0_serial\n",
            "[  0.02%   0.030 s   1000x |    0.008     0.030    10.435 ms] gaussian_point_rasterisation_c94_0_kernel_0_serial\n",
            "[  0.02%   0.029 s   1000x |    0.018     0.029     2.042 ms] find_tile_start_and_end_c90_0_kernel_1_range_for\n",
            "[  0.02%   0.026 s   1000x |    0.003     0.026     4.412 ms] find_tile_start_and_end_c90_0_kernel_0_serial\n",
            "[  0.01%   0.017 s   1000x |    0.008     0.017     0.576 ms] generate_point_sort_key_by_num_overlap_tiles_c88_0_kernel_0_serial\n",
            "[  0.01%   0.011 s   1000x |    0.004     0.011     1.260 ms] find_tile_start_and_end_c90_0_kernel_2_serial\n",
            "[  0.00%   0.005 s   1000x |    0.004     0.005     0.051 ms] gaussian_point_rasterisation_backward_c96_0_kernel_0_serial\n",
            "[  0.00%   0.000 s     20x |    0.008     0.015     0.031 ms] sample_from_point_c100_0_kernel_0_serial\n",
            "[  0.00%   0.000 s     20x |    0.008     0.014     0.026 ms] sample_from_point_c100_0_kernel_1_range_for\n",
            "-------------------------------------------------------------------------\n",
            "[100.00%] Total execution time: 124.256 s   number of results: 19\n",
            "=========================================================================\n",
            "=========================================================================\n",
            "Kernel Profiler(count, default) @ CUDA on Tesla T4\n",
            "=========================================================================\n",
            "[      %     total   count |      min       avg       max   ] Kernel name\n",
            "-------------------------------------------------------------------------\n",
            "-------------------------------------------------------------------------\n",
            "[100.00%] Total execution time:   0.000 s   number of results: 0\n",
            "=========================================================================\n",
            "\n",
            "  0% 0/22 [00:00<?, ?it/s]\u001b[A\n",
            "  5% 1/22 [00:07<02:33,  7.29s/it]\u001b[A\n",
            "  9% 2/22 [00:10<01:42,  5.14s/it]\u001b[A\n",
            " 14% 3/22 [00:14<01:23,  4.39s/it]\u001b[A\n",
            " 18% 4/22 [00:17<01:10,  3.93s/it]\u001b[A\n",
            " 23% 5/22 [00:23<01:17,  4.55s/it]\u001b[A\n",
            " 27% 6/22 [00:28<01:18,  4.89s/it]\u001b[A\n",
            " 32% 7/22 [00:34<01:18,  5.22s/it]\u001b[A\n",
            " 36% 8/22 [00:38<01:05,  4.64s/it]\u001b[A\n",
            " 41% 9/22 [00:41<00:55,  4.28s/it]\u001b[A\n",
            " 45% 10/22 [00:45<00:51,  4.28s/it]\u001b[A\n",
            " 50% 11/22 [00:51<00:52,  4.73s/it]\u001b[A\n",
            " 55% 12/22 [00:57<00:50,  5.00s/it]\u001b[A\n",
            " 59% 13/22 [01:01<00:42,  4.75s/it]\u001b[A\n",
            " 64% 14/22 [01:05<00:37,  4.65s/it]\u001b[A\n",
            " 68% 15/22 [01:10<00:31,  4.53s/it]\u001b[A\n",
            " 73% 16/22 [01:14<00:27,  4.61s/it]\u001b[A\n",
            " 77% 17/22 [01:19<00:23,  4.74s/it]\u001b[A\n",
            " 82% 18/22 [01:24<00:19,  4.75s/it]\u001b[A\n",
            " 86% 19/22 [01:28<00:13,  4.54s/it]\u001b[A\n",
            " 91% 20/22 [01:32<00:08,  4.35s/it]\u001b[A\n",
            " 95% 21/22 [01:38<00:04,  4.84s/it]\u001b[A\n",
            "100% 22/22 [01:44<00:00,  4.74s/it]\n",
            "=========================================================================\n",
            "Kernel Profiler(count, default) @ CUDA on Tesla T4\n",
            "=========================================================================\n",
            "[      %     total   count |      min       avg       max   ] Kernel name\n",
            "-------------------------------------------------------------------------\n",
            "[ 44.77%   0.709 s     22x |    3.775    32.244    90.385 ms] generate_num_overlap_tiles_c86_0_kernel_1_range_for\n",
            "[ 44.72%   0.709 s     22x |    4.348    32.209    87.972 ms] generate_point_sort_key_by_num_overlap_tiles_c88_0_kernel_1_range_for\n",
            "[ 10.15%   0.161 s     22x |    3.480     7.313     9.271 ms] gaussian_point_rasterisation_c94_0_kernel_1_range_for\n",
            "[  0.11%   0.002 s     22x |    0.074     0.080     0.096 ms] generate_point_attributes_in_camera_plane_c92_0_kernel_1_range_for\n",
            "[  0.05%   0.001 s     22x |    0.035     0.038     0.068 ms] filter_point_in_camera_c82_0_kernel_1_range_for\n",
            "[  0.04%   0.001 s     22x |    0.024     0.029     0.043 ms] find_tile_start_and_end_c90_0_kernel_1_range_for\n",
            "[  0.03%   0.000 s     22x |    0.015     0.020     0.035 ms] filter_point_in_camera_c82_0_kernel_0_serial\n",
            "[  0.02%   0.000 s     22x |    0.014     0.017     0.035 ms] generate_point_attributes_in_camera_plane_c92_0_kernel_0_serial\n",
            "[  0.02%   0.000 s     22x |    0.012     0.016     0.046 ms] gaussian_point_rasterisation_c94_0_kernel_0_serial\n",
            "[  0.02%   0.000 s     22x |    0.012     0.016     0.032 ms] generate_point_sort_key_by_num_overlap_tiles_c88_0_kernel_0_serial\n",
            "[  0.02%   0.000 s     22x |    0.011     0.015     0.033 ms] generate_num_overlap_tiles_c86_0_kernel_0_serial\n",
            "[  0.01%   0.000 s     22x |    0.006     0.011     0.029 ms] find_tile_start_and_end_c90_0_kernel_0_serial\n",
            "[  0.01%   0.000 s     22x |    0.007     0.010     0.018 ms] find_tile_start_and_end_c90_0_kernel_2_serial\n",
            "-------------------------------------------------------------------------\n",
            "[100.00%] Total execution time:   1.584 s   number of results: 13\n",
            "=========================================================================\n",
            " 20% 6006/30001 [37:37<38:51:57,  5.83s/it]/usr/local/lib/python3.10/site-packages/torch/utils/data/dataloader.py:560: UserWarning: This DataLoader will create 4 worker processes in total. Our suggested max number of worker in current system is 2, which is smaller than what this DataLoader is going to create. Please be aware that excessive worker creation might get DataLoader running slow or even freeze, lower the worker number to avoid potential slowness/freeze if necessary.\n",
            "  warnings.warn(_create_warning_msg(\n",
            " 20% 6100/30001 [38:03<1:47:49,  3.69it/s]num_valid_points=25069;\n",
            "num_over_reconstructed: 71, num_under_reconstructed: 57\n",
            "total valid points: 25069 -> 25151, num_densify_points: 128, num_fillable_densify_points: 128\n",
            "num_transparent_points: 46, num_floaters_points: 0\n",
            " 21% 6200/30001 [38:30<1:23:57,  4.72it/s]1072 1920\n",
            "num_valid_points=25151;\n",
            "num_over_reconstructed: 49, num_under_reconstructed: 65\n",
            "total valid points: 25151 -> 25217, num_densify_points: 114, num_fillable_densify_points: 114\n",
            "num_transparent_points: 40, num_floaters_points: 8\n",
            " 21% 6300/30001 [39:01<1:25:19,  4.63it/s]num_valid_points=25217;\n",
            "num_over_reconstructed: 113, num_under_reconstructed: 41\n",
            "total valid points: 25217 -> 25323, num_densify_points: 154, num_fillable_densify_points: 154\n",
            "num_transparent_points: 44, num_floaters_points: 4\n",
            " 21% 6400/30001 [39:29<1:44:42,  3.76it/s]1072 1920\n",
            "num_valid_points=25323;\n",
            "num_over_reconstructed: 126, num_under_reconstructed: 90\n",
            "total valid points: 25323 -> 25503, num_densify_points: 216, num_fillable_densify_points: 216\n",
            "num_transparent_points: 36, num_floaters_points: 0\n",
            " 22% 6500/30001 [40:03<1:41:55,  3.84it/s]num_valid_points=25503;\n",
            "num_over_reconstructed: 158, num_under_reconstructed: 75\n",
            "total valid points: 25503 -> 25690, num_densify_points: 233, num_fillable_densify_points: 233\n",
            "num_transparent_points: 45, num_floaters_points: 1\n",
            " 22% 6600/30001 [40:31<1:53:23,  3.44it/s]1072 1920\n",
            "num_valid_points=25690;\n",
            "num_over_reconstructed: 30, num_under_reconstructed: 87\n",
            "total valid points: 25690 -> 25743, num_densify_points: 117, num_fillable_densify_points: 117\n",
            "num_transparent_points: 59, num_floaters_points: 5\n",
            " 22% 6700/30001 [41:04<1:27:34,  4.43it/s]num_valid_points=25743;\n",
            "num_over_reconstructed: 93, num_under_reconstructed: 62\n",
            "total valid points: 25743 -> 25861, num_densify_points: 155, num_fillable_densify_points: 155\n",
            "num_transparent_points: 32, num_floaters_points: 5\n",
            " 23% 6800/30001 [41:31<1:24:18,  4.59it/s]1072 1920\n",
            "num_valid_points=25861;\n",
            "num_over_reconstructed: 114, num_under_reconstructed: 69\n",
            "total valid points: 25861 -> 25999, num_densify_points: 183, num_fillable_densify_points: 183\n",
            "num_transparent_points: 42, num_floaters_points: 3\n",
            " 23% 6900/30001 [42:06<1:40:36,  3.83it/s]num_valid_points=25999;\n",
            "num_over_reconstructed: 49, num_under_reconstructed: 68\n",
            "total valid points: 25999 -> 26060, num_densify_points: 117, num_fillable_densify_points: 117\n",
            "num_transparent_points: 50, num_floaters_points: 6\n",
            " 23% 7000/30001 [42:32<1:37:25,  3.93it/s]1072 1920\n",
            "num_valid_points=26060;\n",
            "num_over_reconstructed: 44, num_under_reconstructed: 73\n",
            "total valid points: 26060 -> 26129, num_densify_points: 117, num_fillable_densify_points: 117\n",
            "num_transparent_points: 42, num_floaters_points: 6\n",
            "=========================================================================\n",
            "Kernel Profiler(count, default) @ CUDA on Tesla T4\n",
            "=========================================================================\n",
            "[      %     total   count |      min       avg       max   ] Kernel name\n",
            "-------------------------------------------------------------------------\n",
            "[ 67.98%  96.322 s   1000x |   56.334    96.322   175.059 ms] gaussian_point_rasterisation_backward_c96_0_kernel_1_range_for\n",
            "[ 14.24%  20.179 s   1000x |    1.464    20.179   103.462 ms] generate_point_sort_key_by_num_overlap_tiles_c88_0_kernel_1_range_for\n",
            "[ 14.13%  20.013 s   1000x |    1.324    20.013   158.515 ms] generate_num_overlap_tiles_c86_0_kernel_1_range_for\n",
            "[  2.16%   3.060 s   1000x |    2.664     3.060     8.169 ms] gaussian_point_rasterisation_c94_0_kernel_1_range_for\n",
            "[  1.19%   1.689 s   1000x |    1.663     1.689     2.968 ms] gaussian_point_rasterisation_backward_c96_0_kernel_3_range_for\n",
            "[  0.06%   0.079 s   1000x |    0.041     0.079    16.058 ms] generate_point_attributes_in_camera_plane_c92_0_kernel_1_range_for\n",
            "[  0.04%   0.055 s   1000x |    0.006     0.055    15.729 ms] generate_num_overlap_tiles_c86_0_kernel_0_serial\n",
            "[  0.04%   0.053 s   1000x |    0.012     0.053    10.535 ms] gaussian_point_rasterisation_backward_c96_0_kernel_2_serial\n",
            "[  0.03%   0.045 s   1000x |    0.009     0.045    10.938 ms] generate_point_attributes_in_camera_plane_c92_0_kernel_0_serial\n",
            "[  0.03%   0.037 s   1000x |    0.010     0.037     7.688 ms] filter_point_in_camera_c82_0_kernel_0_serial\n",
            "[  0.03%   0.036 s   1000x |    0.006     0.036     9.054 ms] generate_point_sort_key_by_num_overlap_tiles_c88_0_kernel_0_serial\n",
            "[  0.02%   0.035 s   1000x |    0.020     0.035     4.178 ms] filter_point_in_camera_c82_0_kernel_1_range_for\n",
            "[  0.02%   0.026 s   1000x |    0.019     0.026     0.403 ms] find_tile_start_and_end_c90_0_kernel_1_range_for\n",
            "[  0.01%   0.016 s   1000x |    0.007     0.016     0.770 ms] gaussian_point_rasterisation_c94_0_kernel_0_serial\n",
            "[  0.01%   0.015 s   1000x |    0.005     0.015     5.024 ms] find_tile_start_and_end_c90_0_kernel_2_serial\n",
            "[  0.01%   0.014 s   1000x |    0.003     0.014     2.009 ms] find_tile_start_and_end_c90_0_kernel_0_serial\n",
            "[  0.00%   0.005 s   1000x |    0.004     0.005     0.058 ms] gaussian_point_rasterisation_backward_c96_0_kernel_0_serial\n",
            "[  0.00%   0.000 s     20x |    0.009     0.015     0.022 ms] sample_from_point_c100_0_kernel_0_serial\n",
            "[  0.00%   0.000 s     20x |    0.007     0.014     0.023 ms] sample_from_point_c100_0_kernel_1_range_for\n",
            "-------------------------------------------------------------------------\n",
            "[100.00%] Total execution time: 141.681 s   number of results: 19\n",
            "=========================================================================\n",
            "=========================================================================\n",
            "Kernel Profiler(count, default) @ CUDA on Tesla T4\n",
            "=========================================================================\n",
            "[      %     total   count |      min       avg       max   ] Kernel name\n",
            "-------------------------------------------------------------------------\n",
            "-------------------------------------------------------------------------\n",
            "[100.00%] Total execution time:   0.000 s   number of results: 0\n",
            "=========================================================================\n",
            "\n",
            "  0% 0/22 [00:00<?, ?it/s]\u001b[A\n",
            "  5% 1/22 [00:05<01:51,  5.33s/it]\u001b[A\n",
            "  9% 2/22 [00:10<01:49,  5.45s/it]\u001b[A\n",
            " 14% 3/22 [00:16<01:43,  5.43s/it]\u001b[A\n",
            " 18% 4/22 [00:22<01:44,  5.78s/it]\u001b[A\n",
            " 23% 5/22 [00:26<01:28,  5.22s/it]\u001b[A\n",
            " 27% 6/22 [00:30<01:14,  4.65s/it]\u001b[A\n",
            " 32% 7/22 [00:37<01:22,  5.49s/it]\u001b[A\n",
            " 36% 8/22 [00:44<01:20,  5.78s/it]\u001b[A\n",
            " 41% 9/22 [00:48<01:08,  5.30s/it]\u001b[A\n",
            " 45% 10/22 [00:53<01:03,  5.30s/it]\u001b[A\n",
            " 50% 11/22 [00:57<00:52,  4.81s/it]\u001b[A\n",
            " 55% 12/22 [01:02<00:50,  5.08s/it]\u001b[A\n",
            " 59% 13/22 [01:08<00:48,  5.34s/it]\u001b[A\n",
            " 64% 14/22 [01:14<00:43,  5.39s/it]\u001b[A\n",
            " 68% 15/22 [01:17<00:33,  4.82s/it]\u001b[A\n",
            " 73% 16/22 [01:20<00:25,  4.31s/it]\u001b[A\n",
            " 77% 17/22 [01:25<00:21,  4.37s/it]\u001b[A\n",
            " 82% 18/22 [01:30<00:18,  4.71s/it]\u001b[A\n",
            " 86% 19/22 [01:36<00:14,  5.00s/it]\u001b[A\n",
            " 91% 20/22 [01:40<00:09,  4.65s/it]\u001b[A\n",
            " 95% 21/22 [01:44<00:04,  4.46s/it]\u001b[A\n",
            "100% 22/22 [01:49<00:00,  5.00s/it]\n",
            "=========================================================================\n",
            "Kernel Profiler(count, default) @ CUDA on Tesla T4\n",
            "=========================================================================\n",
            "[      %     total   count |      min       avg       max   ] Kernel name\n",
            "-------------------------------------------------------------------------\n",
            "[ 53.68%   1.428 s     22x |    3.783    64.914   157.334 ms] generate_num_overlap_tiles_c86_0_kernel_1_range_for\n",
            "[ 40.58%   1.080 s     22x |    4.430    49.075    98.418 ms] generate_point_sort_key_by_num_overlap_tiles_c88_0_kernel_1_range_for\n",
            "[  5.52%   0.147 s     22x |    3.217     6.678     9.313 ms] gaussian_point_rasterisation_c94_0_kernel_1_range_for\n",
            "[  0.07%   0.002 s     22x |    0.074     0.084     0.108 ms] generate_point_attributes_in_camera_plane_c92_0_kernel_1_range_for\n",
            "[  0.03%   0.001 s     22x |    0.034     0.037     0.047 ms] filter_point_in_camera_c82_0_kernel_1_range_for\n",
            "[  0.02%   0.001 s     22x |    0.023     0.030     0.054 ms] find_tile_start_and_end_c90_0_kernel_1_range_for\n",
            "[  0.02%   0.000 s     22x |    0.014     0.020     0.063 ms] filter_point_in_camera_c82_0_kernel_0_serial\n",
            "[  0.01%   0.000 s     22x |    0.013     0.018     0.031 ms] generate_point_attributes_in_camera_plane_c92_0_kernel_0_serial\n",
            "[  0.01%   0.000 s     22x |    0.013     0.017     0.038 ms] gaussian_point_rasterisation_c94_0_kernel_0_serial\n",
            "[  0.01%   0.000 s     22x |    0.013     0.017     0.029 ms] generate_point_sort_key_by_num_overlap_tiles_c88_0_kernel_0_serial\n",
            "[  0.01%   0.000 s     22x |    0.010     0.015     0.033 ms] generate_num_overlap_tiles_c86_0_kernel_0_serial\n",
            "[  0.01%   0.000 s     22x |    0.006     0.015     0.048 ms] find_tile_start_and_end_c90_0_kernel_0_serial\n",
            "[  0.01%   0.000 s     22x |    0.007     0.010     0.033 ms] find_tile_start_and_end_c90_0_kernel_2_serial\n",
            "-------------------------------------------------------------------------\n",
            "[100.00%] Total execution time:   2.660 s   number of results: 13\n",
            "=========================================================================\n",
            " 23% 7014/30001 [44:31<3:36:29,  1.77it/s]/usr/local/lib/python3.10/site-packages/torch/utils/data/dataloader.py:560: UserWarning: This DataLoader will create 4 worker processes in total. Our suggested max number of worker in current system is 2, which is smaller than what this DataLoader is going to create. Please be aware that excessive worker creation might get DataLoader running slow or even freeze, lower the worker number to avoid potential slowness/freeze if necessary.\n",
            "  warnings.warn(_create_warning_msg(\n",
            " 24% 7100/30001 [44:55<3:30:39,  1.81it/s]num_valid_points=26129;\n",
            "num_over_reconstructed: 131, num_under_reconstructed: 72\n",
            "total valid points: 26129 -> 26282, num_densify_points: 203, num_fillable_densify_points: 203\n",
            "num_transparent_points: 47, num_floaters_points: 3\n",
            " 24% 7200/30001 [45:21<1:27:52,  4.32it/s]1072 1920\n",
            "num_valid_points=26282;\n",
            "num_over_reconstructed: 78, num_under_reconstructed: 49\n",
            "total valid points: 26282 -> 26335, num_densify_points: 127, num_fillable_densify_points: 127\n",
            "num_transparent_points: 67, num_floaters_points: 7\n",
            " 24% 7300/30001 [45:52<1:24:15,  4.49it/s]num_valid_points=26335;\n",
            "num_over_reconstructed: 152, num_under_reconstructed: 116\n",
            "total valid points: 26335 -> 26552, num_densify_points: 268, num_fillable_densify_points: 268\n",
            "num_transparent_points: 50, num_floaters_points: 1\n",
            " 25% 7400/30001 [46:18<1:31:03,  4.14it/s]1072 1920\n",
            "num_valid_points=26552;\n",
            "num_over_reconstructed: 95, num_under_reconstructed: 66\n",
            "total valid points: 26552 -> 26662, num_densify_points: 161, num_fillable_densify_points: 161\n",
            "num_transparent_points: 48, num_floaters_points: 3\n",
            " 25% 7500/30001 [46:47<1:18:15,  4.79it/s]num_valid_points=26662;\n",
            "num_over_reconstructed: 87, num_under_reconstructed: 75\n",
            "total valid points: 26662 -> 26772, num_densify_points: 162, num_fillable_densify_points: 162\n",
            "num_transparent_points: 51, num_floaters_points: 1\n",
            " 25% 7600/30001 [47:12<1:14:17,  5.03it/s]1072 1920\n",
            "num_valid_points=26772;\n",
            "num_over_reconstructed: 88, num_under_reconstructed: 69\n",
            "total valid points: 26772 -> 26882, num_densify_points: 157, num_fillable_densify_points: 157\n",
            "num_transparent_points: 44, num_floaters_points: 3\n",
            " 26% 7700/30001 [47:45<1:25:53,  4.33it/s]num_valid_points=26882;\n",
            "num_over_reconstructed: 58, num_under_reconstructed: 85\n",
            "total valid points: 26882 -> 26964, num_densify_points: 143, num_fillable_densify_points: 143\n",
            "num_transparent_points: 54, num_floaters_points: 7\n",
            " 26% 7800/30001 [48:09<1:26:22,  4.28it/s]1072 1920\n",
            "num_valid_points=26964;\n",
            "num_over_reconstructed: 46, num_under_reconstructed: 76\n",
            "total valid points: 26964 -> 27025, num_densify_points: 122, num_fillable_densify_points: 122\n",
            "num_transparent_points: 59, num_floaters_points: 2\n",
            " 26% 7900/30001 [48:41<2:13:01,  2.77it/s]num_valid_points=27025;\n",
            "num_over_reconstructed: 59, num_under_reconstructed: 59\n",
            "total valid points: 27025 -> 27098, num_densify_points: 118, num_fillable_densify_points: 118\n",
            "num_transparent_points: 41, num_floaters_points: 4\n",
            " 27% 8000/30001 [49:06<1:15:24,  4.86it/s]1072 1920\n",
            "num_valid_points=27098;\n",
            "num_over_reconstructed: 31, num_under_reconstructed: 87\n",
            "total valid points: 27098 -> 27170, num_densify_points: 118, num_fillable_densify_points: 118\n",
            "num_transparent_points: 37, num_floaters_points: 9\n",
            "=========================================================================\n",
            "Kernel Profiler(count, default) @ CUDA on Tesla T4\n",
            "=========================================================================\n",
            "[      %     total   count |      min       avg       max   ] Kernel name\n",
            "-------------------------------------------------------------------------\n",
            "[ 78.39%  98.268 s   1000x |   52.599    98.268   167.449 ms] gaussian_point_rasterisation_backward_c96_0_kernel_1_range_for\n",
            "[  8.83%  11.069 s   1000x |    1.495    11.069    75.787 ms] generate_point_sort_key_by_num_overlap_tiles_c88_0_kernel_1_range_for\n",
            "[  8.57%  10.745 s   1000x |    1.331    10.745    76.403 ms] generate_num_overlap_tiles_c86_0_kernel_1_range_for\n",
            "[  2.53%   3.166 s   1000x |    2.680     3.166    10.303 ms] gaussian_point_rasterisation_c94_0_kernel_1_range_for\n",
            "[  1.37%   1.718 s   1000x |    1.668     1.718     8.440 ms] gaussian_point_rasterisation_backward_c96_0_kernel_3_range_for\n",
            "[  0.05%   0.061 s   1000x |    0.043     0.061     6.441 ms] generate_point_attributes_in_camera_plane_c92_0_kernel_1_range_for\n",
            "[  0.04%   0.053 s   1000x |    0.010     0.053     8.068 ms] filter_point_in_camera_c82_0_kernel_0_serial\n",
            "[  0.04%   0.052 s   1000x |    0.007     0.052     9.253 ms] generate_num_overlap_tiles_c86_0_kernel_0_serial\n",
            "[  0.03%   0.042 s   1000x |    0.014     0.042     1.837 ms] gaussian_point_rasterisation_backward_c96_0_kernel_2_serial\n",
            "[  0.03%   0.041 s   1000x |    0.008     0.041    11.211 ms] gaussian_point_rasterisation_c94_0_kernel_0_serial\n",
            "[  0.03%   0.038 s   1000x |    0.021     0.038     6.861 ms] filter_point_in_camera_c82_0_kernel_1_range_for\n",
            "[  0.03%   0.032 s   1000x |    0.019     0.032     5.534 ms] find_tile_start_and_end_c90_0_kernel_1_range_for\n",
            "[  0.02%   0.031 s   1000x |    0.009     0.031     6.132 ms] generate_point_attributes_in_camera_plane_c92_0_kernel_0_serial\n",
            "[  0.02%   0.024 s   1000x |    0.008     0.024     2.925 ms] generate_point_sort_key_by_num_overlap_tiles_c88_0_kernel_0_serial\n",
            "[  0.01%   0.010 s   1000x |    0.004     0.010     1.131 ms] find_tile_start_and_end_c90_0_kernel_2_serial\n",
            "[  0.01%   0.010 s   1000x |    0.003     0.010     0.158 ms] find_tile_start_and_end_c90_0_kernel_0_serial\n",
            "[  0.00%   0.005 s   1000x |    0.004     0.005     0.048 ms] gaussian_point_rasterisation_backward_c96_0_kernel_0_serial\n",
            "[  0.00%   0.000 s     20x |    0.009     0.016     0.053 ms] sample_from_point_c100_0_kernel_0_serial\n",
            "[  0.00%   0.000 s     20x |    0.006     0.013     0.020 ms] sample_from_point_c100_0_kernel_1_range_for\n",
            "-------------------------------------------------------------------------\n",
            "[100.00%] Total execution time: 125.363 s   number of results: 19\n",
            "=========================================================================\n",
            "=========================================================================\n",
            "Kernel Profiler(count, default) @ CUDA on Tesla T4\n",
            "=========================================================================\n",
            "[      %     total   count |      min       avg       max   ] Kernel name\n",
            "-------------------------------------------------------------------------\n",
            "-------------------------------------------------------------------------\n",
            "[100.00%] Total execution time:   0.000 s   number of results: 0\n",
            "=========================================================================\n",
            "\n",
            "  0% 0/22 [00:00<?, ?it/s]\u001b[A\n",
            "  5% 1/22 [00:06<02:16,  6.52s/it]\u001b[A\n",
            "  9% 2/22 [00:13<02:14,  6.73s/it]\u001b[A\n",
            " 14% 3/22 [00:20<02:07,  6.69s/it]\u001b[A\n",
            " 18% 4/22 [00:25<01:49,  6.11s/it]\u001b[A\n",
            " 23% 5/22 [00:30<01:36,  5.66s/it]\u001b[A\n",
            " 27% 6/22 [00:37<01:39,  6.19s/it]\u001b[A\n",
            " 32% 7/22 [00:44<01:38,  6.57s/it]\u001b[A\n",
            " 36% 8/22 [00:48<01:21,  5.79s/it]\u001b[A\n",
            " 41% 9/22 [00:52<01:05,  5.03s/it]\u001b[A\n",
            " 45% 10/22 [00:56<00:59,  4.94s/it]\u001b[A\n",
            " 50% 11/22 [01:02<00:57,  5.25s/it]\u001b[A\n",
            " 55% 12/22 [01:09<00:55,  5.55s/it]\u001b[A\n",
            " 59% 13/22 [01:13<00:46,  5.21s/it]\u001b[A\n",
            " 64% 14/22 [01:18<00:41,  5.24s/it]\u001b[A\n",
            " 68% 15/22 [01:24<00:37,  5.31s/it]\u001b[A\n",
            " 73% 16/22 [01:29<00:31,  5.17s/it]\u001b[A\n",
            " 77% 17/22 [01:35<00:27,  5.56s/it]\u001b[A\n",
            " 82% 18/22 [01:39<00:20,  5.10s/it]\u001b[A\n",
            " 86% 19/22 [01:44<00:15,  5.01s/it]\u001b[A\n",
            " 91% 20/22 [01:50<00:10,  5.30s/it]\u001b[A\n",
            " 95% 21/22 [01:56<00:05,  5.53s/it]\u001b[A\n",
            "100% 22/22 [02:01<00:00,  5.53s/it]\n",
            "=========================================================================\n",
            "Kernel Profiler(count, default) @ CUDA on Tesla T4\n",
            "=========================================================================\n",
            "[      %     total   count |      min       avg       max   ] Kernel name\n",
            "-------------------------------------------------------------------------\n",
            "[ 41.35%   0.410 s     22x |    5.041    18.614    45.210 ms] generate_point_sort_key_by_num_overlap_tiles_c88_0_kernel_1_range_for\n",
            "[ 39.36%   0.390 s     22x |    4.539    17.718    43.414 ms] generate_num_overlap_tiles_c86_0_kernel_1_range_for\n",
            "[ 17.75%   0.176 s     22x |    7.311     7.993     9.054 ms] gaussian_point_rasterisation_c94_0_kernel_1_range_for\n",
            "[  0.64%   0.006 s     22x |    0.008     0.289     6.152 ms] find_tile_start_and_end_c90_0_kernel_2_serial\n",
            "[  0.38%   0.004 s     22x |    0.011     0.169     3.423 ms] generate_num_overlap_tiles_c86_0_kernel_0_serial\n",
            "[  0.20%   0.002 s     22x |    0.077     0.091     0.102 ms] generate_point_attributes_in_camera_plane_c92_0_kernel_1_range_for\n",
            "[  0.09%   0.001 s     22x |    0.035     0.039     0.061 ms] filter_point_in_camera_c82_0_kernel_1_range_for\n",
            "[  0.07%   0.001 s     22x |    0.025     0.030     0.040 ms] find_tile_start_and_end_c90_0_kernel_1_range_for\n",
            "[  0.04%   0.000 s     22x |    0.016     0.019     0.035 ms] filter_point_in_camera_c82_0_kernel_0_serial\n",
            "[  0.04%   0.000 s     22x |    0.014     0.018     0.043 ms] generate_point_attributes_in_camera_plane_c92_0_kernel_0_serial\n",
            "[  0.04%   0.000 s     22x |    0.012     0.017     0.033 ms] generate_point_sort_key_by_num_overlap_tiles_c88_0_kernel_0_serial\n",
            "[  0.03%   0.000 s     22x |    0.012     0.014     0.027 ms] gaussian_point_rasterisation_c94_0_kernel_0_serial\n",
            "[  0.02%   0.000 s     22x |    0.006     0.009     0.024 ms] find_tile_start_and_end_c90_0_kernel_0_serial\n",
            "-------------------------------------------------------------------------\n",
            "[100.00%] Total execution time:   0.990 s   number of results: 13\n",
            "=========================================================================\n",
            " 27% 8022/30001 [51:22<1:30:04,  4.07it/s]/usr/local/lib/python3.10/site-packages/torch/utils/data/dataloader.py:560: UserWarning: This DataLoader will create 4 worker processes in total. Our suggested max number of worker in current system is 2, which is smaller than what this DataLoader is going to create. Please be aware that excessive worker creation might get DataLoader running slow or even freeze, lower the worker number to avoid potential slowness/freeze if necessary.\n",
            "  warnings.warn(_create_warning_msg(\n",
            " 27% 8100/30001 [51:44<1:22:21,  4.43it/s]num_valid_points=27170;\n",
            "num_over_reconstructed: 12, num_under_reconstructed: 9\n",
            "total valid points: 27170 -> 26911, num_densify_points: 21, num_fillable_densify_points: 21\n",
            "num_transparent_points: 273, num_floaters_points: 7\n",
            " 27% 8200/30001 [52:13<1:40:44,  3.61it/s]1072 1920\n",
            "num_valid_points=26911;\n",
            "num_over_reconstructed: 30, num_under_reconstructed: 2\n",
            "total valid points: 26911 -> 26826, num_densify_points: 32, num_fillable_densify_points: 32\n",
            "num_transparent_points: 109, num_floaters_points: 8\n",
            " 28% 8300/30001 [52:46<1:24:41,  4.27it/s]num_valid_points=26826;\n",
            "num_over_reconstructed: 46, num_under_reconstructed: 2\n",
            "total valid points: 26826 -> 26778, num_densify_points: 48, num_fillable_densify_points: 48\n",
            "num_transparent_points: 94, num_floaters_points: 2\n",
            " 28% 8400/30001 [53:13<1:19:00,  4.56it/s]1072 1920\n",
            "num_valid_points=26778;\n",
            "num_over_reconstructed: 53, num_under_reconstructed: 2\n",
            "total valid points: 26778 -> 26723, num_densify_points: 55, num_fillable_densify_points: 55\n",
            "num_transparent_points: 104, num_floaters_points: 6\n",
            " 28% 8500/30001 [53:46<1:25:33,  4.19it/s]num_valid_points=26723;\n",
            "num_over_reconstructed: 95, num_under_reconstructed: 3\n",
            "total valid points: 26723 -> 26726, num_densify_points: 98, num_fillable_densify_points: 98\n",
            "num_transparent_points: 92, num_floaters_points: 3\n",
            " 29% 8600/30001 [54:13<1:35:28,  3.74it/s]1072 1920\n",
            "num_valid_points=26726;\n",
            "num_over_reconstructed: 63, num_under_reconstructed: 14\n",
            "total valid points: 26726 -> 26698, num_densify_points: 77, num_fillable_densify_points: 77\n",
            "num_transparent_points: 102, num_floaters_points: 3\n",
            " 29% 8700/30001 [54:49<1:59:15,  2.98it/s]num_valid_points=26698;\n",
            "num_over_reconstructed: 21, num_under_reconstructed: 23\n",
            "total valid points: 26698 -> 26586, num_densify_points: 44, num_fillable_densify_points: 44\n",
            "num_transparent_points: 153, num_floaters_points: 3\n",
            " 29% 8800/30001 [55:16<1:28:39,  3.99it/s]1072 1920\n",
            "num_valid_points=26586;\n",
            "num_over_reconstructed: 35, num_under_reconstructed: 23\n",
            "total valid points: 26586 -> 26516, num_densify_points: 58, num_fillable_densify_points: 58\n",
            "num_transparent_points: 121, num_floaters_points: 7\n",
            " 30% 8900/30001 [55:47<1:14:09,  4.74it/s]num_valid_points=26516;\n",
            "num_over_reconstructed: 79, num_under_reconstructed: 17\n",
            "total valid points: 26516 -> 26461, num_densify_points: 96, num_fillable_densify_points: 96\n",
            "num_transparent_points: 148, num_floaters_points: 3\n",
            " 30% 9000/30001 [56:15<1:31:05,  3.84it/s]1072 1920\n",
            "num_valid_points=26461;\n",
            "num_over_reconstructed: 73, num_under_reconstructed: 14\n",
            "total valid points: 26461 -> 26404, num_densify_points: 87, num_fillable_densify_points: 87\n",
            "num_transparent_points: 138, num_floaters_points: 6\n",
            "=========================================================================\n",
            "Kernel Profiler(count, default) @ CUDA on Tesla T4\n",
            "=========================================================================\n",
            "[      %     total   count |      min       avg       max   ] Kernel name\n",
            "-------------------------------------------------------------------------\n",
            "[ 85.34% 124.292 s   1000x |   65.629   124.292   208.531 ms] gaussian_point_rasterisation_backward_c96_0_kernel_1_range_for\n",
            "[  5.43%   7.902 s   1000x |    1.859     7.902    43.190 ms] generate_point_sort_key_by_num_overlap_tiles_c88_0_kernel_1_range_for\n",
            "[  5.22%   7.597 s   1000x |    1.628     7.597    41.357 ms] generate_num_overlap_tiles_c86_0_kernel_1_range_for\n",
            "[  2.59%   3.772 s   1000x |    2.920     3.772    12.759 ms] gaussian_point_rasterisation_c94_0_kernel_1_range_for\n",
            "[  1.18%   1.712 s   1000x |    1.688     1.712     2.515 ms] gaussian_point_rasterisation_backward_c96_0_kernel_3_range_for\n",
            "[  0.04%   0.051 s   1000x |    0.043     0.051     1.501 ms] generate_point_attributes_in_camera_plane_c92_0_kernel_1_range_for\n",
            "[  0.03%   0.050 s   1000x |    0.021     0.050    10.264 ms] filter_point_in_camera_c82_0_kernel_1_range_for\n",
            "[  0.03%   0.046 s   1000x |    0.013     0.046     7.096 ms] gaussian_point_rasterisation_backward_c96_0_kernel_2_serial\n",
            "[  0.03%   0.042 s   1000x |    0.007     0.042     9.031 ms] generate_num_overlap_tiles_c86_0_kernel_0_serial\n",
            "[  0.02%   0.035 s   1000x |    0.008     0.035     9.321 ms] generate_point_sort_key_by_num_overlap_tiles_c88_0_kernel_0_serial\n",
            "[  0.02%   0.032 s   1000x |    0.010     0.032     4.055 ms] filter_point_in_camera_c82_0_kernel_0_serial\n",
            "[  0.02%   0.032 s   1000x |    0.020     0.032     1.143 ms] find_tile_start_and_end_c90_0_kernel_1_range_for\n",
            "[  0.02%   0.030 s   1000x |    0.008     0.030     6.336 ms] generate_point_attributes_in_camera_plane_c92_0_kernel_0_serial\n",
            "[  0.02%   0.025 s   1000x |    0.008     0.025     3.103 ms] gaussian_point_rasterisation_c94_0_kernel_0_serial\n",
            "[  0.01%   0.013 s   1000x |    0.004     0.013     4.121 ms] find_tile_start_and_end_c90_0_kernel_2_serial\n",
            "[  0.01%   0.011 s   1000x |    0.003     0.011     1.942 ms] find_tile_start_and_end_c90_0_kernel_0_serial\n",
            "[  0.00%   0.005 s   1000x |    0.004     0.005     0.027 ms] gaussian_point_rasterisation_backward_c96_0_kernel_0_serial\n",
            "[  0.00%   0.000 s     20x |    0.009     0.016     0.027 ms] sample_from_point_c100_0_kernel_0_serial\n",
            "[  0.00%   0.000 s     20x |    0.008     0.015     0.037 ms] sample_from_point_c100_0_kernel_1_range_for\n",
            "-------------------------------------------------------------------------\n",
            "[100.00%] Total execution time: 145.648 s   number of results: 19\n",
            "=========================================================================\n",
            "=========================================================================\n",
            "Kernel Profiler(count, default) @ CUDA on Tesla T4\n",
            "=========================================================================\n",
            "[      %     total   count |      min       avg       max   ] Kernel name\n",
            "-------------------------------------------------------------------------\n",
            "-------------------------------------------------------------------------\n",
            "[100.00%] Total execution time:   0.000 s   number of results: 0\n",
            "=========================================================================\n",
            "\n",
            "  0% 0/22 [00:00<?, ?it/s]\u001b[A\n",
            "  5% 1/22 [00:12<04:24, 12.58s/it]\u001b[A\n",
            "  9% 2/22 [00:26<04:32, 13.61s/it]\u001b[A\n",
            " 14% 3/22 [00:41<04:28, 14.14s/it]\u001b[A\n",
            " 18% 4/22 [00:56<04:22, 14.58s/it]\u001b[A\n",
            " 23% 5/22 [01:11<04:06, 14.52s/it]\u001b[A\n",
            " 27% 6/22 [01:23<03:40, 13.78s/it]\u001b[A\n",
            " 32% 7/22 [01:34<03:13, 12.91s/it]\u001b[A\n",
            " 36% 8/22 [01:46<02:57, 12.65s/it]\u001b[A\n",
            " 41% 9/22 [01:54<02:25, 11.19s/it]\u001b[A\n",
            " 45% 10/22 [02:08<02:22, 11.85s/it]\u001b[A\n",
            " 50% 11/22 [02:19<02:08, 11.68s/it]\u001b[A\n",
            " 55% 12/22 [02:34<02:06, 12.62s/it]\u001b[A\n",
            " 59% 13/22 [02:42<01:40, 11.15s/it]\u001b[A\n",
            " 64% 14/22 [03:00<01:46, 13.28s/it]\u001b[A\n",
            " 68% 15/22 [03:10<01:27, 12.47s/it]\u001b[A\n",
            " 73% 16/22 [03:29<01:25, 14.24s/it]\u001b[A\n",
            " 77% 17/22 [03:34<00:57, 11.54s/it]\u001b[A\n",
            " 82% 18/22 [03:52<00:54, 13.50s/it]\u001b[A\n",
            " 86% 19/22 [04:01<00:36, 12.01s/it]\u001b[A\n",
            " 91% 20/22 [04:14<00:25, 12.51s/it]\u001b[A\n",
            " 95% 21/22 [04:29<00:13, 13.21s/it]\u001b[A\n",
            "100% 22/22 [04:38<00:00, 12.66s/it]\n",
            "=========================================================================\n",
            "Kernel Profiler(count, default) @ CUDA on Tesla T4\n",
            "=========================================================================\n",
            "[      %     total   count |      min       avg       max   ] Kernel name\n",
            "-------------------------------------------------------------------------\n",
            "[ 37.75%   0.305 s     22x |    6.592    13.863    57.194 ms] generate_point_sort_key_by_num_overlap_tiles_c88_0_kernel_1_range_for\n",
            "[ 35.29%   0.285 s     22x |    5.884    12.959    55.136 ms] generate_num_overlap_tiles_c86_0_kernel_1_range_for\n",
            "[ 26.18%   0.211 s     22x |    8.544     9.613    10.653 ms] gaussian_point_rasterisation_c94_0_kernel_1_range_for\n",
            "[  0.24%   0.002 s     22x |    0.077     0.089     0.104 ms] generate_point_attributes_in_camera_plane_c92_0_kernel_1_range_for\n",
            "[  0.10%   0.001 s     22x |    0.036     0.038     0.048 ms] filter_point_in_camera_c82_0_kernel_1_range_for\n",
            "[  0.09%   0.001 s     22x |    0.029     0.035     0.044 ms] find_tile_start_and_end_c90_0_kernel_1_range_for\n",
            "[  0.07%   0.001 s     22x |    0.006     0.026     0.381 ms] find_tile_start_and_end_c90_0_kernel_0_serial\n",
            "[  0.06%   0.000 s     22x |    0.014     0.020     0.043 ms] filter_point_in_camera_c82_0_kernel_0_serial\n",
            "[  0.05%   0.000 s     22x |    0.014     0.019     0.045 ms] generate_point_attributes_in_camera_plane_c92_0_kernel_0_serial\n",
            "[  0.05%   0.000 s     22x |    0.011     0.017     0.046 ms] generate_num_overlap_tiles_c86_0_kernel_0_serial\n",
            "[  0.04%   0.000 s     22x |    0.012     0.015     0.040 ms] generate_point_sort_key_by_num_overlap_tiles_c88_0_kernel_0_serial\n",
            "[  0.04%   0.000 s     22x |    0.010     0.015     0.027 ms] gaussian_point_rasterisation_c94_0_kernel_0_serial\n",
            "[  0.03%   0.000 s     22x |    0.007     0.012     0.027 ms] find_tile_start_and_end_c90_0_kernel_2_serial\n",
            "-------------------------------------------------------------------------\n",
            "[100.00%] Total execution time:   0.808 s   number of results: 13\n",
            "=========================================================================\n",
            " 30% 9030/30001 [1:01:08<1:13:08,  4.78it/s]/usr/local/lib/python3.10/site-packages/torch/utils/data/dataloader.py:560: UserWarning: This DataLoader will create 4 worker processes in total. Our suggested max number of worker in current system is 2, which is smaller than what this DataLoader is going to create. Please be aware that excessive worker creation might get DataLoader running slow or even freeze, lower the worker number to avoid potential slowness/freeze if necessary.\n",
            "  warnings.warn(_create_warning_msg(\n",
            " 30% 9100/30001 [1:01:27<1:28:52,  3.92it/s]num_valid_points=26404;\n",
            "num_over_reconstructed: 29, num_under_reconstructed: 29\n",
            "total valid points: 26404 -> 26323, num_densify_points: 58, num_fillable_densify_points: 58\n",
            "num_transparent_points: 135, num_floaters_points: 4\n",
            " 31% 9200/30001 [1:01:54<2:28:47,  2.33it/s]1072 1920\n",
            "num_valid_points=26323;\n",
            "num_over_reconstructed: 31, num_under_reconstructed: 22\n",
            "total valid points: 26323 -> 26247, num_densify_points: 53, num_fillable_densify_points: 53\n",
            "num_transparent_points: 127, num_floaters_points: 2\n",
            " 31% 9300/30001 [1:02:28<1:15:26,  4.57it/s]num_valid_points=26247;\n",
            "num_over_reconstructed: 37, num_under_reconstructed: 18\n",
            "total valid points: 26247 -> 26176, num_densify_points: 55, num_fillable_densify_points: 55\n",
            "num_transparent_points: 125, num_floaters_points: 1\n",
            " 31% 9400/30001 [1:02:54<1:25:13,  4.03it/s]1072 1920\n",
            "num_valid_points=26176;\n",
            "num_over_reconstructed: 47, num_under_reconstructed: 20\n",
            "total valid points: 26176 -> 26112, num_densify_points: 67, num_fillable_densify_points: 67\n",
            "num_transparent_points: 129, num_floaters_points: 2\n",
            " 32% 9500/30001 [1:03:27<1:38:45,  3.46it/s]num_valid_points=26112;\n",
            "num_over_reconstructed: 122, num_under_reconstructed: 12\n",
            "total valid points: 26112 -> 26133, num_densify_points: 134, num_fillable_densify_points: 134\n",
            "num_transparent_points: 109, num_floaters_points: 4\n",
            " 32% 9600/30001 [1:03:53<1:21:52,  4.15it/s]1072 1920\n",
            "num_valid_points=26133;\n",
            "num_over_reconstructed: 63, num_under_reconstructed: 22\n",
            "total valid points: 26133 -> 26137, num_densify_points: 85, num_fillable_densify_points: 85\n",
            "num_transparent_points: 78, num_floaters_points: 3\n",
            " 32% 9700/30001 [1:04:24<1:13:28,  4.60it/s]num_valid_points=26137;\n",
            "num_over_reconstructed: 58, num_under_reconstructed: 20\n",
            "total valid points: 26137 -> 26122, num_densify_points: 78, num_fillable_densify_points: 78\n",
            "num_transparent_points: 92, num_floaters_points: 1\n",
            " 33% 9800/30001 [1:04:52<1:15:39,  4.45it/s]1072 1920\n",
            "num_valid_points=26122;\n",
            "num_over_reconstructed: 17, num_under_reconstructed: 42\n",
            "total valid points: 26122 -> 26095, num_densify_points: 59, num_fillable_densify_points: 59\n",
            "num_transparent_points: 83, num_floaters_points: 3\n",
            " 33% 9900/30001 [1:05:23<1:27:15,  3.84it/s]num_valid_points=26095;\n",
            "num_over_reconstructed: 68, num_under_reconstructed: 37\n",
            "total valid points: 26095 -> 26154, num_densify_points: 105, num_fillable_densify_points: 105\n",
            "num_transparent_points: 43, num_floaters_points: 3\n",
            " 33% 10000/30001 [1:05:50<2:15:18,  2.46it/s]1072 1920\n",
            "num_valid_points=26154;\n",
            "num_over_reconstructed: 28, num_under_reconstructed: 50\n",
            "total valid points: 26154 -> 26152, num_densify_points: 78, num_fillable_densify_points: 78\n",
            "num_transparent_points: 76, num_floaters_points: 4\n",
            "=========================================================================\n",
            "Kernel Profiler(count, default) @ CUDA on Tesla T4\n",
            "=========================================================================\n",
            "[      %     total   count |      min       avg       max   ] Kernel name\n",
            "-------------------------------------------------------------------------\n",
            "[ 88.08% 122.216 s   1000x |   79.013   122.216   230.590 ms] gaussian_point_rasterisation_backward_c96_0_kernel_1_range_for\n",
            "[  3.93%   5.460 s   1000x |    2.028     5.460    39.447 ms] generate_point_sort_key_by_num_overlap_tiles_c88_0_kernel_1_range_for\n",
            "[  3.74%   5.184 s   1000x |    1.835     5.184    38.755 ms] generate_num_overlap_tiles_c86_0_kernel_1_range_for\n",
            "[  2.69%   3.735 s   1000x |    3.222     3.735    13.427 ms] gaussian_point_rasterisation_c94_0_kernel_1_range_for\n",
            "[  1.24%   1.720 s   1000x |    1.685     1.720     3.375 ms] gaussian_point_rasterisation_backward_c96_0_kernel_3_range_for\n",
            "[  0.05%   0.076 s   1000x |    0.044     0.076    13.206 ms] generate_point_attributes_in_camera_plane_c92_0_kernel_1_range_for\n",
            "[  0.05%   0.064 s   1000x |    0.007     0.064    24.545 ms] generate_num_overlap_tiles_c86_0_kernel_0_serial\n",
            "[  0.03%   0.041 s   1000x |    0.008     0.041     9.030 ms] gaussian_point_rasterisation_c94_0_kernel_0_serial\n",
            "[  0.03%   0.036 s   1000x |    0.021     0.036     3.094 ms] find_tile_start_and_end_c90_0_kernel_1_range_for\n",
            "[  0.03%   0.036 s   1000x |    0.011     0.036     1.219 ms] gaussian_point_rasterisation_backward_c96_0_kernel_2_serial\n",
            "[  0.03%   0.035 s   1000x |    0.020     0.035     6.899 ms] filter_point_in_camera_c82_0_kernel_1_range_for\n",
            "[  0.02%   0.034 s   1000x |    0.010     0.034     4.818 ms] filter_point_in_camera_c82_0_kernel_0_serial\n",
            "[  0.02%   0.030 s   1000x |    0.008     0.030    10.012 ms] generate_point_attributes_in_camera_plane_c92_0_kernel_0_serial\n",
            "[  0.02%   0.030 s   1000x |    0.004     0.030     9.136 ms] find_tile_start_and_end_c90_0_kernel_2_serial\n",
            "[  0.02%   0.026 s   1000x |    0.003     0.026    15.282 ms] find_tile_start_and_end_c90_0_kernel_0_serial\n",
            "[  0.02%   0.023 s   1000x |    0.008     0.023     6.016 ms] generate_point_sort_key_by_num_overlap_tiles_c88_0_kernel_0_serial\n",
            "[  0.00%   0.005 s   1000x |    0.004     0.005     0.066 ms] gaussian_point_rasterisation_backward_c96_0_kernel_0_serial\n",
            "[  0.00%   0.000 s     20x |    0.009     0.017     0.035 ms] sample_from_point_c100_0_kernel_0_serial\n",
            "[  0.00%   0.000 s     20x |    0.008     0.014     0.032 ms] sample_from_point_c100_0_kernel_1_range_for\n",
            "-------------------------------------------------------------------------\n",
            "[100.00%] Total execution time: 138.752 s   number of results: 19\n",
            "=========================================================================\n",
            "=========================================================================\n",
            "Kernel Profiler(count, default) @ CUDA on Tesla T4\n",
            "=========================================================================\n",
            "[      %     total   count |      min       avg       max   ] Kernel name\n",
            "-------------------------------------------------------------------------\n",
            "-------------------------------------------------------------------------\n",
            "[100.00%] Total execution time:   0.000 s   number of results: 0\n",
            "=========================================================================\n",
            "\n",
            "  0% 0/22 [00:00<?, ?it/s]\u001b[A\n",
            "  5% 1/22 [00:06<02:05,  6.00s/it]\u001b[A\n",
            "  9% 2/22 [00:09<01:30,  4.55s/it]\u001b[A\n",
            " 14% 3/22 [00:13<01:18,  4.13s/it]\u001b[A\n",
            " 18% 4/22 [00:18<01:24,  4.67s/it]\u001b[A\n",
            " 23% 5/22 [00:23<01:22,  4.84s/it]\u001b[A\n",
            " 27% 6/22 [00:29<01:19,  4.98s/it]\u001b[A\n",
            " 32% 7/22 [00:33<01:11,  4.79s/it]\u001b[A\n",
            " 36% 8/22 [00:38<01:08,  4.89s/it]\u001b[A\n",
            " 41% 9/22 [00:43<01:05,  5.00s/it]\u001b[A\n",
            " 45% 10/22 [00:49<01:03,  5.29s/it]\u001b[A\n",
            " 50% 11/22 [00:54<00:57,  5.21s/it]\u001b[A\n",
            " 55% 12/22 [00:58<00:47,  4.74s/it]\u001b[A\n",
            " 59% 13/22 [01:02<00:40,  4.52s/it]\u001b[A\n",
            " 64% 14/22 [01:08<00:39,  4.96s/it]\u001b[A\n",
            " 68% 15/22 [01:13<00:35,  5.05s/it]\u001b[A\n",
            " 73% 16/22 [01:18<00:29,  4.92s/it]\u001b[A\n",
            " 77% 17/22 [01:23<00:24,  4.94s/it]\u001b[A\n",
            " 82% 18/22 [01:28<00:20,  5.12s/it]\u001b[A\n",
            " 86% 19/22 [01:34<00:16,  5.41s/it]\u001b[A\n",
            " 91% 20/22 [01:40<00:10,  5.47s/it]\u001b[A\n",
            " 95% 21/22 [01:45<00:05,  5.30s/it]\u001b[A\n",
            "100% 22/22 [01:49<00:00,  4.97s/it]\n",
            "=========================================================================\n",
            "Kernel Profiler(count, default) @ CUDA on Tesla T4\n",
            "=========================================================================\n",
            "[      %     total   count |      min       avg       max   ] Kernel name\n",
            "-------------------------------------------------------------------------\n",
            "[ 33.56%   0.211 s     22x |    4.952     9.570    17.638 ms] generate_point_sort_key_by_num_overlap_tiles_c88_0_kernel_1_range_for\n",
            "[ 33.54%   0.210 s     22x |    8.629     9.562    10.684 ms] gaussian_point_rasterisation_c94_0_kernel_1_range_for\n",
            "[ 31.01%   0.195 s     22x |    4.333     8.843    16.675 ms] generate_num_overlap_tiles_c86_0_kernel_1_range_for\n",
            "[  1.02%   0.006 s     22x |    0.012     0.291     6.072 ms] generate_num_overlap_tiles_c86_0_kernel_0_serial\n",
            "[  0.32%   0.002 s     22x |    0.081     0.090     0.104 ms] generate_point_attributes_in_camera_plane_c92_0_kernel_1_range_for\n",
            "[  0.13%   0.001 s     22x |    0.035     0.038     0.049 ms] filter_point_in_camera_c82_0_kernel_1_range_for\n",
            "[  0.13%   0.001 s     22x |    0.029     0.036     0.068 ms] find_tile_start_and_end_c90_0_kernel_1_range_for\n",
            "[  0.07%   0.000 s     22x |    0.016     0.020     0.045 ms] filter_point_in_camera_c82_0_kernel_0_serial\n",
            "[  0.06%   0.000 s     22x |    0.014     0.016     0.038 ms] generate_point_attributes_in_camera_plane_c92_0_kernel_0_serial\n",
            "[  0.05%   0.000 s     22x |    0.012     0.015     0.025 ms] gaussian_point_rasterisation_c94_0_kernel_0_serial\n",
            "[  0.05%   0.000 s     22x |    0.012     0.014     0.029 ms] generate_point_sort_key_by_num_overlap_tiles_c88_0_kernel_0_serial\n",
            "[  0.04%   0.000 s     22x |    0.008     0.011     0.028 ms] find_tile_start_and_end_c90_0_kernel_2_serial\n",
            "[  0.03%   0.000 s     22x |    0.006     0.007     0.015 ms] find_tile_start_and_end_c90_0_kernel_0_serial\n",
            "-------------------------------------------------------------------------\n",
            "[100.00%] Total execution time:   0.627 s   number of results: 13\n",
            "=========================================================================\n",
            " 33% 10038/30001 [1:07:55<1:11:34,  4.65it/s]/usr/local/lib/python3.10/site-packages/torch/utils/data/dataloader.py:560: UserWarning: This DataLoader will create 4 worker processes in total. Our suggested max number of worker in current system is 2, which is smaller than what this DataLoader is going to create. Please be aware that excessive worker creation might get DataLoader running slow or even freeze, lower the worker number to avoid potential slowness/freeze if necessary.\n",
            "  warnings.warn(_create_warning_msg(\n",
            " 34% 10100/30001 [1:08:11<1:13:07,  4.54it/s]num_valid_points=26152;\n",
            "num_over_reconstructed: 57, num_under_reconstructed: 65\n",
            "total valid points: 26152 -> 26198, num_densify_points: 122, num_fillable_densify_points: 122\n",
            "num_transparent_points: 67, num_floaters_points: 9\n",
            " 34% 10200/30001 [1:08:37<1:10:25,  4.69it/s]1072 1920\n",
            "num_valid_points=26198;\n",
            "num_over_reconstructed: 33, num_under_reconstructed: 77\n",
            "total valid points: 26198 -> 26246, num_densify_points: 110, num_fillable_densify_points: 110\n",
            "num_transparent_points: 60, num_floaters_points: 2\n",
            " 34% 10300/30001 [1:09:11<1:27:47,  3.74it/s]num_valid_points=26246;\n",
            "num_over_reconstructed: 26, num_under_reconstructed: 79\n",
            "total valid points: 26246 -> 26299, num_densify_points: 105, num_fillable_densify_points: 105\n",
            "num_transparent_points: 47, num_floaters_points: 5\n",
            " 35% 10400/30001 [1:09:36<1:10:49,  4.61it/s]1072 1920\n",
            "num_valid_points=26299;\n",
            "num_over_reconstructed: 62, num_under_reconstructed: 30\n",
            "total valid points: 26299 -> 26342, num_densify_points: 92, num_fillable_densify_points: 92\n",
            "num_transparent_points: 46, num_floaters_points: 3\n",
            " 35% 10500/30001 [1:10:07<1:09:41,  4.66it/s]num_valid_points=26342;\n",
            "num_over_reconstructed: 62, num_under_reconstructed: 51\n",
            "total valid points: 26342 -> 26388, num_densify_points: 113, num_fillable_densify_points: 113\n",
            "num_transparent_points: 63, num_floaters_points: 4\n",
            " 35% 10600/30001 [1:10:34<1:07:43,  4.77it/s]1072 1920\n",
            "num_valid_points=26388;\n",
            "num_over_reconstructed: 31, num_under_reconstructed: 76\n",
            "total valid points: 26388 -> 26420, num_densify_points: 107, num_fillable_densify_points: 107\n",
            "num_transparent_points: 68, num_floaters_points: 7\n",
            " 36% 10700/30001 [1:11:04<1:08:48,  4.68it/s]num_valid_points=26420;\n",
            "num_over_reconstructed: 22, num_under_reconstructed: 67\n",
            "total valid points: 26420 -> 26449, num_densify_points: 89, num_fillable_densify_points: 89\n",
            "num_transparent_points: 54, num_floaters_points: 6\n",
            " 36% 10800/30001 [1:11:31<1:54:40,  2.79it/s]1072 1920\n",
            "num_valid_points=26449;\n",
            "num_over_reconstructed: 36, num_under_reconstructed: 40\n",
            "total valid points: 26449 -> 26466, num_densify_points: 76, num_fillable_densify_points: 76\n",
            "num_transparent_points: 55, num_floaters_points: 4\n",
            " 36% 10900/30001 [1:12:03<1:14:47,  4.26it/s]num_valid_points=26466;\n",
            "num_over_reconstructed: 57, num_under_reconstructed: 34\n",
            "total valid points: 26466 -> 26501, num_densify_points: 91, num_fillable_densify_points: 91\n",
            "num_transparent_points: 51, num_floaters_points: 5\n",
            " 37% 11000/30001 [1:12:29<1:07:06,  4.72it/s]1072 1920\n",
            "num_valid_points=26501;\n",
            "num_over_reconstructed: 22, num_under_reconstructed: 74\n",
            "total valid points: 26501 -> 26547, num_densify_points: 96, num_fillable_densify_points: 96\n",
            "num_transparent_points: 46, num_floaters_points: 4\n",
            "=========================================================================\n",
            "Kernel Profiler(count, default) @ CUDA on Tesla T4\n",
            "=========================================================================\n",
            "[      %     total   count |      min       avg       max   ] Kernel name\n",
            "-------------------------------------------------------------------------\n",
            "[ 89.85% 121.795 s   1000x |   79.163   121.795   223.427 ms] gaussian_point_rasterisation_backward_c96_0_kernel_1_range_for\n",
            "[  3.01%   4.087 s   1000x |    1.723     4.087    16.638 ms] generate_point_sort_key_by_num_overlap_tiles_c88_0_kernel_1_range_for\n",
            "[  2.78%   3.774 s   1000x |    1.534     3.774    15.626 ms] generate_num_overlap_tiles_c86_0_kernel_1_range_for\n",
            "[  2.73%   3.706 s   1000x |    3.213     3.706     9.976 ms] gaussian_point_rasterisation_c94_0_kernel_1_range_for\n",
            "[  1.28%   1.732 s   1000x |    1.694     1.732     4.653 ms] gaussian_point_rasterisation_backward_c96_0_kernel_3_range_for\n",
            "[  0.05%   0.071 s   1000x |    0.045     0.071     6.750 ms] generate_point_attributes_in_camera_plane_c92_0_kernel_1_range_for\n",
            "[  0.05%   0.070 s   1000x |    0.009     0.070    19.234 ms] generate_point_attributes_in_camera_plane_c92_0_kernel_0_serial\n",
            "[  0.04%   0.053 s   1000x |    0.011     0.053    11.047 ms] gaussian_point_rasterisation_backward_c96_0_kernel_2_serial\n",
            "[  0.04%   0.051 s   1000x |    0.008     0.051    15.149 ms] gaussian_point_rasterisation_c94_0_kernel_0_serial\n",
            "[  0.03%   0.043 s   1000x |    0.009     0.043    12.062 ms] filter_point_in_camera_c82_0_kernel_0_serial\n",
            "[  0.03%   0.037 s   1000x |    0.008     0.037    13.847 ms] generate_point_sort_key_by_num_overlap_tiles_c88_0_kernel_0_serial\n",
            "[  0.03%   0.035 s   1000x |    0.007     0.035     6.767 ms] generate_num_overlap_tiles_c86_0_kernel_0_serial\n",
            "[  0.02%   0.032 s   1000x |    0.021     0.032     1.425 ms] find_tile_start_and_end_c90_0_kernel_1_range_for\n",
            "[  0.02%   0.030 s   1000x |    0.021     0.030     4.924 ms] filter_point_in_camera_c82_0_kernel_1_range_for\n",
            "[  0.01%   0.019 s   1000x |    0.004     0.019     5.814 ms] find_tile_start_and_end_c90_0_kernel_2_serial\n",
            "[  0.01%   0.010 s   1000x |    0.003     0.010     3.299 ms] find_tile_start_and_end_c90_0_kernel_0_serial\n",
            "[  0.00%   0.005 s   1000x |    0.004     0.005     0.034 ms] gaussian_point_rasterisation_backward_c96_0_kernel_0_serial\n",
            "[  0.00%   0.000 s     20x |    0.010     0.018     0.041 ms] sample_from_point_c100_0_kernel_0_serial\n",
            "[  0.00%   0.000 s     20x |    0.006     0.016     0.039 ms] sample_from_point_c100_0_kernel_1_range_for\n",
            "-------------------------------------------------------------------------\n",
            "[100.00%] Total execution time: 135.549 s   number of results: 19\n",
            "=========================================================================\n",
            "=========================================================================\n",
            "Kernel Profiler(count, default) @ CUDA on Tesla T4\n",
            "=========================================================================\n",
            "[      %     total   count |      min       avg       max   ] Kernel name\n",
            "-------------------------------------------------------------------------\n",
            "-------------------------------------------------------------------------\n",
            "[100.00%] Total execution time:   0.000 s   number of results: 0\n",
            "=========================================================================\n",
            "\n",
            "  0% 0/22 [00:00<?, ?it/s]\u001b[A\n",
            "  5% 1/22 [00:07<02:42,  7.72s/it]\u001b[A\n",
            "  9% 2/22 [00:25<04:29, 13.49s/it]\u001b[A\n",
            " 14% 3/22 [00:32<03:22, 10.68s/it]\u001b[A\n",
            " 18% 4/22 [00:41<02:57,  9.87s/it]\u001b[A\n",
            " 23% 5/22 [00:49<02:37,  9.26s/it]\u001b[A\n",
            " 27% 6/22 [00:52<01:56,  7.28s/it]\u001b[A\n",
            " 32% 7/22 [01:00<01:51,  7.40s/it]\u001b[A\n",
            " 36% 8/22 [01:06<01:35,  6.81s/it]\u001b[A\n",
            " 41% 9/22 [01:11<01:24,  6.48s/it]\u001b[A\n",
            " 45% 10/22 [01:16<01:12,  6.04s/it]\u001b[A\n",
            " 50% 11/22 [01:22<01:04,  5.84s/it]\u001b[A\n",
            " 55% 12/22 [01:27<00:57,  5.79s/it]\u001b[A\n",
            " 59% 13/22 [01:33<00:52,  5.85s/it]\u001b[A\n",
            " 64% 14/22 [01:42<00:53,  6.63s/it]\u001b[A\n",
            " 68% 15/22 [01:45<00:39,  5.69s/it]\u001b[A\n",
            " 73% 16/22 [01:52<00:34,  5.83s/it]\u001b[A\n",
            " 77% 17/22 [01:57<00:28,  5.75s/it]\u001b[A\n",
            " 82% 18/22 [02:02<00:22,  5.61s/it]\u001b[A\n",
            " 86% 19/22 [02:10<00:18,  6.21s/it]\u001b[A\n",
            " 91% 20/22 [02:15<00:11,  5.76s/it]\u001b[A\n",
            " 95% 21/22 [02:24<00:06,  6.70s/it]\u001b[A\n",
            "100% 22/22 [02:28<00:00,  6.76s/it]\n",
            "=========================================================================\n",
            "Kernel Profiler(count, default) @ CUDA on Tesla T4\n",
            "=========================================================================\n",
            "[      %     total   count |      min       avg       max   ] Kernel name\n",
            "-------------------------------------------------------------------------\n",
            "[ 35.11%   0.241 s     22x |    5.011    10.955    22.356 ms] generate_point_sort_key_by_num_overlap_tiles_c88_0_kernel_1_range_for\n",
            "[ 32.46%   0.223 s     22x |    4.208    10.126    21.292 ms] generate_num_overlap_tiles_c86_0_kernel_1_range_for\n",
            "[ 30.78%   0.211 s     22x |    8.644     9.603    10.912 ms] gaussian_point_rasterisation_c94_0_kernel_1_range_for\n",
            "[  0.80%   0.005 s     22x |    0.006     0.249     5.300 ms] find_tile_start_and_end_c90_0_kernel_0_serial\n",
            "[  0.31%   0.002 s     22x |    0.081     0.096     0.112 ms] generate_point_attributes_in_camera_plane_c92_0_kernel_1_range_for\n",
            "[  0.12%   0.001 s     22x |    0.035     0.038     0.049 ms] filter_point_in_camera_c82_0_kernel_1_range_for\n",
            "[  0.12%   0.001 s     22x |    0.029     0.036     0.070 ms] find_tile_start_and_end_c90_0_kernel_1_range_for\n",
            "[  0.06%   0.000 s     22x |    0.015     0.020     0.047 ms] filter_point_in_camera_c82_0_kernel_0_serial\n",
            "[  0.05%   0.000 s     22x |    0.013     0.017     0.035 ms] generate_point_attributes_in_camera_plane_c92_0_kernel_0_serial\n",
            "[  0.05%   0.000 s     22x |    0.011     0.016     0.036 ms] generate_point_sort_key_by_num_overlap_tiles_c88_0_kernel_0_serial\n",
            "[  0.05%   0.000 s     22x |    0.012     0.015     0.038 ms] generate_num_overlap_tiles_c86_0_kernel_0_serial\n",
            "[  0.05%   0.000 s     22x |    0.012     0.015     0.031 ms] gaussian_point_rasterisation_c94_0_kernel_0_serial\n",
            "[  0.03%   0.000 s     22x |    0.008     0.011     0.025 ms] find_tile_start_and_end_c90_0_kernel_2_serial\n",
            "-------------------------------------------------------------------------\n",
            "[100.00%] Total execution time:   0.686 s   number of results: 13\n",
            "=========================================================================\n",
            " 37% 11004/30001 [1:15:03<84:33:11, 16.02s/it] /usr/local/lib/python3.10/site-packages/torch/utils/data/dataloader.py:560: UserWarning: This DataLoader will create 4 worker processes in total. Our suggested max number of worker in current system is 2, which is smaller than what this DataLoader is going to create. Please be aware that excessive worker creation might get DataLoader running slow or even freeze, lower the worker number to avoid potential slowness/freeze if necessary.\n",
            "  warnings.warn(_create_warning_msg(\n",
            " 37% 11100/30001 [1:15:29<1:10:02,  4.50it/s]num_valid_points=26547;\n",
            "num_over_reconstructed: 49, num_under_reconstructed: 93\n",
            "total valid points: 26547 -> 26643, num_densify_points: 142, num_fillable_densify_points: 142\n",
            "num_transparent_points: 45, num_floaters_points: 1\n",
            " 37% 11200/30001 [1:15:55<1:04:42,  4.84it/s]1072 1920\n",
            "num_valid_points=26643;\n",
            "num_over_reconstructed: 12, num_under_reconstructed: 111\n",
            "total valid points: 26643 -> 26719, num_densify_points: 123, num_fillable_densify_points: 123\n",
            "num_transparent_points: 45, num_floaters_points: 2\n",
            " 38% 11300/30001 [1:16:28<3:09:07,  1.65it/s]num_valid_points=26719;\n",
            "num_over_reconstructed: 85, num_under_reconstructed: 57\n",
            "total valid points: 26719 -> 26812, num_densify_points: 142, num_fillable_densify_points: 142\n",
            "num_transparent_points: 47, num_floaters_points: 2\n",
            " 38% 11400/30001 [1:16:54<1:16:42,  4.04it/s]1072 1920\n",
            "num_valid_points=26812;\n",
            "num_over_reconstructed: 45, num_under_reconstructed: 67\n",
            "total valid points: 26812 -> 26886, num_densify_points: 112, num_fillable_densify_points: 112\n",
            "num_transparent_points: 31, num_floaters_points: 7\n",
            " 38% 11500/30001 [1:17:25<1:12:47,  4.24it/s]num_valid_points=26886;\n",
            "num_over_reconstructed: 57, num_under_reconstructed: 80\n",
            "total valid points: 26886 -> 26983, num_densify_points: 137, num_fillable_densify_points: 137\n",
            "num_transparent_points: 34, num_floaters_points: 6\n",
            " 39% 11600/30001 [1:17:51<1:13:35,  4.17it/s]1072 1920\n",
            "num_valid_points=26983;\n",
            "num_over_reconstructed: 22, num_under_reconstructed: 68\n",
            "total valid points: 26983 -> 27022, num_densify_points: 90, num_fillable_densify_points: 90\n",
            "num_transparent_points: 49, num_floaters_points: 2\n",
            " 39% 11700/30001 [1:18:22<1:04:17,  4.74it/s]num_valid_points=27022;\n",
            "num_over_reconstructed: 26, num_under_reconstructed: 88\n",
            "total valid points: 27022 -> 27081, num_densify_points: 114, num_fillable_densify_points: 114\n",
            "num_transparent_points: 47, num_floaters_points: 8\n",
            " 39% 11800/30001 [1:18:47<1:02:37,  4.84it/s]1072 1920\n",
            "num_valid_points=27081;\n",
            "num_over_reconstructed: 45, num_under_reconstructed: 54\n",
            "total valid points: 27081 -> 27137, num_densify_points: 99, num_fillable_densify_points: 99\n",
            "num_transparent_points: 43, num_floaters_points: 0\n",
            " 40% 11900/30001 [1:19:21<1:17:07,  3.91it/s]num_valid_points=27137;\n",
            "num_over_reconstructed: 42, num_under_reconstructed: 56\n",
            "total valid points: 27137 -> 27193, num_densify_points: 98, num_fillable_densify_points: 98\n",
            "num_transparent_points: 41, num_floaters_points: 1\n",
            " 40% 12000/30001 [1:19:47<1:09:35,  4.31it/s]1072 1920\n",
            "num_valid_points=27193;\n",
            "num_over_reconstructed: 38, num_under_reconstructed: 28\n",
            "total valid points: 27193 -> 27214, num_densify_points: 66, num_fillable_densify_points: 66\n",
            "num_transparent_points: 43, num_floaters_points: 2\n",
            "=========================================================================\n",
            "Kernel Profiler(count, default) @ CUDA on Tesla T4\n",
            "=========================================================================\n",
            "[      %     total   count |      min       avg       max   ] Kernel name\n",
            "-------------------------------------------------------------------------\n",
            "[ 89.83% 121.649 s   1000x |   77.144   121.649   241.469 ms] gaussian_point_rasterisation_backward_c96_0_kernel_1_range_for\n",
            "[  3.03%   4.102 s   1000x |    1.783     4.102    23.390 ms] generate_point_sort_key_by_num_overlap_tiles_c88_0_kernel_1_range_for\n",
            "[  2.82%   3.826 s   1000x |    1.632     3.826    22.817 ms] generate_num_overlap_tiles_c86_0_kernel_1_range_for\n",
            "[  2.76%   3.732 s   1000x |    3.242     3.732    10.746 ms] gaussian_point_rasterisation_c94_0_kernel_1_range_for\n",
            "[  1.28%   1.739 s   1000x |    1.701     1.739    12.794 ms] gaussian_point_rasterisation_backward_c96_0_kernel_3_range_for\n",
            "[  0.04%   0.056 s   1000x |    0.046     0.056     4.120 ms] generate_point_attributes_in_camera_plane_c92_0_kernel_1_range_for\n",
            "[  0.03%   0.043 s   1000x |    0.011     0.043     3.921 ms] gaussian_point_rasterisation_backward_c96_0_kernel_2_serial\n",
            "[  0.03%   0.043 s   1000x |    0.008     0.043    10.537 ms] gaussian_point_rasterisation_c94_0_kernel_0_serial\n",
            "[  0.03%   0.042 s   1000x |    0.010     0.042    18.530 ms] filter_point_in_camera_c82_0_kernel_0_serial\n",
            "[  0.03%   0.035 s   1000x |    0.008     0.035     8.976 ms] generate_point_attributes_in_camera_plane_c92_0_kernel_0_serial\n",
            "[  0.03%   0.034 s   1000x |    0.022     0.034     2.866 ms] find_tile_start_and_end_c90_0_kernel_1_range_for\n",
            "[  0.02%   0.033 s   1000x |    0.006     0.033     7.941 ms] generate_num_overlap_tiles_c86_0_kernel_0_serial\n",
            "[  0.02%   0.032 s   1000x |    0.021     0.032     6.742 ms] filter_point_in_camera_c82_0_kernel_1_range_for\n",
            "[  0.02%   0.021 s   1000x |    0.003     0.021    12.463 ms] find_tile_start_and_end_c90_0_kernel_0_serial\n",
            "[  0.01%   0.019 s   1000x |    0.009     0.019     2.722 ms] generate_point_sort_key_by_num_overlap_tiles_c88_0_kernel_0_serial\n",
            "[  0.01%   0.011 s   1000x |    0.005     0.011     2.015 ms] find_tile_start_and_end_c90_0_kernel_2_serial\n",
            "[  0.00%   0.005 s   1000x |    0.004     0.005     0.101 ms] gaussian_point_rasterisation_backward_c96_0_kernel_0_serial\n",
            "[  0.00%   0.000 s     20x |    0.008     0.016     0.031 ms] sample_from_point_c100_0_kernel_0_serial\n",
            "[  0.00%   0.000 s     20x |    0.006     0.015     0.039 ms] sample_from_point_c100_0_kernel_1_range_for\n",
            "-------------------------------------------------------------------------\n",
            "[100.00%] Total execution time: 135.423 s   number of results: 19\n",
            "=========================================================================\n",
            "=========================================================================\n",
            "Kernel Profiler(count, default) @ CUDA on Tesla T4\n",
            "=========================================================================\n",
            "[      %     total   count |      min       avg       max   ] Kernel name\n",
            "-------------------------------------------------------------------------\n",
            "-------------------------------------------------------------------------\n",
            "[100.00%] Total execution time:   0.000 s   number of results: 0\n",
            "=========================================================================\n",
            "\n",
            "  0% 0/22 [00:00<?, ?it/s]\u001b[A\n",
            "  5% 1/22 [00:07<02:32,  7.25s/it]\u001b[A\n",
            "  9% 2/22 [00:12<02:03,  6.19s/it]\u001b[A\n",
            " 14% 3/22 [00:18<01:52,  5.94s/it]\u001b[A\n",
            " 18% 4/22 [00:23<01:40,  5.56s/it]\u001b[A\n",
            " 23% 5/22 [00:26<01:21,  4.81s/it]\u001b[A\n",
            " 27% 6/22 [00:32<01:20,  5.00s/it]\u001b[A\n",
            " 32% 7/22 [00:39<01:27,  5.84s/it]\u001b[A\n",
            " 36% 8/22 [00:46<01:26,  6.17s/it]\u001b[A\n",
            " 41% 9/22 [00:50<01:11,  5.50s/it]\u001b[A\n",
            " 45% 10/22 [00:53<00:57,  4.78s/it]\u001b[A\n",
            " 50% 11/22 [00:59<00:55,  5.06s/it]\u001b[A\n",
            " 55% 12/22 [01:06<00:55,  5.56s/it]\u001b[A\n",
            " 59% 13/22 [01:13<00:54,  6.05s/it]\u001b[A\n",
            " 64% 14/22 [01:18<00:45,  5.68s/it]\u001b[A\n",
            " 68% 15/22 [01:21<00:35,  5.03s/it]\u001b[A\n",
            " 73% 16/22 [01:25<00:27,  4.62s/it]\u001b[A\n",
            " 77% 17/22 [01:31<00:25,  5.03s/it]\u001b[A\n",
            " 82% 18/22 [01:38<00:22,  5.55s/it]\u001b[A\n",
            " 86% 19/22 [01:44<00:17,  5.74s/it]\u001b[A\n",
            " 91% 20/22 [01:48<00:10,  5.25s/it]\u001b[A\n",
            " 95% 21/22 [01:56<00:05,  5.95s/it]\u001b[A\n",
            "100% 22/22 [02:03<00:00,  5.62s/it]\n",
            "=========================================================================\n",
            "Kernel Profiler(count, default) @ CUDA on Tesla T4\n",
            "=========================================================================\n",
            "[      %     total   count |      min       avg       max   ] Kernel name\n",
            "-------------------------------------------------------------------------\n",
            "[ 36.38%   0.260 s     22x |    5.880    11.805    23.447 ms] generate_point_sort_key_by_num_overlap_tiles_c88_0_kernel_1_range_for\n",
            "[ 33.60%   0.240 s     22x |    5.138    10.904    22.380 ms] generate_num_overlap_tiles_c86_0_kernel_1_range_for\n",
            "[ 29.20%   0.208 s     22x |    8.690     9.475    10.195 ms] gaussian_point_rasterisation_c94_0_kernel_1_range_for\n",
            "[  0.29%   0.002 s     22x |    0.083     0.095     0.114 ms] generate_point_attributes_in_camera_plane_c92_0_kernel_1_range_for\n",
            "[  0.12%   0.001 s     22x |    0.035     0.037     0.047 ms] filter_point_in_camera_c82_0_kernel_1_range_for\n",
            "[  0.10%   0.001 s     22x |    0.028     0.034     0.048 ms] find_tile_start_and_end_c90_0_kernel_1_range_for\n",
            "[  0.06%   0.000 s     22x |    0.015     0.020     0.052 ms] filter_point_in_camera_c82_0_kernel_0_serial\n",
            "[  0.06%   0.000 s     22x |    0.013     0.018     0.049 ms] generate_point_attributes_in_camera_plane_c92_0_kernel_0_serial\n",
            "[  0.05%   0.000 s     22x |    0.012     0.015     0.033 ms] generate_point_sort_key_by_num_overlap_tiles_c88_0_kernel_0_serial\n",
            "[  0.05%   0.000 s     22x |    0.012     0.015     0.033 ms] generate_num_overlap_tiles_c86_0_kernel_0_serial\n",
            "[  0.04%   0.000 s     22x |    0.012     0.014     0.021 ms] gaussian_point_rasterisation_c94_0_kernel_0_serial\n",
            "[  0.03%   0.000 s     22x |    0.008     0.010     0.019 ms] find_tile_start_and_end_c90_0_kernel_2_serial\n",
            "[  0.02%   0.000 s     22x |    0.006     0.008     0.016 ms] find_tile_start_and_end_c90_0_kernel_0_serial\n",
            "-------------------------------------------------------------------------\n",
            "[100.00%] Total execution time:   0.714 s   number of results: 13\n",
            "=========================================================================\n",
            " 40% 12012/30001 [1:22:04<5:10:47,  1.04s/it]/usr/local/lib/python3.10/site-packages/torch/utils/data/dataloader.py:560: UserWarning: This DataLoader will create 4 worker processes in total. Our suggested max number of worker in current system is 2, which is smaller than what this DataLoader is going to create. Please be aware that excessive worker creation might get DataLoader running slow or even freeze, lower the worker number to avoid potential slowness/freeze if necessary.\n",
            "  warnings.warn(_create_warning_msg(\n",
            " 40% 12100/30001 [1:22:31<1:50:25,  2.70it/s]num_valid_points=27214;\n",
            "num_over_reconstructed: 37, num_under_reconstructed: 7\n",
            "total valid points: 27214 -> 27058, num_densify_points: 44, num_fillable_densify_points: 44\n",
            "num_transparent_points: 197, num_floaters_points: 3\n",
            " 41% 12200/30001 [1:22:59<1:05:06,  4.56it/s]1072 1920\n",
            "num_valid_points=27058;\n",
            "num_over_reconstructed: 18, num_under_reconstructed: 3\n",
            "total valid points: 27058 -> 26990, num_densify_points: 21, num_fillable_densify_points: 21\n",
            "num_transparent_points: 84, num_floaters_points: 5\n",
            " 41% 12300/30001 [1:23:35<1:14:20,  3.97it/s]num_valid_points=26990;\n",
            "num_over_reconstructed: 10, num_under_reconstructed: 5\n",
            "total valid points: 26990 -> 26939, num_densify_points: 15, num_fillable_densify_points: 15\n",
            "num_transparent_points: 56, num_floaters_points: 10\n",
            " 41% 12400/30001 [1:24:04<1:22:54,  3.54it/s]1072 1920\n",
            "num_valid_points=26939;\n",
            "num_over_reconstructed: 56, num_under_reconstructed: 4\n",
            "total valid points: 26939 -> 26940, num_densify_points: 60, num_fillable_densify_points: 60\n",
            "num_transparent_points: 59, num_floaters_points: 0\n",
            " 42% 12500/30001 [1:24:36<1:07:59,  4.29it/s]num_valid_points=26940;\n",
            "num_over_reconstructed: 42, num_under_reconstructed: 7\n",
            "total valid points: 26940 -> 26938, num_densify_points: 49, num_fillable_densify_points: 49\n",
            "num_transparent_points: 50, num_floaters_points: 1\n",
            " 42% 12600/30001 [1:25:04<1:03:07,  4.59it/s]1072 1920\n",
            "num_valid_points=26938;\n",
            "num_over_reconstructed: 54, num_under_reconstructed: 4\n",
            "total valid points: 26938 -> 26931, num_densify_points: 58, num_fillable_densify_points: 58\n",
            "num_transparent_points: 62, num_floaters_points: 3\n",
            " 42% 12700/30001 [1:25:39<1:13:02,  3.95it/s]num_valid_points=26931;\n",
            "num_over_reconstructed: 29, num_under_reconstructed: 10\n",
            "total valid points: 26931 -> 26891, num_densify_points: 39, num_fillable_densify_points: 39\n",
            "num_transparent_points: 79, num_floaters_points: 0\n",
            " 43% 12800/30001 [1:26:07<1:07:43,  4.23it/s]1072 1920\n",
            "num_valid_points=26891;\n",
            "num_over_reconstructed: 11, num_under_reconstructed: 15\n",
            "total valid points: 26891 -> 26849, num_densify_points: 26, num_fillable_densify_points: 26\n",
            "num_transparent_points: 67, num_floaters_points: 1\n",
            " 43% 12900/30001 [1:26:40<1:20:02,  3.56it/s]num_valid_points=26849;\n",
            "num_over_reconstructed: 31, num_under_reconstructed: 19\n",
            "total valid points: 26849 -> 26820, num_densify_points: 50, num_fillable_densify_points: 50\n",
            "num_transparent_points: 76, num_floaters_points: 3\n",
            " 43% 13000/30001 [1:27:07<1:16:40,  3.70it/s]1072 1920\n",
            "num_valid_points=26820;\n",
            "num_over_reconstructed: 28, num_under_reconstructed: 8\n",
            "total valid points: 26820 -> 26788, num_densify_points: 36, num_fillable_densify_points: 36\n",
            "num_transparent_points: 66, num_floaters_points: 2\n",
            "=========================================================================\n",
            "Kernel Profiler(count, default) @ CUDA on Tesla T4\n",
            "=========================================================================\n",
            "[      %     total   count |      min       avg       max   ] Kernel name\n",
            "-------------------------------------------------------------------------\n",
            "[ 90.75% 140.989 s   1000x |   90.647   140.989   248.778 ms] gaussian_point_rasterisation_backward_c96_0_kernel_1_range_for\n",
            "[  2.69%   4.173 s   1000x |    3.543     4.173    11.287 ms] gaussian_point_rasterisation_c94_0_kernel_1_range_for\n",
            "[  2.68%   4.169 s   1000x |    1.656     4.169    18.116 ms] generate_point_sort_key_by_num_overlap_tiles_c88_0_kernel_1_range_for\n",
            "[  2.49%   3.875 s   1000x |    1.502     3.875    16.779 ms] generate_num_overlap_tiles_c86_0_kernel_1_range_for\n",
            "[  1.11%   1.730 s   1000x |    1.703     1.730     2.878 ms] gaussian_point_rasterisation_backward_c96_0_kernel_3_range_for\n",
            "[  0.04%   0.069 s   1000x |    0.045     0.069     7.088 ms] generate_point_attributes_in_camera_plane_c92_0_kernel_1_range_for\n",
            "[  0.04%   0.056 s   1000x |    0.010     0.056    14.617 ms] filter_point_in_camera_c82_0_kernel_0_serial\n",
            "[  0.03%   0.052 s   1000x |    0.008     0.052    16.063 ms] generate_point_attributes_in_camera_plane_c92_0_kernel_0_serial\n",
            "[  0.03%   0.051 s   1000x |    0.021     0.051    20.541 ms] filter_point_in_camera_c82_0_kernel_1_range_for\n",
            "[  0.02%   0.038 s   1000x |    0.013     0.038     3.562 ms] gaussian_point_rasterisation_backward_c96_0_kernel_2_serial\n",
            "[  0.02%   0.035 s   1000x |    0.023     0.035     3.639 ms] find_tile_start_and_end_c90_0_kernel_1_range_for\n",
            "[  0.02%   0.034 s   1000x |    0.008     0.034     8.075 ms] gaussian_point_rasterisation_c94_0_kernel_0_serial\n",
            "[  0.02%   0.033 s   1000x |    0.007     0.033    13.933 ms] generate_num_overlap_tiles_c86_0_kernel_0_serial\n",
            "[  0.01%   0.019 s   1000x |    0.008     0.019     2.949 ms] generate_point_sort_key_by_num_overlap_tiles_c88_0_kernel_0_serial\n",
            "[  0.01%   0.015 s   1000x |    0.004     0.015     5.024 ms] find_tile_start_and_end_c90_0_kernel_2_serial\n",
            "[  0.01%   0.013 s   1000x |    0.003     0.013     3.374 ms] find_tile_start_and_end_c90_0_kernel_0_serial\n",
            "[  0.00%   0.005 s   1000x |    0.004     0.005     0.019 ms] gaussian_point_rasterisation_backward_c96_0_kernel_0_serial\n",
            "[  0.00%   0.000 s     20x |    0.008     0.015     0.027 ms] sample_from_point_c100_0_kernel_0_serial\n",
            "[  0.00%   0.000 s     20x |    0.006     0.014     0.027 ms] sample_from_point_c100_0_kernel_1_range_for\n",
            "-------------------------------------------------------------------------\n",
            "[100.00%] Total execution time: 155.354 s   number of results: 19\n",
            "=========================================================================\n",
            "=========================================================================\n",
            "Kernel Profiler(count, default) @ CUDA on Tesla T4\n",
            "=========================================================================\n",
            "[      %     total   count |      min       avg       max   ] Kernel name\n",
            "-------------------------------------------------------------------------\n",
            "-------------------------------------------------------------------------\n",
            "[100.00%] Total execution time:   0.000 s   number of results: 0\n",
            "=========================================================================\n",
            "\n",
            "  0% 0/22 [00:00<?, ?it/s]\u001b[A\n",
            "  5% 1/22 [00:08<02:50,  8.11s/it]\u001b[A\n",
            "  9% 2/22 [00:11<01:48,  5.41s/it]\u001b[A\n",
            " 14% 3/22 [00:15<01:26,  4.53s/it]\u001b[A\n",
            " 18% 4/22 [00:18<01:14,  4.16s/it]\u001b[A\n",
            " 23% 5/22 [00:25<01:24,  4.98s/it]\u001b[A\n",
            " 27% 6/22 [00:32<01:34,  5.93s/it]\u001b[A\n",
            " 32% 7/22 [00:37<01:21,  5.42s/it]\u001b[A\n",
            " 36% 8/22 [00:40<01:06,  4.73s/it]\u001b[A\n",
            " 41% 9/22 [00:44<00:56,  4.36s/it]\u001b[A\n",
            " 45% 10/22 [00:50<00:58,  4.89s/it]\u001b[A\n",
            " 50% 11/22 [00:56<00:58,  5.29s/it]\u001b[A\n",
            " 55% 12/22 [01:02<00:54,  5.44s/it]\u001b[A\n",
            " 59% 13/22 [01:08<00:50,  5.61s/it]\u001b[A\n",
            " 64% 14/22 [01:16<00:50,  6.30s/it]\u001b[A\n",
            " 68% 15/22 [01:22<00:44,  6.34s/it]\u001b[A\n",
            " 73% 16/22 [01:27<00:35,  5.86s/it]\u001b[A\n",
            " 77% 17/22 [01:32<00:28,  5.69s/it]\u001b[A\n",
            " 82% 18/22 [01:37<00:21,  5.40s/it]\u001b[A\n",
            " 86% 19/22 [01:44<00:18,  6.11s/it]\u001b[A\n",
            " 91% 20/22 [01:50<00:12,  6.08s/it]\u001b[A\n",
            " 95% 21/22 [01:54<00:05,  5.42s/it]\u001b[A\n",
            "100% 22/22 [01:58<00:00,  5.39s/it]\n",
            "=========================================================================\n",
            "Kernel Profiler(count, default) @ CUDA on Tesla T4\n",
            "=========================================================================\n",
            "[      %     total   count |      min       avg       max   ] Kernel name\n",
            "-------------------------------------------------------------------------\n",
            "[ 37.10%   0.234 s     22x |    9.655    10.656    11.942 ms] gaussian_point_rasterisation_c94_0_kernel_1_range_for\n",
            "[ 32.36%   0.205 s     22x |    4.829     9.296    16.271 ms] generate_point_sort_key_by_num_overlap_tiles_c88_0_kernel_1_range_for\n",
            "[ 29.59%   0.187 s     22x |    4.234     8.499    15.085 ms] generate_num_overlap_tiles_c86_0_kernel_1_range_for\n",
            "[  0.33%   0.002 s     22x |    0.082     0.095     0.131 ms] generate_point_attributes_in_camera_plane_c92_0_kernel_1_range_for\n",
            "[  0.14%   0.001 s     22x |    0.032     0.039     0.058 ms] find_tile_start_and_end_c90_0_kernel_1_range_for\n",
            "[  0.13%   0.001 s     22x |    0.035     0.038     0.054 ms] filter_point_in_camera_c82_0_kernel_1_range_for\n",
            "[  0.06%   0.000 s     22x |    0.013     0.018     0.042 ms] generate_point_attributes_in_camera_plane_c92_0_kernel_0_serial\n",
            "[  0.06%   0.000 s     22x |    0.015     0.018     0.043 ms] filter_point_in_camera_c82_0_kernel_0_serial\n",
            "[  0.05%   0.000 s     22x |    0.012     0.015     0.027 ms] generate_point_sort_key_by_num_overlap_tiles_c88_0_kernel_0_serial\n",
            "[  0.05%   0.000 s     22x |    0.010     0.015     0.033 ms] generate_num_overlap_tiles_c86_0_kernel_0_serial\n",
            "[  0.05%   0.000 s     22x |    0.012     0.014     0.023 ms] gaussian_point_rasterisation_c94_0_kernel_0_serial\n",
            "[  0.04%   0.000 s     22x |    0.008     0.011     0.021 ms] find_tile_start_and_end_c90_0_kernel_2_serial\n",
            "[  0.03%   0.000 s     22x |    0.006     0.009     0.027 ms] find_tile_start_and_end_c90_0_kernel_0_serial\n",
            "-------------------------------------------------------------------------\n",
            "[100.00%] Total execution time:   0.632 s   number of results: 13\n",
            "=========================================================================\n",
            " 43% 13020/30001 [1:29:17<1:15:32,  3.75it/s]/usr/local/lib/python3.10/site-packages/torch/utils/data/dataloader.py:560: UserWarning: This DataLoader will create 4 worker processes in total. Our suggested max number of worker in current system is 2, which is smaller than what this DataLoader is going to create. Please be aware that excessive worker creation might get DataLoader running slow or even freeze, lower the worker number to avoid potential slowness/freeze if necessary.\n",
            "  warnings.warn(_create_warning_msg(\n",
            " 44% 13100/30001 [1:29:38<1:05:53,  4.27it/s]num_valid_points=26788;\n",
            "num_over_reconstructed: 37, num_under_reconstructed: 17\n",
            "total valid points: 26788 -> 26757, num_densify_points: 54, num_fillable_densify_points: 54\n",
            "num_transparent_points: 84, num_floaters_points: 1\n",
            " 44% 13200/30001 [1:30:08<1:17:28,  3.61it/s]1072 1920\n",
            "num_valid_points=26757;\n",
            "num_over_reconstructed: 21, num_under_reconstructed: 27\n",
            "total valid points: 26757 -> 26716, num_densify_points: 48, num_fillable_densify_points: 48\n",
            "num_transparent_points: 86, num_floaters_points: 3\n",
            " 44% 13300/30001 [1:30:43<1:03:09,  4.41it/s]num_valid_points=26716;\n",
            "num_over_reconstructed: 15, num_under_reconstructed: 20\n",
            "total valid points: 26716 -> 26675, num_densify_points: 35, num_fillable_densify_points: 35\n",
            "num_transparent_points: 75, num_floaters_points: 1\n",
            " 45% 13400/30001 [1:31:12<2:08:33,  2.15it/s]1072 1920\n",
            "num_valid_points=26675;\n",
            "num_over_reconstructed: 30, num_under_reconstructed: 20\n",
            "total valid points: 26675 -> 26635, num_densify_points: 50, num_fillable_densify_points: 50\n",
            "num_transparent_points: 78, num_floaters_points: 12\n",
            " 45% 13500/30001 [1:31:46<1:07:17,  4.09it/s]num_valid_points=26635;\n",
            "num_over_reconstructed: 40, num_under_reconstructed: 6\n",
            "total valid points: 26635 -> 26609, num_densify_points: 46, num_fillable_densify_points: 46\n",
            "num_transparent_points: 68, num_floaters_points: 4\n",
            " 45% 13600/30001 [1:32:14<1:07:29,  4.05it/s]1072 1920\n",
            "num_valid_points=26609;\n",
            "num_over_reconstructed: 16, num_under_reconstructed: 25\n",
            "total valid points: 26609 -> 26592, num_densify_points: 41, num_fillable_densify_points: 41\n",
            "num_transparent_points: 50, num_floaters_points: 8\n",
            " 46% 13700/30001 [1:32:48<1:06:39,  4.08it/s]num_valid_points=26592;\n",
            "num_over_reconstructed: 8, num_under_reconstructed: 30\n",
            "total valid points: 26592 -> 26571, num_densify_points: 38, num_fillable_densify_points: 38\n",
            "num_transparent_points: 59, num_floaters_points: 0\n",
            " 46% 13800/30001 [1:33:15<1:02:07,  4.35it/s]1072 1920\n",
            "num_valid_points=26571;\n",
            "num_over_reconstructed: 13, num_under_reconstructed: 40\n",
            "total valid points: 26571 -> 26573, num_densify_points: 53, num_fillable_densify_points: 53\n",
            "num_transparent_points: 43, num_floaters_points: 8\n",
            " 46% 13900/30001 [1:33:48<1:02:13,  4.31it/s]num_valid_points=26573;\n",
            "num_over_reconstructed: 27, num_under_reconstructed: 39\n",
            "total valid points: 26573 -> 26581, num_densify_points: 66, num_fillable_densify_points: 66\n",
            "num_transparent_points: 53, num_floaters_points: 5\n",
            " 47% 14000/30001 [1:34:18<1:06:43,  4.00it/s]1072 1920\n",
            "num_valid_points=26581;\n",
            "num_over_reconstructed: 81, num_under_reconstructed: 22\n",
            "total valid points: 26581 -> 26621, num_densify_points: 103, num_fillable_densify_points: 103\n",
            "num_transparent_points: 58, num_floaters_points: 5\n",
            "=========================================================================\n",
            "Kernel Profiler(count, default) @ CUDA on Tesla T4\n",
            "=========================================================================\n",
            "[      %     total   count |      min       avg       max   ] Kernel name\n",
            "-------------------------------------------------------------------------\n",
            "[ 90.78% 136.747 s   1000x |   89.037   136.747   267.217 ms] gaussian_point_rasterisation_backward_c96_0_kernel_1_range_for\n",
            "[  2.70%   4.071 s   1000x |    3.545     4.071    10.517 ms] gaussian_point_rasterisation_c94_0_kernel_1_range_for\n",
            "[  2.66%   4.004 s   1000x |    1.792     4.004    16.161 ms] generate_point_sort_key_by_num_overlap_tiles_c88_0_kernel_1_range_for\n",
            "[  2.45%   3.693 s   1000x |    1.586     3.693    15.561 ms] generate_num_overlap_tiles_c86_0_kernel_1_range_for\n",
            "[  1.15%   1.731 s   1000x |    1.706     1.731     2.853 ms] gaussian_point_rasterisation_backward_c96_0_kernel_3_range_for\n",
            "[  0.06%   0.090 s   1000x |    0.046     0.090    14.416 ms] generate_point_attributes_in_camera_plane_c92_0_kernel_1_range_for\n",
            "[  0.04%   0.053 s   1000x |    0.010     0.053     8.684 ms] filter_point_in_camera_c82_0_kernel_0_serial\n",
            "[  0.03%   0.040 s   1000x |    0.008     0.040    10.007 ms] generate_point_attributes_in_camera_plane_c92_0_kernel_0_serial\n",
            "[  0.03%   0.038 s   1000x |    0.013     0.038     1.966 ms] gaussian_point_rasterisation_backward_c96_0_kernel_2_serial\n",
            "[  0.02%   0.037 s   1000x |    0.022     0.037     4.075 ms] find_tile_start_and_end_c90_0_kernel_1_range_for\n",
            "[  0.02%   0.026 s   1000x |    0.008     0.026     4.883 ms] gaussian_point_rasterisation_c94_0_kernel_0_serial\n",
            "[  0.02%   0.026 s   1000x |    0.021     0.026     0.343 ms] filter_point_in_camera_c82_0_kernel_1_range_for\n",
            "[  0.02%   0.023 s   1000x |    0.007     0.023     4.039 ms] generate_num_overlap_tiles_c86_0_kernel_0_serial\n",
            "[  0.02%   0.023 s   1000x |    0.008     0.023     3.962 ms] generate_point_sort_key_by_num_overlap_tiles_c88_0_kernel_0_serial\n",
            "[  0.01%   0.014 s   1000x |    0.003     0.014     6.126 ms] find_tile_start_and_end_c90_0_kernel_0_serial\n",
            "[  0.01%   0.009 s   1000x |    0.005     0.009     0.215 ms] find_tile_start_and_end_c90_0_kernel_2_serial\n",
            "[  0.00%   0.005 s   1000x |    0.004     0.005     0.042 ms] gaussian_point_rasterisation_backward_c96_0_kernel_0_serial\n",
            "[  0.00%   0.000 s     20x |    0.008     0.016     0.033 ms] sample_from_point_c100_0_kernel_1_range_for\n",
            "[  0.00%   0.000 s     20x |    0.009     0.015     0.026 ms] sample_from_point_c100_0_kernel_0_serial\n",
            "-------------------------------------------------------------------------\n",
            "[100.00%] Total execution time: 150.630 s   number of results: 19\n",
            "=========================================================================\n",
            "=========================================================================\n",
            "Kernel Profiler(count, default) @ CUDA on Tesla T4\n",
            "=========================================================================\n",
            "[      %     total   count |      min       avg       max   ] Kernel name\n",
            "-------------------------------------------------------------------------\n",
            "-------------------------------------------------------------------------\n",
            "[100.00%] Total execution time:   0.000 s   number of results: 0\n",
            "=========================================================================\n",
            "\n",
            "  0% 0/22 [00:00<?, ?it/s]\u001b[A\n",
            "  5% 1/22 [00:14<05:00, 14.30s/it]\u001b[A\n",
            "  9% 2/22 [00:30<05:05, 15.30s/it]\u001b[A\n",
            " 14% 3/22 [00:37<03:37, 11.47s/it]\u001b[A\n",
            " 18% 4/22 [00:47<03:17, 11.00s/it]\u001b[A\n",
            " 23% 5/22 [00:54<02:42,  9.53s/it]\u001b[A\n",
            " 27% 6/22 [01:03<02:27,  9.25s/it]\u001b[A\n",
            " 32% 7/22 [01:09<02:06,  8.46s/it]\u001b[A\n",
            " 36% 8/22 [01:15<01:46,  7.58s/it]\u001b[A\n",
            " 41% 9/22 [01:20<01:28,  6.81s/it]\u001b[A\n",
            " 45% 10/22 [01:24<01:11,  5.92s/it]\u001b[A\n",
            " 50% 11/22 [01:31<01:06,  6.07s/it]\u001b[A\n",
            " 55% 12/22 [01:38<01:03,  6.35s/it]\u001b[A\n",
            " 59% 13/22 [01:42<00:51,  5.67s/it]\u001b[A\n",
            " 64% 14/22 [01:46<00:42,  5.30s/it]\u001b[A\n",
            " 68% 15/22 [01:51<00:35,  5.03s/it]\u001b[A\n",
            " 73% 16/22 [01:56<00:31,  5.29s/it]\u001b[A\n",
            " 77% 17/22 [02:01<00:25,  5.14s/it]\u001b[A\n",
            " 82% 18/22 [02:07<00:20,  5.21s/it]\u001b[A\n",
            " 86% 19/22 [02:13<00:16,  5.45s/it]\u001b[A\n",
            " 91% 20/22 [02:18<00:11,  5.54s/it]\u001b[A\n",
            " 95% 21/22 [02:26<00:06,  6.27s/it]\u001b[A\n",
            "100% 22/22 [02:30<00:00,  6.86s/it]\n",
            "=========================================================================\n",
            "Kernel Profiler(count, default) @ CUDA on Tesla T4\n",
            "=========================================================================\n",
            "[      %     total   count |      min       avg       max   ] Kernel name\n",
            "-------------------------------------------------------------------------\n",
            "[ 39.77%   0.230 s     22x |    9.621    10.433    11.657 ms] gaussian_point_rasterisation_c94_0_kernel_1_range_for\n",
            "[ 30.54%   0.176 s     22x |    5.315     8.012    11.142 ms] generate_point_sort_key_by_num_overlap_tiles_c88_0_kernel_1_range_for\n",
            "[ 27.42%   0.158 s     22x |    4.878     7.193    10.084 ms] generate_num_overlap_tiles_c86_0_kernel_1_range_for\n",
            "[  1.61%   0.009 s     22x |    0.084     0.421     7.145 ms] generate_point_attributes_in_camera_plane_c92_0_kernel_1_range_for\n",
            "[  0.15%   0.001 s     22x |    0.036     0.040     0.062 ms] filter_point_in_camera_c82_0_kernel_1_range_for\n",
            "[  0.14%   0.001 s     22x |    0.030     0.037     0.049 ms] find_tile_start_and_end_c90_0_kernel_1_range_for\n",
            "[  0.08%   0.000 s     22x |    0.015     0.021     0.039 ms] filter_point_in_camera_c82_0_kernel_0_serial\n",
            "[  0.07%   0.000 s     22x |    0.014     0.018     0.033 ms] generate_point_attributes_in_camera_plane_c92_0_kernel_0_serial\n",
            "[  0.06%   0.000 s     22x |    0.012     0.015     0.026 ms] generate_num_overlap_tiles_c86_0_kernel_0_serial\n",
            "[  0.05%   0.000 s     22x |    0.012     0.014     0.033 ms] generate_point_sort_key_by_num_overlap_tiles_c88_0_kernel_0_serial\n",
            "[  0.05%   0.000 s     22x |    0.012     0.014     0.021 ms] gaussian_point_rasterisation_c94_0_kernel_0_serial\n",
            "[  0.04%   0.000 s     22x |    0.008     0.010     0.018 ms] find_tile_start_and_end_c90_0_kernel_2_serial\n",
            "[  0.03%   0.000 s     22x |    0.006     0.008     0.014 ms] find_tile_start_and_end_c90_0_kernel_0_serial\n",
            "-------------------------------------------------------------------------\n",
            "[100.00%] Total execution time:   0.577 s   number of results: 13\n",
            "=========================================================================\n",
            " 47% 14028/30001 [1:37:01<1:00:10,  4.42it/s]/usr/local/lib/python3.10/site-packages/torch/utils/data/dataloader.py:560: UserWarning: This DataLoader will create 4 worker processes in total. Our suggested max number of worker in current system is 2, which is smaller than what this DataLoader is going to create. Please be aware that excessive worker creation might get DataLoader running slow or even freeze, lower the worker number to avoid potential slowness/freeze if necessary.\n",
            "  warnings.warn(_create_warning_msg(\n",
            " 47% 14100/30001 [1:37:22<57:17,  4.63it/s]num_valid_points=26621;\n",
            "num_over_reconstructed: 23, num_under_reconstructed: 43\n",
            "total valid points: 26621 -> 26626, num_densify_points: 66, num_fillable_densify_points: 66\n",
            "num_transparent_points: 51, num_floaters_points: 10\n",
            " 47% 14200/30001 [1:37:50<1:34:22,  2.79it/s]1072 1920\n",
            "num_valid_points=26626;\n",
            "num_over_reconstructed: 41, num_under_reconstructed: 29\n",
            "total valid points: 26626 -> 26669, num_densify_points: 70, num_fillable_densify_points: 70\n",
            "num_transparent_points: 25, num_floaters_points: 2\n",
            " 48% 14300/30001 [1:38:26<1:10:11,  3.73it/s]num_valid_points=26669;\n",
            "num_over_reconstructed: 17, num_under_reconstructed: 26\n",
            "total valid points: 26669 -> 26682, num_densify_points: 43, num_fillable_densify_points: 43\n",
            "num_transparent_points: 28, num_floaters_points: 2\n",
            " 48% 14400/30001 [1:38:53<1:02:29,  4.16it/s]1072 1920\n",
            "num_valid_points=26682;\n",
            "num_over_reconstructed: 27, num_under_reconstructed: 23\n",
            "total valid points: 26682 -> 26688, num_densify_points: 50, num_fillable_densify_points: 50\n",
            "num_transparent_points: 39, num_floaters_points: 5\n",
            " 48% 14500/30001 [1:39:27<1:01:24,  4.21it/s]num_valid_points=26688;\n",
            "num_over_reconstructed: 16, num_under_reconstructed: 69\n",
            "total valid points: 26688 -> 26729, num_densify_points: 85, num_fillable_densify_points: 85\n",
            "num_transparent_points: 38, num_floaters_points: 6\n",
            " 49% 14600/30001 [1:39:54<56:58,  4.50it/s]1072 1920\n",
            "num_valid_points=26729;\n",
            "num_over_reconstructed: 29, num_under_reconstructed: 54\n",
            "total valid points: 26729 -> 26779, num_densify_points: 83, num_fillable_densify_points: 83\n",
            "num_transparent_points: 31, num_floaters_points: 2\n",
            " 49% 14700/30001 [1:40:26<58:22,  4.37it/s]num_valid_points=26779;\n",
            "num_over_reconstructed: 15, num_under_reconstructed: 38\n",
            "total valid points: 26779 -> 26802, num_densify_points: 53, num_fillable_densify_points: 53\n",
            "num_transparent_points: 27, num_floaters_points: 3\n",
            " 49% 14800/30001 [1:40:55<1:03:39,  3.98it/s]1072 1920\n",
            "num_valid_points=26802;\n",
            "num_over_reconstructed: 43, num_under_reconstructed: 44\n",
            "total valid points: 26802 -> 26854, num_densify_points: 87, num_fillable_densify_points: 87\n",
            "num_transparent_points: 27, num_floaters_points: 8\n",
            " 50% 14900/30001 [1:41:27<57:22,  4.39it/s]num_valid_points=26854;\n",
            "num_over_reconstructed: 34, num_under_reconstructed: 58\n",
            "total valid points: 26854 -> 26907, num_densify_points: 92, num_fillable_densify_points: 92\n",
            "num_transparent_points: 36, num_floaters_points: 3\n",
            " 50% 15000/30001 [1:41:55<1:10:48,  3.53it/s]1072 1920\n",
            "num_valid_points=26907;\n",
            "num_over_reconstructed: 27, num_under_reconstructed: 58\n",
            "total valid points: 26907 -> 26962, num_densify_points: 85, num_fillable_densify_points: 85\n",
            "num_transparent_points: 19, num_floaters_points: 11\n",
            "=========================================================================\n",
            "Kernel Profiler(count, default) @ CUDA on Tesla T4\n",
            "=========================================================================\n",
            "[      %     total   count |      min       avg       max   ] Kernel name\n",
            "-------------------------------------------------------------------------\n",
            "[ 90.81% 134.990 s   1000x |   89.333   134.990   271.507 ms] gaussian_point_rasterisation_backward_c96_0_kernel_1_range_for\n",
            "[  2.72%   4.046 s   1000x |    3.489     4.046    11.508 ms] gaussian_point_rasterisation_c94_0_kernel_1_range_for\n",
            "[  2.63%   3.906 s   1000x |    2.028     3.906    14.608 ms] generate_point_sort_key_by_num_overlap_tiles_c88_0_kernel_1_range_for\n",
            "[  2.41%   3.589 s   1000x |    1.791     3.589    13.222 ms] generate_num_overlap_tiles_c86_0_kernel_1_range_for\n",
            "[  1.17%   1.743 s   1000x |    1.707     1.743    13.534 ms] gaussian_point_rasterisation_backward_c96_0_kernel_3_range_for\n",
            "[  0.04%   0.058 s   1000x |    0.045     0.058     2.496 ms] generate_point_attributes_in_camera_plane_c92_0_kernel_1_range_for\n",
            "[  0.04%   0.053 s   1000x |    0.012     0.053     6.312 ms] gaussian_point_rasterisation_backward_c96_0_kernel_2_serial\n",
            "[  0.03%   0.042 s   1000x |    0.008     0.042    23.687 ms] generate_point_sort_key_by_num_overlap_tiles_c88_0_kernel_0_serial\n",
            "[  0.03%   0.041 s   1000x |    0.023     0.041     4.082 ms] find_tile_start_and_end_c90_0_kernel_1_range_for\n",
            "[  0.02%   0.037 s   1000x |    0.021     0.037     8.018 ms] filter_point_in_camera_c82_0_kernel_1_range_for\n",
            "[  0.02%   0.033 s   1000x |    0.008     0.033     6.718 ms] generate_point_attributes_in_camera_plane_c92_0_kernel_0_serial\n",
            "[  0.02%   0.028 s   1000x |    0.007     0.028    12.917 ms] generate_num_overlap_tiles_c86_0_kernel_0_serial\n",
            "[  0.02%   0.028 s   1000x |    0.010     0.028     4.659 ms] filter_point_in_camera_c82_0_kernel_0_serial\n",
            "[  0.02%   0.027 s   1000x |    0.008     0.027     8.060 ms] gaussian_point_rasterisation_c94_0_kernel_0_serial\n",
            "[  0.01%   0.012 s   1000x |    0.004     0.012     0.988 ms] find_tile_start_and_end_c90_0_kernel_2_serial\n",
            "[  0.01%   0.008 s   1000x |    0.003     0.008     1.007 ms] find_tile_start_and_end_c90_0_kernel_0_serial\n",
            "[  0.00%   0.005 s   1000x |    0.004     0.005     0.066 ms] gaussian_point_rasterisation_backward_c96_0_kernel_0_serial\n",
            "[  0.00%   0.000 s     20x |    0.010     0.018     0.031 ms] sample_from_point_c100_0_kernel_0_serial\n",
            "[  0.00%   0.000 s     20x |    0.006     0.014     0.027 ms] sample_from_point_c100_0_kernel_1_range_for\n",
            "-------------------------------------------------------------------------\n",
            "[100.00%] Total execution time: 148.647 s   number of results: 19\n",
            "=========================================================================\n",
            "=========================================================================\n",
            "Kernel Profiler(count, default) @ CUDA on Tesla T4\n",
            "=========================================================================\n",
            "[      %     total   count |      min       avg       max   ] Kernel name\n",
            "-------------------------------------------------------------------------\n",
            "-------------------------------------------------------------------------\n",
            "[100.00%] Total execution time:   0.000 s   number of results: 0\n",
            "=========================================================================\n",
            "\n",
            "  0% 0/22 [00:00<?, ?it/s]\u001b[A\n",
            "  5% 1/22 [00:10<03:29, 10.00s/it]\u001b[A\n",
            "  9% 2/22 [00:18<03:05,  9.29s/it]\u001b[A\n",
            " 14% 3/22 [00:28<03:02,  9.58s/it]\u001b[A\n",
            " 18% 4/22 [00:37<02:44,  9.16s/it]\u001b[A\n",
            " 23% 5/22 [00:42<02:14,  7.91s/it]\u001b[A\n",
            " 27% 6/22 [00:52<02:13,  8.32s/it]\u001b[A\n",
            " 32% 7/22 [00:59<01:59,  7.94s/it]\u001b[A\n",
            " 36% 8/22 [01:05<01:44,  7.49s/it]\u001b[A\n",
            " 41% 9/22 [01:08<01:19,  6.15s/it]\u001b[A\n",
            " 45% 10/22 [01:12<01:02,  5.21s/it]\u001b[A\n",
            " 50% 11/22 [01:19<01:03,  5.78s/it]\u001b[A\n",
            " 55% 12/22 [01:24<00:57,  5.77s/it]\u001b[A\n",
            " 59% 13/22 [01:30<00:52,  5.81s/it]\u001b[A\n",
            " 64% 14/22 [01:36<00:46,  5.82s/it]\u001b[A\n",
            " 68% 15/22 [01:43<00:42,  6.12s/it]\u001b[A\n",
            " 73% 16/22 [01:50<00:37,  6.26s/it]\u001b[A\n",
            " 77% 17/22 [01:54<00:28,  5.71s/it]\u001b[A\n",
            " 82% 18/22 [01:58<00:21,  5.31s/it]\u001b[A\n",
            " 86% 19/22 [02:03<00:15,  5.01s/it]\u001b[A\n",
            " 91% 20/22 [02:09<00:10,  5.31s/it]\u001b[A\n",
            " 95% 21/22 [02:16<00:06,  6.02s/it]\u001b[A\n",
            "100% 22/22 [02:24<00:00,  6.58s/it]\n",
            "=========================================================================\n",
            "Kernel Profiler(count, default) @ CUDA on Tesla T4\n",
            "=========================================================================\n",
            "[      %     total   count |      min       avg       max   ] Kernel name\n",
            "-------------------------------------------------------------------------\n",
            "[ 37.79%   0.231 s     22x |    9.650    10.505    12.173 ms] gaussian_point_rasterisation_c94_0_kernel_1_range_for\n",
            "[ 31.85%   0.195 s     22x |    5.037     8.854    12.186 ms] generate_point_sort_key_by_num_overlap_tiles_c88_0_kernel_1_range_for\n",
            "[ 29.37%   0.180 s     22x |    4.425     8.163    11.447 ms] generate_num_overlap_tiles_c86_0_kernel_1_range_for\n",
            "[  0.36%   0.002 s     22x |    0.088     0.100     0.129 ms] generate_point_attributes_in_camera_plane_c92_0_kernel_1_range_for\n",
            "[  0.14%   0.001 s     22x |    0.036     0.038     0.050 ms] filter_point_in_camera_c82_0_kernel_1_range_for\n",
            "[  0.13%   0.001 s     22x |    0.030     0.037     0.051 ms] find_tile_start_and_end_c90_0_kernel_1_range_for\n",
            "[  0.07%   0.000 s     22x |    0.015     0.019     0.039 ms] filter_point_in_camera_c82_0_kernel_0_serial\n",
            "[  0.06%   0.000 s     22x |    0.014     0.017     0.031 ms] generate_point_attributes_in_camera_plane_c92_0_kernel_0_serial\n",
            "[  0.06%   0.000 s     22x |    0.012     0.016     0.027 ms] generate_point_sort_key_by_num_overlap_tiles_c88_0_kernel_0_serial\n",
            "[  0.05%   0.000 s     22x |    0.011     0.015     0.029 ms] generate_num_overlap_tiles_c86_0_kernel_0_serial\n",
            "[  0.05%   0.000 s     22x |    0.012     0.015     0.030 ms] gaussian_point_rasterisation_c94_0_kernel_0_serial\n",
            "[  0.04%   0.000 s     22x |    0.008     0.010     0.019 ms] find_tile_start_and_end_c90_0_kernel_2_serial\n",
            "[  0.03%   0.000 s     22x |    0.006     0.008     0.018 ms] find_tile_start_and_end_c90_0_kernel_0_serial\n",
            "-------------------------------------------------------------------------\n",
            "[100.00%] Total execution time:   0.612 s   number of results: 13\n",
            "=========================================================================\n",
            " 50% 15036/30001 [1:44:34<54:27,  4.58it/s]/usr/local/lib/python3.10/site-packages/torch/utils/data/dataloader.py:560: UserWarning: This DataLoader will create 4 worker processes in total. Our suggested max number of worker in current system is 2, which is smaller than what this DataLoader is going to create. Please be aware that excessive worker creation might get DataLoader running slow or even freeze, lower the worker number to avoid potential slowness/freeze if necessary.\n",
            "  warnings.warn(_create_warning_msg(\n",
            " 50% 15100/30001 [1:44:52<56:25,  4.40it/s]num_valid_points=26962;\n",
            "num_over_reconstructed: 27, num_under_reconstructed: 77\n",
            "total valid points: 26962 -> 27026, num_densify_points: 104, num_fillable_densify_points: 104\n",
            "num_transparent_points: 28, num_floaters_points: 12\n",
            " 51% 15200/30001 [1:45:19<55:27,  4.45it/s]1072 1920\n",
            "num_valid_points=27026;\n",
            "num_over_reconstructed: 67, num_under_reconstructed: 78\n",
            "total valid points: 27026 -> 27133, num_densify_points: 145, num_fillable_densify_points: 145\n",
            "num_transparent_points: 34, num_floaters_points: 4\n",
            " 51% 15300/30001 [1:45:56<1:06:37,  3.68it/s]num_valid_points=27133;\n",
            "num_over_reconstructed: 23, num_under_reconstructed: 38\n",
            "total valid points: 27133 -> 27159, num_densify_points: 61, num_fillable_densify_points: 61\n",
            "num_transparent_points: 30, num_floaters_points: 5\n",
            " 51% 15400/30001 [1:46:23<56:34,  4.30it/s]1072 1920\n",
            "num_valid_points=27159;\n",
            "num_over_reconstructed: 9, num_under_reconstructed: 75\n",
            "total valid points: 27159 -> 27214, num_densify_points: 84, num_fillable_densify_points: 84\n",
            "num_transparent_points: 15, num_floaters_points: 14\n",
            " 52% 15500/30001 [1:46:56<1:53:21,  2.13it/s]num_valid_points=27214;\n",
            "num_over_reconstructed: 24, num_under_reconstructed: 44\n",
            "total valid points: 27214 -> 27248, num_densify_points: 68, num_fillable_densify_points: 68\n",
            "num_transparent_points: 26, num_floaters_points: 8\n",
            " 52% 15600/30001 [1:47:23<55:55,  4.29it/s]1072 1920\n",
            "num_valid_points=27248;\n",
            "num_over_reconstructed: 46, num_under_reconstructed: 58\n",
            "total valid points: 27248 -> 27328, num_densify_points: 104, num_fillable_densify_points: 104\n",
            "num_transparent_points: 23, num_floaters_points: 1\n",
            " 52% 15700/30001 [1:47:57<1:00:59,  3.91it/s]num_valid_points=27328;\n",
            "num_over_reconstructed: 30, num_under_reconstructed: 65\n",
            "total valid points: 27328 -> 27387, num_densify_points: 95, num_fillable_densify_points: 95\n",
            "num_transparent_points: 33, num_floaters_points: 3\n",
            " 53% 15800/30001 [1:48:26<1:13:35,  3.22it/s]1072 1920\n",
            "num_valid_points=27387;\n",
            "num_over_reconstructed: 32, num_under_reconstructed: 98\n",
            "total valid points: 27387 -> 27484, num_densify_points: 130, num_fillable_densify_points: 130\n",
            "num_transparent_points: 31, num_floaters_points: 2\n",
            " 53% 15900/30001 [1:48:58<53:21,  4.40it/s]num_valid_points=27484;\n",
            "num_over_reconstructed: 55, num_under_reconstructed: 66\n",
            "total valid points: 27484 -> 27577, num_densify_points: 121, num_fillable_densify_points: 121\n",
            "num_transparent_points: 19, num_floaters_points: 9\n",
            " 53% 16000/30001 [1:49:25<53:41,  4.35it/s]1072 1920\n",
            "num_valid_points=27577;\n",
            "num_over_reconstructed: 28, num_under_reconstructed: 68\n",
            "total valid points: 27577 -> 27631, num_densify_points: 96, num_fillable_densify_points: 96\n",
            "num_transparent_points: 32, num_floaters_points: 10\n",
            "=========================================================================\n",
            "Kernel Profiler(count, default) @ CUDA on Tesla T4\n",
            "=========================================================================\n",
            "[      %     total   count |      min       avg       max   ] Kernel name\n",
            "-------------------------------------------------------------------------\n",
            "[ 89.47% 134.513 s   1000x |   87.859   134.513   278.776 ms] gaussian_point_rasterisation_backward_c96_0_kernel_1_range_for\n",
            "[  3.35%   5.030 s   1000x |    1.985     5.030    30.714 ms] generate_point_sort_key_by_num_overlap_tiles_c88_0_kernel_1_range_for\n",
            "[  3.08%   4.628 s   1000x |    1.747     4.628    27.268 ms] generate_num_overlap_tiles_c86_0_kernel_1_range_for\n",
            "[  2.68%   4.027 s   1000x |    3.503     4.027    11.800 ms] gaussian_point_rasterisation_c94_0_kernel_1_range_for\n",
            "[  1.15%   1.734 s   1000x |    1.708     1.734     3.572 ms] gaussian_point_rasterisation_backward_c96_0_kernel_3_range_for\n",
            "[  0.05%   0.068 s   1000x |    0.008     0.068    16.096 ms] generate_point_attributes_in_camera_plane_c92_0_kernel_0_serial\n",
            "[  0.04%   0.060 s   1000x |    0.014     0.060    18.771 ms] gaussian_point_rasterisation_backward_c96_0_kernel_2_serial\n",
            "[  0.04%   0.059 s   1000x |    0.047     0.059     3.076 ms] generate_point_attributes_in_camera_plane_c92_0_kernel_1_range_for\n",
            "[  0.03%   0.043 s   1000x |    0.023     0.043     9.054 ms] find_tile_start_and_end_c90_0_kernel_1_range_for\n",
            "[  0.03%   0.042 s   1000x |    0.006     0.042     9.359 ms] generate_num_overlap_tiles_c86_0_kernel_0_serial\n",
            "[  0.03%   0.039 s   1000x |    0.010     0.039     8.620 ms] filter_point_in_camera_c82_0_kernel_0_serial\n",
            "[  0.02%   0.036 s   1000x |    0.021     0.036     4.596 ms] filter_point_in_camera_c82_0_kernel_1_range_for\n",
            "[  0.02%   0.029 s   1000x |    0.008     0.029     5.950 ms] gaussian_point_rasterisation_c94_0_kernel_0_serial\n",
            "[  0.01%   0.016 s   1000x |    0.009     0.016     0.193 ms] generate_point_sort_key_by_num_overlap_tiles_c88_0_kernel_0_serial\n",
            "[  0.01%   0.011 s   1000x |    0.005     0.011     0.902 ms] find_tile_start_and_end_c90_0_kernel_2_serial\n",
            "[  0.01%   0.008 s   1000x |    0.003     0.008     1.267 ms] find_tile_start_and_end_c90_0_kernel_0_serial\n",
            "[  0.00%   0.006 s   1000x |    0.004     0.006     1.268 ms] gaussian_point_rasterisation_backward_c96_0_kernel_0_serial\n",
            "[  0.00%   0.000 s     20x |    0.008     0.016     0.039 ms] sample_from_point_c100_0_kernel_0_serial\n",
            "[  0.00%   0.000 s     20x |    0.006     0.015     0.031 ms] sample_from_point_c100_0_kernel_1_range_for\n",
            "-------------------------------------------------------------------------\n",
            "[100.00%] Total execution time: 150.349 s   number of results: 19\n",
            "=========================================================================\n",
            "=========================================================================\n",
            "Kernel Profiler(count, default) @ CUDA on Tesla T4\n",
            "=========================================================================\n",
            "[      %     total   count |      min       avg       max   ] Kernel name\n",
            "-------------------------------------------------------------------------\n",
            "-------------------------------------------------------------------------\n",
            "[100.00%] Total execution time:   0.000 s   number of results: 0\n",
            "=========================================================================\n",
            "\n",
            "  0% 0/22 [00:00<?, ?it/s]\u001b[A\n",
            "  5% 1/22 [00:07<02:47,  7.96s/it]\u001b[A\n",
            "  9% 2/22 [00:11<01:49,  5.45s/it]\u001b[A\n",
            " 14% 3/22 [00:15<01:28,  4.64s/it]\u001b[A\n",
            " 18% 4/22 [00:18<01:15,  4.22s/it]\u001b[A\n",
            " 23% 5/22 [00:24<01:21,  4.78s/it]\u001b[A\n",
            " 27% 6/22 [00:30<01:22,  5.15s/it]\u001b[A\n",
            " 32% 7/22 [00:35<01:18,  5.23s/it]\u001b[A\n",
            " 36% 8/22 [00:39<01:05,  4.69s/it]\u001b[A\n",
            " 41% 9/22 [00:42<00:55,  4.30s/it]\u001b[A\n",
            " 45% 10/22 [00:49<00:59,  4.97s/it]\u001b[A\n",
            " 50% 11/22 [00:56<01:00,  5.50s/it]\u001b[A\n",
            " 55% 12/22 [01:00<00:51,  5.18s/it]\u001b[A\n",
            " 59% 13/22 [01:04<00:43,  4.88s/it]\u001b[A\n",
            " 64% 14/22 [01:13<00:47,  5.90s/it]\u001b[A\n",
            " 68% 15/22 [01:19<00:42,  6.12s/it]\u001b[A\n",
            " 73% 16/22 [01:24<00:33,  5.60s/it]\u001b[A\n",
            " 77% 17/22 [01:27<00:24,  4.96s/it]\u001b[A\n",
            " 82% 18/22 [01:33<00:20,  5.21s/it]\u001b[A\n",
            " 86% 19/22 [01:41<00:18,  6.15s/it]\u001b[A\n",
            " 91% 20/22 [01:47<00:12,  6.10s/it]\u001b[A\n",
            " 95% 21/22 [01:52<00:05,  5.59s/it]\u001b[A\n",
            "100% 22/22 [01:56<00:00,  5.27s/it]\n",
            "=========================================================================\n",
            "Kernel Profiler(count, default) @ CUDA on Tesla T4\n",
            "=========================================================================\n",
            "[      %     total   count |      min       avg       max   ] Kernel name\n",
            "-------------------------------------------------------------------------\n",
            "[ 37.41%   0.317 s     22x |    7.616    14.411    28.869 ms] generate_point_sort_key_by_num_overlap_tiles_c88_0_kernel_1_range_for\n",
            "[ 34.64%   0.294 s     22x |    7.037    13.347    26.504 ms] generate_num_overlap_tiles_c86_0_kernel_1_range_for\n",
            "[ 26.92%   0.228 s     22x |    9.379    10.372    11.332 ms] gaussian_point_rasterisation_c94_0_kernel_1_range_for\n",
            "[  0.38%   0.003 s     22x |    0.016     0.147     2.873 ms] filter_point_in_camera_c82_0_kernel_0_serial\n",
            "[  0.25%   0.002 s     22x |    0.088     0.097     0.116 ms] generate_point_attributes_in_camera_plane_c92_0_kernel_1_range_for\n",
            "[  0.10%   0.001 s     22x |    0.036     0.038     0.049 ms] filter_point_in_camera_c82_0_kernel_1_range_for\n",
            "[  0.09%   0.001 s     22x |    0.029     0.035     0.045 ms] find_tile_start_and_end_c90_0_kernel_1_range_for\n",
            "[  0.04%   0.000 s     22x |    0.013     0.017     0.037 ms] generate_point_attributes_in_camera_plane_c92_0_kernel_0_serial\n",
            "[  0.04%   0.000 s     22x |    0.011     0.015     0.027 ms] generate_point_sort_key_by_num_overlap_tiles_c88_0_kernel_0_serial\n",
            "[  0.04%   0.000 s     22x |    0.011     0.014     0.029 ms] generate_num_overlap_tiles_c86_0_kernel_0_serial\n",
            "[  0.04%   0.000 s     22x |    0.012     0.014     0.022 ms] gaussian_point_rasterisation_c94_0_kernel_0_serial\n",
            "[  0.03%   0.000 s     22x |    0.008     0.010     0.018 ms] find_tile_start_and_end_c90_0_kernel_2_serial\n",
            "[  0.02%   0.000 s     22x |    0.006     0.008     0.015 ms] find_tile_start_and_end_c90_0_kernel_0_serial\n",
            "-------------------------------------------------------------------------\n",
            "[100.00%] Total execution time:   0.848 s   number of results: 13\n",
            "=========================================================================\n",
            " 53% 16002/30001 [1:51:33<107:13:27, 27.57s/it]/usr/local/lib/python3.10/site-packages/torch/utils/data/dataloader.py:560: UserWarning: This DataLoader will create 4 worker processes in total. Our suggested max number of worker in current system is 2, which is smaller than what this DataLoader is going to create. Please be aware that excessive worker creation might get DataLoader running slow or even freeze, lower the worker number to avoid potential slowness/freeze if necessary.\n",
            "  warnings.warn(_create_warning_msg(\n",
            " 54% 16100/30001 [1:52:04<1:03:50,  3.63it/s]num_valid_points=27631;\n",
            "num_over_reconstructed: 20, num_under_reconstructed: 3\n",
            "total valid points: 27631 -> 27432, num_densify_points: 23, num_fillable_densify_points: 23\n",
            "num_transparent_points: 211, num_floaters_points: 11\n",
            " 54% 16200/30001 [1:52:34<1:02:47,  3.66it/s]1072 1920\n",
            "num_valid_points=27432;\n",
            "num_over_reconstructed: 10, num_under_reconstructed: 4\n",
            "total valid points: 27432 -> 27368, num_densify_points: 14, num_fillable_densify_points: 14\n",
            "num_transparent_points: 72, num_floaters_points: 6\n",
            " 54% 16300/30001 [1:53:11<1:46:57,  2.14it/s]num_valid_points=27368;\n",
            "num_over_reconstructed: 17, num_under_reconstructed: 4\n",
            "total valid points: 27368 -> 27306, num_densify_points: 21, num_fillable_densify_points: 21\n",
            "num_transparent_points: 75, num_floaters_points: 8\n",
            " 55% 16400/30001 [1:53:40<1:03:52,  3.55it/s]1072 1920\n",
            "num_valid_points=27306;\n",
            "num_over_reconstructed: 15, num_under_reconstructed: 6\n",
            "total valid points: 27306 -> 27246, num_densify_points: 21, num_fillable_densify_points: 21\n",
            "num_transparent_points: 70, num_floaters_points: 11\n",
            " 55% 16500/30001 [1:54:17<57:02,  3.94it/s]num_valid_points=27246;\n",
            "num_over_reconstructed: 15, num_under_reconstructed: 13\n",
            "total valid points: 27246 -> 27202, num_densify_points: 28, num_fillable_densify_points: 28\n",
            "num_transparent_points: 64, num_floaters_points: 8\n",
            " 55% 16600/30001 [1:54:46<58:16,  3.83it/s]1072 1920\n",
            "num_valid_points=27202;\n",
            "num_over_reconstructed: 12, num_under_reconstructed: 11\n",
            "total valid points: 27202 -> 27156, num_densify_points: 23, num_fillable_densify_points: 23\n",
            "num_transparent_points: 51, num_floaters_points: 18\n",
            " 56% 16700/30001 [1:55:21<59:18,  3.74it/s]num_valid_points=27156;\n",
            "num_over_reconstructed: 8, num_under_reconstructed: 17\n",
            "total valid points: 27156 -> 27120, num_densify_points: 25, num_fillable_densify_points: 25\n",
            "num_transparent_points: 48, num_floaters_points: 13\n",
            " 56% 16800/30001 [1:55:49<54:50,  4.01it/s]1072 1920\n",
            "num_valid_points=27120;\n",
            "num_over_reconstructed: 42, num_under_reconstructed: 29\n",
            "total valid points: 27120 -> 27136, num_densify_points: 71, num_fillable_densify_points: 71\n",
            "num_transparent_points: 52, num_floaters_points: 3\n",
            " 56% 16900/30001 [1:56:24<52:07,  4.19it/s]num_valid_points=27136;\n",
            "num_over_reconstructed: 12, num_under_reconstructed: 13\n",
            "total valid points: 27136 -> 27083, num_densify_points: 25, num_fillable_densify_points: 25\n",
            "num_transparent_points: 69, num_floaters_points: 9\n",
            " 57% 17000/30001 [1:56:53<59:09,  3.66it/s]  1072 1920\n",
            "num_valid_points=27083;\n",
            "num_over_reconstructed: 46, num_under_reconstructed: 23\n",
            "total valid points: 27083 -> 27080, num_densify_points: 69, num_fillable_densify_points: 69\n",
            "num_transparent_points: 61, num_floaters_points: 11\n",
            "=========================================================================\n",
            "Kernel Profiler(count, default) @ CUDA on Tesla T4\n",
            "=========================================================================\n",
            "[      %     total   count |      min       avg       max   ] Kernel name\n",
            "-------------------------------------------------------------------------\n",
            "[ 88.82% 150.438 s   1000x |  100.368   150.438   259.551 ms] gaussian_point_rasterisation_backward_c96_0_kernel_1_range_for\n",
            "[  3.80%   6.428 s   1000x |    2.062     6.428    31.810 ms] generate_point_sort_key_by_num_overlap_tiles_c88_0_kernel_1_range_for\n",
            "[  3.53%   5.975 s   1000x |    1.810     5.975    28.746 ms] generate_num_overlap_tiles_c86_0_kernel_1_range_for\n",
            "[  2.59%   4.383 s   1000x |    3.681     4.383    12.536 ms] gaussian_point_rasterisation_c94_0_kernel_1_range_for\n",
            "[  1.03%   1.740 s   1000x |    1.712     1.740     8.204 ms] gaussian_point_rasterisation_backward_c96_0_kernel_3_range_for\n",
            "[  0.05%   0.084 s   1000x |    0.047     0.084    12.311 ms] generate_point_attributes_in_camera_plane_c92_0_kernel_1_range_for\n",
            "[  0.03%   0.050 s   1000x |    0.013     0.050     6.346 ms] gaussian_point_rasterisation_backward_c96_0_kernel_2_serial\n",
            "[  0.03%   0.049 s   1000x |    0.009     0.049    12.396 ms] generate_point_sort_key_by_num_overlap_tiles_c88_0_kernel_0_serial\n",
            "[  0.02%   0.041 s   1000x |    0.025     0.041     4.025 ms] find_tile_start_and_end_c90_0_kernel_1_range_for\n",
            "[  0.02%   0.039 s   1000x |    0.021     0.039     6.563 ms] filter_point_in_camera_c82_0_kernel_1_range_for\n",
            "[  0.02%   0.035 s   1000x |    0.008     0.035    10.045 ms] generate_point_attributes_in_camera_plane_c92_0_kernel_0_serial\n",
            "[  0.02%   0.032 s   1000x |    0.010     0.032     6.036 ms] filter_point_in_camera_c82_0_kernel_0_serial\n",
            "[  0.02%   0.027 s   1000x |    0.006     0.027     3.969 ms] generate_num_overlap_tiles_c86_0_kernel_0_serial\n",
            "[  0.01%   0.022 s   1000x |    0.005     0.022     8.135 ms] find_tile_start_and_end_c90_0_kernel_2_serial\n",
            "[  0.01%   0.021 s   1000x |    0.008     0.021     3.041 ms] gaussian_point_rasterisation_c94_0_kernel_0_serial\n",
            "[  0.00%   0.006 s   1000x |    0.003     0.006     0.715 ms] find_tile_start_and_end_c90_0_kernel_0_serial\n",
            "[  0.00%   0.005 s   1000x |    0.004     0.005     0.078 ms] gaussian_point_rasterisation_backward_c96_0_kernel_0_serial\n",
            "[  0.00%   0.000 s     20x |    0.008     0.016     0.040 ms] sample_from_point_c100_0_kernel_0_serial\n",
            "[  0.00%   0.000 s     20x |    0.007     0.013     0.020 ms] sample_from_point_c100_0_kernel_1_range_for\n",
            "-------------------------------------------------------------------------\n",
            "[100.00%] Total execution time: 169.377 s   number of results: 19\n",
            "=========================================================================\n",
            "=========================================================================\n",
            "Kernel Profiler(count, default) @ CUDA on Tesla T4\n",
            "=========================================================================\n",
            "[      %     total   count |      min       avg       max   ] Kernel name\n",
            "-------------------------------------------------------------------------\n",
            "-------------------------------------------------------------------------\n",
            "[100.00%] Total execution time:   0.000 s   number of results: 0\n",
            "=========================================================================\n",
            "\n",
            "  0% 0/22 [00:00<?, ?it/s]\u001b[A\n",
            "  5% 1/22 [00:06<02:26,  6.98s/it]\u001b[A\n",
            "  9% 2/22 [00:14<02:23,  7.16s/it]\u001b[A\n",
            " 14% 3/22 [00:21<02:13,  7.04s/it]\u001b[A\n",
            " 18% 4/22 [00:26<01:53,  6.28s/it]\u001b[A\n",
            " 23% 5/22 [00:32<01:48,  6.36s/it]\u001b[A\n",
            " 27% 6/22 [00:38<01:37,  6.11s/it]\u001b[A\n",
            " 32% 7/22 [00:45<01:36,  6.43s/it]\u001b[A\n",
            " 36% 8/22 [00:51<01:26,  6.16s/it]\u001b[A\n",
            " 41% 9/22 [00:58<01:24,  6.49s/it]\u001b[A\n",
            " 45% 10/22 [01:01<01:05,  5.45s/it]\u001b[A\n",
            " 50% 11/22 [01:05<00:53,  4.89s/it]\u001b[A\n",
            " 55% 12/22 [01:11<00:54,  5.50s/it]\u001b[A\n",
            " 59% 13/22 [01:18<00:51,  5.71s/it]\u001b[A\n",
            " 64% 14/22 [01:23<00:45,  5.70s/it]\u001b[A\n",
            " 68% 15/22 [01:27<00:35,  5.05s/it]\u001b[A\n",
            " 73% 16/22 [01:31<00:28,  4.75s/it]\u001b[A\n",
            " 77% 17/22 [01:38<00:26,  5.37s/it]\u001b[A\n",
            " 82% 18/22 [01:43<00:21,  5.44s/it]\u001b[A\n",
            " 86% 19/22 [01:52<00:18,  6.28s/it]\u001b[A\n",
            " 91% 20/22 [01:55<00:11,  5.53s/it]\u001b[A\n",
            " 95% 21/22 [02:03<00:06,  6.27s/it]\u001b[A\n",
            "100% 22/22 [02:11<00:00,  5.97s/it]\n",
            "=========================================================================\n",
            "Kernel Profiler(count, default) @ CUDA on Tesla T4\n",
            "=========================================================================\n",
            "[      %     total   count |      min       avg       max   ] Kernel name\n",
            "-------------------------------------------------------------------------\n",
            "[ 37.55%   0.352 s     22x |    5.295    15.980    31.750 ms] generate_point_sort_key_by_num_overlap_tiles_c88_0_kernel_1_range_for\n",
            "[ 34.19%   0.320 s     22x |    4.782    14.550    29.569 ms] generate_num_overlap_tiles_c86_0_kernel_1_range_for\n",
            "[ 26.45%   0.248 s     22x |   10.277    11.256    12.809 ms] gaussian_point_rasterisation_c94_0_kernel_1_range_for\n",
            "[  0.99%   0.009 s     22x |    0.088     0.421     7.096 ms] generate_point_attributes_in_camera_plane_c92_0_kernel_1_range_for\n",
            "[  0.43%   0.004 s     22x |    0.014     0.182     3.162 ms] generate_point_attributes_in_camera_plane_c92_0_kernel_0_serial\n",
            "[  0.09%   0.001 s     22x |    0.031     0.039     0.064 ms] find_tile_start_and_end_c90_0_kernel_1_range_for\n",
            "[  0.09%   0.001 s     22x |    0.035     0.038     0.060 ms] filter_point_in_camera_c82_0_kernel_1_range_for\n",
            "[  0.04%   0.000 s     22x |    0.015     0.018     0.037 ms] filter_point_in_camera_c82_0_kernel_0_serial\n",
            "[  0.04%   0.000 s     22x |    0.012     0.017     0.047 ms] generate_num_overlap_tiles_c86_0_kernel_0_serial\n",
            "[  0.04%   0.000 s     22x |    0.012     0.016     0.032 ms] gaussian_point_rasterisation_c94_0_kernel_0_serial\n",
            "[  0.03%   0.000 s     22x |    0.012     0.014     0.029 ms] generate_point_sort_key_by_num_overlap_tiles_c88_0_kernel_0_serial\n",
            "[  0.02%   0.000 s     22x |    0.008     0.010     0.020 ms] find_tile_start_and_end_c90_0_kernel_2_serial\n",
            "[  0.02%   0.000 s     22x |    0.006     0.009     0.027 ms] find_tile_start_and_end_c90_0_kernel_0_serial\n",
            "-------------------------------------------------------------------------\n",
            "[100.00%] Total execution time:   0.936 s   number of results: 13\n",
            "=========================================================================\n",
            " 57% 17010/30001 [1:59:13<6:53:52,  1.91s/it]/usr/local/lib/python3.10/site-packages/torch/utils/data/dataloader.py:560: UserWarning: This DataLoader will create 4 worker processes in total. Our suggested max number of worker in current system is 2, which is smaller than what this DataLoader is going to create. Please be aware that excessive worker creation might get DataLoader running slow or even freeze, lower the worker number to avoid potential slowness/freeze if necessary.\n",
            "  warnings.warn(_create_warning_msg(\n",
            " 57% 17100/30001 [1:59:40<1:06:32,  3.23it/s]num_valid_points=27080;\n",
            "num_over_reconstructed: 27, num_under_reconstructed: 35\n",
            "total valid points: 27080 -> 27048, num_densify_points: 62, num_fillable_densify_points: 62\n",
            "num_transparent_points: 89, num_floaters_points: 5\n",
            " 57% 17200/30001 [2:00:08<51:40,  4.13it/s]1072 1920\n",
            "num_valid_points=27048;\n",
            "num_over_reconstructed: 19, num_under_reconstructed: 49\n",
            "total valid points: 27048 -> 27044, num_densify_points: 68, num_fillable_densify_points: 68\n",
            "num_transparent_points: 59, num_floaters_points: 13\n",
            " 58% 17300/30001 [2:00:43<50:40,  4.18it/s]num_valid_points=27044;\n",
            "num_over_reconstructed: 34, num_under_reconstructed: 28\n",
            "total valid points: 27044 -> 27025, num_densify_points: 62, num_fillable_densify_points: 62\n",
            "num_transparent_points: 72, num_floaters_points: 9\n",
            " 58% 17400/30001 [2:01:13<57:54,  3.63it/s]1072 1920\n",
            "num_valid_points=27025;\n",
            "num_over_reconstructed: 41, num_under_reconstructed: 32\n",
            "total valid points: 27025 -> 27025, num_densify_points: 73, num_fillable_densify_points: 73\n",
            "num_transparent_points: 66, num_floaters_points: 7\n",
            " 58% 17500/30001 [2:01:47<52:01,  4.00it/s]num_valid_points=27025;\n",
            "num_over_reconstructed: 8, num_under_reconstructed: 51\n",
            "total valid points: 27025 -> 27013, num_densify_points: 59, num_fillable_densify_points: 59\n",
            "num_transparent_points: 61, num_floaters_points: 10\n",
            " 59% 17600/30001 [2:02:17<2:04:28,  1.66it/s]1072 1920\n",
            "num_valid_points=27013;\n",
            "num_over_reconstructed: 22, num_under_reconstructed: 47\n",
            "total valid points: 27013 -> 27022, num_densify_points: 69, num_fillable_densify_points: 69\n",
            "num_transparent_points: 53, num_floaters_points: 7\n",
            " 59% 17700/30001 [2:02:52<54:12,  3.78it/s]num_valid_points=27022;\n",
            "num_over_reconstructed: 9, num_under_reconstructed: 40\n",
            "total valid points: 27022 -> 27025, num_densify_points: 49, num_fillable_densify_points: 49\n",
            "num_transparent_points: 40, num_floaters_points: 6\n",
            " 59% 17800/30001 [2:03:21<47:16,  4.30it/s]1072 1920\n",
            "num_valid_points=27025;\n",
            "num_over_reconstructed: 10, num_under_reconstructed: 58\n",
            "total valid points: 27025 -> 27028, num_densify_points: 68, num_fillable_densify_points: 68\n",
            "num_transparent_points: 46, num_floaters_points: 19\n",
            " 60% 17900/30001 [2:03:58<1:06:54,  3.01it/s]num_valid_points=27028;\n",
            "num_over_reconstructed: 29, num_under_reconstructed: 64\n",
            "total valid points: 27028 -> 27065, num_densify_points: 93, num_fillable_densify_points: 93\n",
            "num_transparent_points: 45, num_floaters_points: 11\n",
            " 60% 18000/30001 [2:04:27<57:54,  3.45it/s]1072 1920\n",
            "num_valid_points=27065;\n",
            "num_over_reconstructed: 25, num_under_reconstructed: 33\n",
            "total valid points: 27065 -> 27064, num_densify_points: 58, num_fillable_densify_points: 58\n",
            "num_transparent_points: 43, num_floaters_points: 16\n",
            "=========================================================================\n",
            "Kernel Profiler(count, default) @ CUDA on Tesla T4\n",
            "=========================================================================\n",
            "[      %     total   count |      min       avg       max   ] Kernel name\n",
            "-------------------------------------------------------------------------\n",
            "[ 87.86% 146.145 s   1000x |   97.473   146.145   294.130 ms] gaussian_point_rasterisation_backward_c96_0_kernel_1_range_for\n",
            "[  4.26%   7.084 s   1000x |    1.643     7.084    27.943 ms] generate_point_sort_key_by_num_overlap_tiles_c88_0_kernel_1_range_for\n",
            "[  3.99%   6.638 s   1000x |    1.501     6.638    27.512 ms] generate_num_overlap_tiles_c86_0_kernel_1_range_for\n",
            "[  2.58%   4.294 s   1000x |    3.681     4.294    15.053 ms] gaussian_point_rasterisation_c94_0_kernel_1_range_for\n",
            "[  1.04%   1.732 s   1000x |    1.714     1.732     1.772 ms] gaussian_point_rasterisation_backward_c96_0_kernel_3_range_for\n",
            "[  0.04%   0.062 s   1000x |    0.008     0.062    14.834 ms] generate_point_attributes_in_camera_plane_c92_0_kernel_0_serial\n",
            "[  0.03%   0.056 s   1000x |    0.014     0.056     7.078 ms] gaussian_point_rasterisation_backward_c96_0_kernel_2_serial\n",
            "[  0.03%   0.055 s   1000x |    0.047     0.055     1.058 ms] generate_point_attributes_in_camera_plane_c92_0_kernel_1_range_for\n",
            "[  0.03%   0.047 s   1000x |    0.021     0.047     9.484 ms] filter_point_in_camera_c82_0_kernel_1_range_for\n",
            "[  0.03%   0.042 s   1000x |    0.010     0.042     8.026 ms] filter_point_in_camera_c82_0_kernel_0_serial\n",
            "[  0.03%   0.042 s   1000x |    0.007     0.042     8.536 ms] generate_num_overlap_tiles_c86_0_kernel_0_serial\n",
            "[  0.02%   0.033 s   1000x |    0.024     0.033     0.407 ms] find_tile_start_and_end_c90_0_kernel_1_range_for\n",
            "[  0.02%   0.028 s   1000x |    0.008     0.028    10.224 ms] gaussian_point_rasterisation_c94_0_kernel_0_serial\n",
            "[  0.02%   0.028 s   1000x |    0.005     0.028    16.108 ms] find_tile_start_and_end_c90_0_kernel_2_serial\n",
            "[  0.02%   0.026 s   1000x |    0.009     0.026     6.455 ms] generate_point_sort_key_by_num_overlap_tiles_c88_0_kernel_0_serial\n",
            "[  0.01%   0.012 s   1000x |    0.003     0.012     4.766 ms] find_tile_start_and_end_c90_0_kernel_0_serial\n",
            "[  0.00%   0.005 s   1000x |    0.004     0.005     0.077 ms] gaussian_point_rasterisation_backward_c96_0_kernel_0_serial\n",
            "[  0.00%   0.000 s     20x |    0.008     0.016     0.032 ms] sample_from_point_c100_0_kernel_0_serial\n",
            "[  0.00%   0.000 s     20x |    0.007     0.015     0.037 ms] sample_from_point_c100_0_kernel_1_range_for\n",
            "-------------------------------------------------------------------------\n",
            "[100.00%] Total execution time: 166.329 s   number of results: 19\n",
            "=========================================================================\n",
            "=========================================================================\n",
            "Kernel Profiler(count, default) @ CUDA on Tesla T4\n",
            "=========================================================================\n",
            "[      %     total   count |      min       avg       max   ] Kernel name\n",
            "-------------------------------------------------------------------------\n",
            "-------------------------------------------------------------------------\n",
            "[100.00%] Total execution time:   0.000 s   number of results: 0\n",
            "=========================================================================\n",
            "\n",
            "  0% 0/22 [00:00<?, ?it/s]\u001b[A\n",
            "  5% 1/22 [00:05<01:48,  5.16s/it]\u001b[A\n",
            "  9% 2/22 [00:12<02:05,  6.26s/it]\u001b[A\n",
            " 14% 3/22 [00:18<02:01,  6.41s/it]\u001b[A\n",
            " 18% 4/22 [00:25<01:56,  6.46s/it]\u001b[A\n",
            " 23% 5/22 [00:28<01:31,  5.38s/it]\u001b[A\n",
            " 27% 6/22 [00:36<01:38,  6.18s/it]\u001b[A\n",
            " 32% 7/22 [00:43<01:38,  6.59s/it]\u001b[A\n",
            " 36% 8/22 [00:49<01:26,  6.17s/it]\u001b[A\n",
            " 41% 9/22 [00:53<01:12,  5.55s/it]\u001b[A\n",
            " 45% 10/22 [00:56<00:57,  4.80s/it]\u001b[A\n",
            " 50% 11/22 [01:03<01:00,  5.47s/it]\u001b[A\n",
            " 55% 12/22 [01:11<01:01,  6.19s/it]\u001b[A\n",
            " 59% 13/22 [01:17<00:54,  6.08s/it]\u001b[A\n",
            " 64% 14/22 [01:21<00:45,  5.65s/it]\u001b[A\n",
            " 68% 15/22 [01:27<00:40,  5.73s/it]\u001b[A\n",
            " 73% 16/22 [01:34<00:36,  6.11s/it]\u001b[A\n",
            " 77% 17/22 [01:41<00:31,  6.32s/it]\u001b[A\n",
            " 82% 18/22 [01:48<00:25,  6.39s/it]\u001b[A\n",
            " 86% 19/22 [01:54<00:19,  6.47s/it]\u001b[A\n",
            " 91% 20/22 [02:01<00:12,  6.45s/it]\u001b[A\n",
            " 95% 21/22 [02:08<00:06,  6.65s/it]\u001b[A\n",
            "100% 22/22 [02:12<00:00,  6.01s/it]\n",
            "=========================================================================\n",
            "Kernel Profiler(count, default) @ CUDA on Tesla T4\n",
            "=========================================================================\n",
            "[      %     total   count |      min       avg       max   ] Kernel name\n",
            "-------------------------------------------------------------------------\n",
            "[ 38.55%   0.376 s     22x |    6.060    17.095    46.987 ms] generate_point_sort_key_by_num_overlap_tiles_c88_0_kernel_1_range_for\n",
            "[ 35.49%   0.346 s     22x |    5.292    15.737    44.784 ms] generate_num_overlap_tiles_c86_0_kernel_1_range_for\n",
            "[ 25.24%   0.246 s     22x |   10.115    11.190    12.654 ms] gaussian_point_rasterisation_c94_0_kernel_1_range_for\n",
            "[  0.23%   0.002 s     22x |    0.090     0.100     0.120 ms] generate_point_attributes_in_camera_plane_c92_0_kernel_1_range_for\n",
            "[  0.12%   0.001 s     22x |    0.008     0.052     0.918 ms] find_tile_start_and_end_c90_0_kernel_2_serial\n",
            "[  0.09%   0.001 s     22x |    0.032     0.039     0.051 ms] find_tile_start_and_end_c90_0_kernel_1_range_for\n",
            "[  0.09%   0.001 s     22x |    0.036     0.038     0.055 ms] filter_point_in_camera_c82_0_kernel_1_range_for\n",
            "[  0.04%   0.000 s     22x |    0.016     0.019     0.041 ms] filter_point_in_camera_c82_0_kernel_0_serial\n",
            "[  0.04%   0.000 s     22x |    0.014     0.017     0.027 ms] generate_point_attributes_in_camera_plane_c92_0_kernel_0_serial\n",
            "[  0.03%   0.000 s     22x |    0.013     0.015     0.035 ms] generate_point_sort_key_by_num_overlap_tiles_c88_0_kernel_0_serial\n",
            "[  0.03%   0.000 s     22x |    0.012     0.014     0.028 ms] gaussian_point_rasterisation_c94_0_kernel_0_serial\n",
            "[  0.03%   0.000 s     22x |    0.012     0.014     0.028 ms] generate_num_overlap_tiles_c86_0_kernel_0_serial\n",
            "[  0.02%   0.000 s     22x |    0.006     0.008     0.015 ms] find_tile_start_and_end_c90_0_kernel_0_serial\n",
            "-------------------------------------------------------------------------\n",
            "[100.00%] Total execution time:   0.975 s   number of results: 13\n",
            "=========================================================================\n",
            " 60% 18018/30001 [2:06:49<1:07:55,  2.94it/s]/usr/local/lib/python3.10/site-packages/torch/utils/data/dataloader.py:560: UserWarning: This DataLoader will create 4 worker processes in total. Our suggested max number of worker in current system is 2, which is smaller than what this DataLoader is going to create. Please be aware that excessive worker creation might get DataLoader running slow or even freeze, lower the worker number to avoid potential slowness/freeze if necessary.\n",
            "  warnings.warn(_create_warning_msg(\n",
            " 60% 18100/30001 [2:07:14<48:19,  4.10it/s]num_valid_points=27064;\n",
            "num_over_reconstructed: 36, num_under_reconstructed: 62\n",
            "total valid points: 27064 -> 27118, num_densify_points: 98, num_fillable_densify_points: 98\n",
            "num_transparent_points: 32, num_floaters_points: 12\n",
            " 61% 18200/30001 [2:07:45<52:50,  3.72it/s]1072 1920\n",
            "num_valid_points=27118;\n",
            "num_over_reconstructed: 28, num_under_reconstructed: 84\n",
            "total valid points: 27118 -> 27182, num_densify_points: 112, num_fillable_densify_points: 112\n",
            "num_transparent_points: 45, num_floaters_points: 3\n",
            " 61% 18300/30001 [2:08:22<53:03,  3.68it/s]num_valid_points=27182;\n",
            "num_over_reconstructed: 19, num_under_reconstructed: 60\n",
            "total valid points: 27182 -> 27210, num_densify_points: 79, num_fillable_densify_points: 79\n",
            "num_transparent_points: 38, num_floaters_points: 13\n",
            " 61% 18400/30001 [2:08:53<1:25:29,  2.26it/s]1072 1920\n",
            "num_valid_points=27210;\n",
            "num_over_reconstructed: 15, num_under_reconstructed: 40\n",
            "total valid points: 27210 -> 27228, num_densify_points: 55, num_fillable_densify_points: 55\n",
            "num_transparent_points: 25, num_floaters_points: 12\n",
            " 62% 18500/30001 [2:09:27<49:11,  3.90it/s]num_valid_points=27228;\n",
            "num_over_reconstructed: 23, num_under_reconstructed: 52\n",
            "total valid points: 27228 -> 27265, num_densify_points: 75, num_fillable_densify_points: 75\n",
            "num_transparent_points: 32, num_floaters_points: 6\n",
            " 62% 18600/30001 [2:09:56<45:14,  4.20it/s]1072 1920\n",
            "num_valid_points=27265;\n",
            "num_over_reconstructed: 6, num_under_reconstructed: 64\n",
            "total valid points: 27265 -> 27290, num_densify_points: 70, num_fillable_densify_points: 70\n",
            "num_transparent_points: 27, num_floaters_points: 18\n",
            " 62% 18700/30001 [2:10:30<53:13,  3.54it/s]num_valid_points=27290;\n",
            "num_over_reconstructed: 11, num_under_reconstructed: 56\n",
            "total valid points: 27290 -> 27314, num_densify_points: 67, num_fillable_densify_points: 67\n",
            "num_transparent_points: 31, num_floaters_points: 12\n",
            " 63% 18800/30001 [2:10:59<54:03,  3.45it/s]1072 1920\n",
            "num_valid_points=27314;\n",
            "num_over_reconstructed: 22, num_under_reconstructed: 47\n",
            "total valid points: 27314 -> 27339, num_densify_points: 69, num_fillable_densify_points: 69\n",
            "num_transparent_points: 23, num_floaters_points: 21\n",
            " 63% 18900/30001 [2:11:34<45:23,  4.08it/s]num_valid_points=27339;\n",
            "num_over_reconstructed: 7, num_under_reconstructed: 85\n",
            "total valid points: 27339 -> 27399, num_densify_points: 92, num_fillable_densify_points: 92\n",
            "num_transparent_points: 24, num_floaters_points: 8\n",
            " 63% 19000/30001 [2:12:04<43:29,  4.22it/s]1072 1920\n",
            "num_valid_points=27399;\n",
            "num_over_reconstructed: 33, num_under_reconstructed: 60\n",
            "total valid points: 27399 -> 27460, num_densify_points: 93, num_fillable_densify_points: 93\n",
            "num_transparent_points: 20, num_floaters_points: 12\n",
            "=========================================================================\n",
            "Kernel Profiler(count, default) @ CUDA on Tesla T4\n",
            "=========================================================================\n",
            "[      %     total   count |      min       avg       max   ] Kernel name\n",
            "-------------------------------------------------------------------------\n",
            "[ 84.66% 142.242 s   1000x |   98.066   142.242   251.419 ms] gaussian_point_rasterisation_backward_c96_0_kernel_1_range_for\n",
            "[  5.91%   9.929 s   1000x |    1.768     9.929    67.596 ms] generate_point_sort_key_by_num_overlap_tiles_c88_0_kernel_1_range_for\n",
            "[  5.64%   9.468 s   1000x |    1.540     9.468    64.703 ms] generate_num_overlap_tiles_c86_0_kernel_1_range_for\n",
            "[  2.52%   4.229 s   1000x |    3.694     4.229    11.619 ms] gaussian_point_rasterisation_c94_0_kernel_1_range_for\n",
            "[  1.03%   1.736 s   1000x |    1.713     1.736     2.714 ms] gaussian_point_rasterisation_backward_c96_0_kernel_3_range_for\n",
            "[  0.05%   0.086 s   1000x |    0.048     0.086    10.890 ms] generate_point_attributes_in_camera_plane_c92_0_kernel_1_range_for\n",
            "[  0.03%   0.047 s   1000x |    0.011     0.047     5.662 ms] gaussian_point_rasterisation_backward_c96_0_kernel_2_serial\n",
            "[  0.03%   0.045 s   1000x |    0.010     0.045     7.975 ms] filter_point_in_camera_c82_0_kernel_0_serial\n",
            "[  0.02%   0.041 s   1000x |    0.008     0.041    12.043 ms] generate_point_attributes_in_camera_plane_c92_0_kernel_0_serial\n",
            "[  0.02%   0.041 s   1000x |    0.008     0.041     9.025 ms] gaussian_point_rasterisation_c94_0_kernel_0_serial\n",
            "[  0.02%   0.035 s   1000x |    0.024     0.035     1.959 ms] find_tile_start_and_end_c90_0_kernel_1_range_for\n",
            "[  0.02%   0.033 s   1000x |    0.007     0.033     6.838 ms] generate_num_overlap_tiles_c86_0_kernel_0_serial\n",
            "[  0.02%   0.027 s   1000x |    0.021     0.027     1.653 ms] filter_point_in_camera_c82_0_kernel_1_range_for\n",
            "[  0.02%   0.025 s   1000x |    0.008     0.025     4.053 ms] generate_point_sort_key_by_num_overlap_tiles_c88_0_kernel_0_serial\n",
            "[  0.01%   0.013 s   1000x |    0.003     0.013     6.897 ms] find_tile_start_and_end_c90_0_kernel_0_serial\n",
            "[  0.01%   0.009 s   1000x |    0.004     0.009     0.151 ms] find_tile_start_and_end_c90_0_kernel_2_serial\n",
            "[  0.00%   0.005 s   1000x |    0.004     0.005     0.059 ms] gaussian_point_rasterisation_backward_c96_0_kernel_0_serial\n",
            "[  0.00%   0.000 s     20x |    0.009     0.017     0.025 ms] sample_from_point_c100_0_kernel_0_serial\n",
            "[  0.00%   0.000 s     20x |    0.006     0.014     0.027 ms] sample_from_point_c100_0_kernel_1_range_for\n",
            "-------------------------------------------------------------------------\n",
            "[100.00%] Total execution time: 168.011 s   number of results: 19\n",
            "=========================================================================\n",
            "=========================================================================\n",
            "Kernel Profiler(count, default) @ CUDA on Tesla T4\n",
            "=========================================================================\n",
            "[      %     total   count |      min       avg       max   ] Kernel name\n",
            "-------------------------------------------------------------------------\n",
            "-------------------------------------------------------------------------\n",
            "[100.00%] Total execution time:   0.000 s   number of results: 0\n",
            "=========================================================================\n",
            "\n",
            "  0% 0/22 [00:00<?, ?it/s]\u001b[A\n",
            "  5% 1/22 [00:08<03:06,  8.86s/it]\u001b[A\n",
            "  9% 2/22 [00:14<02:16,  6.82s/it]\u001b[A\n",
            " 14% 3/22 [00:19<01:59,  6.29s/it]\u001b[A\n",
            " 18% 4/22 [00:25<01:51,  6.20s/it]\u001b[A\n",
            " 23% 5/22 [00:31<01:41,  5.95s/it]\u001b[A\n",
            " 27% 6/22 [00:38<01:41,  6.37s/it]\u001b[A\n",
            " 32% 7/22 [00:43<01:26,  5.75s/it]\u001b[A\n",
            " 36% 8/22 [00:46<01:10,  5.00s/it]\u001b[A\n",
            " 41% 9/22 [00:51<01:05,  5.01s/it]\u001b[A\n",
            " 45% 10/22 [00:58<01:05,  5.49s/it]\u001b[A\n",
            " 50% 11/22 [01:04<01:03,  5.81s/it]\u001b[A\n",
            " 55% 12/22 [01:08<00:53,  5.31s/it]\u001b[A\n",
            " 59% 13/22 [01:16<00:54,  6.06s/it]\u001b[A\n",
            " 64% 14/22 [01:24<00:52,  6.55s/it]\u001b[A\n",
            " 68% 15/22 [01:28<00:41,  5.96s/it]\u001b[A\n",
            " 73% 16/22 [01:33<00:33,  5.61s/it]\u001b[A\n",
            " 77% 17/22 [01:37<00:24,  4.96s/it]\u001b[A\n",
            " 82% 18/22 [01:45<00:23,  5.83s/it]\u001b[A\n",
            " 86% 19/22 [01:50<00:17,  5.85s/it]\u001b[A\n",
            " 91% 20/22 [01:55<00:10,  5.44s/it]\u001b[A\n",
            " 95% 21/22 [01:59<00:05,  5.06s/it]\u001b[A\n",
            "100% 22/22 [02:04<00:00,  5.66s/it]\n",
            "=========================================================================\n",
            "Kernel Profiler(count, default) @ CUDA on Tesla T4\n",
            "=========================================================================\n",
            "[      %     total   count |      min       avg       max   ] Kernel name\n",
            "-------------------------------------------------------------------------\n",
            "[ 39.41%   0.407 s     22x |    7.203    18.517    39.442 ms] generate_point_sort_key_by_num_overlap_tiles_c88_0_kernel_1_range_for\n",
            "[ 36.55%   0.378 s     22x |    6.585    17.173    37.321 ms] generate_num_overlap_tiles_c86_0_kernel_1_range_for\n",
            "[ 23.46%   0.243 s     22x |   10.013    11.023    12.827 ms] gaussian_point_rasterisation_c94_0_kernel_1_range_for\n",
            "[  0.21%   0.002 s     22x |    0.089     0.097     0.124 ms] generate_point_attributes_in_camera_plane_c92_0_kernel_1_range_for\n",
            "[  0.08%   0.001 s     22x |    0.033     0.039     0.057 ms] find_tile_start_and_end_c90_0_kernel_1_range_for\n",
            "[  0.08%   0.001 s     22x |    0.036     0.038     0.049 ms] filter_point_in_camera_c82_0_kernel_1_range_for\n",
            "[  0.04%   0.000 s     22x |    0.014     0.019     0.039 ms] filter_point_in_camera_c82_0_kernel_0_serial\n",
            "[  0.03%   0.000 s     22x |    0.013     0.016     0.033 ms] generate_point_attributes_in_camera_plane_c92_0_kernel_0_serial\n",
            "[  0.03%   0.000 s     22x |    0.013     0.015     0.029 ms] generate_point_sort_key_by_num_overlap_tiles_c88_0_kernel_0_serial\n",
            "[  0.03%   0.000 s     22x |    0.012     0.015     0.022 ms] gaussian_point_rasterisation_c94_0_kernel_0_serial\n",
            "[  0.03%   0.000 s     22x |    0.011     0.014     0.027 ms] generate_num_overlap_tiles_c86_0_kernel_0_serial\n",
            "[  0.02%   0.000 s     22x |    0.008     0.010     0.017 ms] find_tile_start_and_end_c90_0_kernel_2_serial\n",
            "[  0.02%   0.000 s     22x |    0.006     0.009     0.018 ms] find_tile_start_and_end_c90_0_kernel_0_serial\n",
            "-------------------------------------------------------------------------\n",
            "[100.00%] Total execution time:   1.034 s   number of results: 13\n",
            "=========================================================================\n",
            " 63% 19026/30001 [2:14:22<43:58,  4.16it/s]/usr/local/lib/python3.10/site-packages/torch/utils/data/dataloader.py:560: UserWarning: This DataLoader will create 4 worker processes in total. Our suggested max number of worker in current system is 2, which is smaller than what this DataLoader is going to create. Please be aware that excessive worker creation might get DataLoader running slow or even freeze, lower the worker number to avoid potential slowness/freeze if necessary.\n",
            "  warnings.warn(_create_warning_msg(\n",
            " 64% 19100/30001 [2:14:44<49:13,  3.69it/s]num_valid_points=27460;\n",
            "num_over_reconstructed: 20, num_under_reconstructed: 78\n",
            "total valid points: 27460 -> 27531, num_densify_points: 98, num_fillable_densify_points: 98\n",
            "num_transparent_points: 17, num_floaters_points: 10\n",
            " 64% 19200/30001 [2:15:14<1:02:45,  2.87it/s]1072 1920\n",
            "num_valid_points=27531;\n",
            "num_over_reconstructed: 19, num_under_reconstructed: 59\n",
            "total valid points: 27531 -> 27557, num_densify_points: 78, num_fillable_densify_points: 78\n",
            "num_transparent_points: 32, num_floaters_points: 20\n",
            " 64% 19300/30001 [2:15:48<41:53,  4.26it/s]num_valid_points=27557;\n",
            "num_over_reconstructed: 29, num_under_reconstructed: 75\n",
            "total valid points: 27557 -> 27620, num_densify_points: 104, num_fillable_densify_points: 104\n",
            "num_transparent_points: 23, num_floaters_points: 18\n",
            " 65% 19400/30001 [2:16:16<43:02,  4.10it/s]1072 1920\n",
            "num_valid_points=27620;\n",
            "num_over_reconstructed: 18, num_under_reconstructed: 63\n",
            "total valid points: 27620 -> 27671, num_densify_points: 81, num_fillable_densify_points: 81\n",
            "num_transparent_points: 25, num_floaters_points: 5\n",
            " 65% 19500/30001 [2:16:55<51:48,  3.38it/s]num_valid_points=27671;\n",
            "num_over_reconstructed: 12, num_under_reconstructed: 65\n",
            "total valid points: 27671 -> 27709, num_densify_points: 77, num_fillable_densify_points: 77\n",
            "num_transparent_points: 32, num_floaters_points: 7\n",
            " 65% 19600/30001 [2:17:24<43:38,  3.97it/s]1072 1920\n",
            "num_valid_points=27709;\n",
            "num_over_reconstructed: 25, num_under_reconstructed: 48\n",
            "total valid points: 27709 -> 27754, num_densify_points: 73, num_fillable_densify_points: 73\n",
            "num_transparent_points: 20, num_floaters_points: 8\n",
            " 66% 19700/30001 [2:18:01<1:40:37,  1.71it/s]num_valid_points=27754;\n",
            "num_over_reconstructed: 25, num_under_reconstructed: 61\n",
            "total valid points: 27754 -> 27812, num_densify_points: 86, num_fillable_densify_points: 86\n",
            "num_transparent_points: 25, num_floaters_points: 3\n",
            " 66% 19800/30001 [2:18:31<46:02,  3.69it/s]1072 1920\n",
            "num_valid_points=27812;\n",
            "num_over_reconstructed: 68, num_under_reconstructed: 65\n",
            "total valid points: 27812 -> 27906, num_densify_points: 133, num_fillable_densify_points: 133\n",
            "num_transparent_points: 21, num_floaters_points: 18\n",
            " 66% 19900/30001 [2:19:06<43:17,  3.89it/s]num_valid_points=27906;\n",
            "num_over_reconstructed: 14, num_under_reconstructed: 65\n",
            "total valid points: 27906 -> 27949, num_densify_points: 79, num_fillable_densify_points: 79\n",
            "num_transparent_points: 27, num_floaters_points: 9\n",
            " 67% 20000/30001 [2:19:36<47:10,  3.53it/s]1072 1920\n",
            "num_valid_points=27949;\n",
            "num_over_reconstructed: 24, num_under_reconstructed: 38\n",
            "total valid points: 27949 -> 27957, num_densify_points: 62, num_fillable_densify_points: 62\n",
            "num_transparent_points: 30, num_floaters_points: 24\n",
            "=========================================================================\n",
            "Kernel Profiler(count, default) @ CUDA on Tesla T4\n",
            "=========================================================================\n",
            "[      %     total   count |      min       avg       max   ] Kernel name\n",
            "-------------------------------------------------------------------------\n",
            "[ 82.81% 139.529 s   1000x |   98.478   139.529   243.288 ms] gaussian_point_rasterisation_backward_c96_0_kernel_1_range_for\n",
            "[  6.87%  11.570 s   1000x |    1.900    11.570    38.840 ms] generate_point_sort_key_by_num_overlap_tiles_c88_0_kernel_1_range_for\n",
            "[  6.58%  11.090 s   1000x |    1.694    11.090    37.058 ms] generate_num_overlap_tiles_c86_0_kernel_1_range_for\n",
            "[  2.47%   4.160 s   1000x |    3.640     4.160    12.619 ms] gaussian_point_rasterisation_c94_0_kernel_1_range_for\n",
            "[  1.03%   1.742 s   1000x |    1.714     1.742     9.064 ms] gaussian_point_rasterisation_backward_c96_0_kernel_3_range_for\n",
            "[  0.05%   0.077 s   1000x |    0.048     0.077     9.095 ms] generate_point_attributes_in_camera_plane_c92_0_kernel_1_range_for\n",
            "[  0.03%   0.054 s   1000x |    0.020     0.054    15.368 ms] filter_point_in_camera_c82_0_kernel_1_range_for\n",
            "[  0.03%   0.048 s   1000x |    0.007     0.048    13.818 ms] generate_num_overlap_tiles_c86_0_kernel_0_serial\n",
            "[  0.03%   0.047 s   1000x |    0.008     0.047     7.277 ms] generate_point_attributes_in_camera_plane_c92_0_kernel_0_serial\n",
            "[  0.03%   0.042 s   1000x |    0.012     0.042     9.143 ms] gaussian_point_rasterisation_backward_c96_0_kernel_2_serial\n",
            "[  0.02%   0.035 s   1000x |    0.008     0.035     9.394 ms] gaussian_point_rasterisation_c94_0_kernel_0_serial\n",
            "[  0.02%   0.034 s   1000x |    0.025     0.034     0.811 ms] find_tile_start_and_end_c90_0_kernel_1_range_for\n",
            "[  0.02%   0.026 s   1000x |    0.009     0.026     5.000 ms] generate_point_sort_key_by_num_overlap_tiles_c88_0_kernel_0_serial\n",
            "[  0.01%   0.025 s   1000x |    0.010     0.025     3.134 ms] filter_point_in_camera_c82_0_kernel_0_serial\n",
            "[  0.01%   0.009 s   1000x |    0.005     0.009     0.045 ms] find_tile_start_and_end_c90_0_kernel_2_serial\n",
            "[  0.00%   0.007 s   1000x |    0.003     0.007     0.762 ms] find_tile_start_and_end_c90_0_kernel_0_serial\n",
            "[  0.00%   0.005 s   1000x |    0.004     0.005     0.031 ms] gaussian_point_rasterisation_backward_c96_0_kernel_0_serial\n",
            "[  0.00%   0.000 s     20x |    0.008     0.016     0.035 ms] sample_from_point_c100_0_kernel_0_serial\n",
            "[  0.00%   0.000 s     20x |    0.006     0.016     0.027 ms] sample_from_point_c100_0_kernel_1_range_for\n",
            "-------------------------------------------------------------------------\n",
            "[100.00%] Total execution time: 168.500 s   number of results: 19\n",
            "=========================================================================\n",
            "=========================================================================\n",
            "Kernel Profiler(count, default) @ CUDA on Tesla T4\n",
            "=========================================================================\n",
            "[      %     total   count |      min       avg       max   ] Kernel name\n",
            "-------------------------------------------------------------------------\n",
            "-------------------------------------------------------------------------\n",
            "[100.00%] Total execution time:   0.000 s   number of results: 0\n",
            "=========================================================================\n",
            "\n",
            "  0% 0/22 [00:00<?, ?it/s]\u001b[A\n",
            "  5% 1/22 [00:10<03:37, 10.37s/it]\u001b[A\n",
            "  9% 2/22 [00:14<02:08,  6.43s/it]\u001b[A\n",
            " 14% 3/22 [00:17<01:38,  5.19s/it]\u001b[A\n",
            " 18% 4/22 [00:22<01:30,  5.04s/it]\u001b[A\n",
            " 23% 5/22 [00:31<01:47,  6.35s/it]\u001b[A\n",
            " 27% 6/22 [00:36<01:35,  5.95s/it]\u001b[A\n",
            " 32% 7/22 [00:40<01:22,  5.49s/it]\u001b[A\n",
            " 36% 8/22 [00:44<01:10,  5.01s/it]\u001b[A\n",
            " 41% 9/22 [00:52<01:13,  5.65s/it]\u001b[A\n",
            " 45% 10/22 [00:57<01:06,  5.51s/it]\u001b[A\n",
            " 50% 11/22 [01:02<01:01,  5.57s/it]\u001b[A\n",
            " 55% 12/22 [01:06<00:49,  4.94s/it]\u001b[A\n",
            " 59% 13/22 [01:10<00:43,  4.83s/it]\u001b[A\n",
            " 64% 14/22 [01:19<00:48,  6.00s/it]\u001b[A\n",
            " 68% 15/22 [01:25<00:41,  5.88s/it]\u001b[A\n",
            " 73% 16/22 [01:30<00:33,  5.55s/it]\u001b[A\n",
            " 77% 17/22 [01:36<00:28,  5.72s/it]\u001b[A\n",
            " 82% 18/22 [01:42<00:23,  5.82s/it]\u001b[A\n",
            " 86% 19/22 [01:49<00:18,  6.27s/it]\u001b[A\n",
            " 91% 20/22 [01:53<00:11,  5.59s/it]\u001b[A\n",
            " 95% 21/22 [01:57<00:05,  5.17s/it]\u001b[A\n",
            "100% 22/22 [02:03<00:00,  5.59s/it]\n",
            "=========================================================================\n",
            "Kernel Profiler(count, default) @ CUDA on Tesla T4\n",
            "=========================================================================\n",
            "[      %     total   count |      min       avg       max   ] Kernel name\n",
            "-------------------------------------------------------------------------\n",
            "[ 43.40%   0.692 s     22x |    5.419    31.437    71.358 ms] generate_point_sort_key_by_num_overlap_tiles_c88_0_kernel_1_range_for\n",
            "[ 41.32%   0.659 s     22x |    4.850    29.934    68.839 ms] generate_num_overlap_tiles_c86_0_kernel_1_range_for\n",
            "[ 14.90%   0.237 s     22x |    7.551    10.793    12.083 ms] gaussian_point_rasterisation_c94_0_kernel_1_range_for\n",
            "[  0.14%   0.002 s     22x |    0.088     0.099     0.133 ms] generate_point_attributes_in_camera_plane_c92_0_kernel_1_range_for\n",
            "[  0.05%   0.001 s     22x |    0.035     0.037     0.048 ms] filter_point_in_camera_c82_0_kernel_1_range_for\n",
            "[  0.05%   0.001 s     22x |    0.029     0.037     0.052 ms] find_tile_start_and_end_c90_0_kernel_1_range_for\n",
            "[  0.03%   0.000 s     22x |    0.014     0.018     0.040 ms] filter_point_in_camera_c82_0_kernel_0_serial\n",
            "[  0.02%   0.000 s     22x |    0.013     0.017     0.054 ms] generate_point_attributes_in_camera_plane_c92_0_kernel_0_serial\n",
            "[  0.02%   0.000 s     22x |    0.013     0.015     0.027 ms] generate_point_sort_key_by_num_overlap_tiles_c88_0_kernel_0_serial\n",
            "[  0.02%   0.000 s     22x |    0.011     0.015     0.030 ms] generate_num_overlap_tiles_c86_0_kernel_0_serial\n",
            "[  0.02%   0.000 s     22x |    0.012     0.014     0.022 ms] gaussian_point_rasterisation_c94_0_kernel_0_serial\n",
            "[  0.01%   0.000 s     22x |    0.008     0.010     0.018 ms] find_tile_start_and_end_c90_0_kernel_2_serial\n",
            "[  0.01%   0.000 s     22x |    0.006     0.009     0.030 ms] find_tile_start_and_end_c90_0_kernel_0_serial\n",
            "-------------------------------------------------------------------------\n",
            "[100.00%] Total execution time:   1.594 s   number of results: 13\n",
            "=========================================================================\n",
            " 67% 20034/30001 [2:22:03<45:26,  3.66it/s]/usr/local/lib/python3.10/site-packages/torch/utils/data/dataloader.py:560: UserWarning: This DataLoader will create 4 worker processes in total. Our suggested max number of worker in current system is 2, which is smaller than what this DataLoader is going to create. Please be aware that excessive worker creation might get DataLoader running slow or even freeze, lower the worker number to avoid potential slowness/freeze if necessary.\n",
            "  warnings.warn(_create_warning_msg(\n",
            " 67% 20100/30001 [2:22:25<47:05,  3.50it/s]num_valid_points=27957;\n",
            "num_over_reconstructed: 13, num_under_reconstructed: 8\n",
            "total valid points: 27957 -> 27809, num_densify_points: 21, num_fillable_densify_points: 21\n",
            "num_transparent_points: 156, num_floaters_points: 13\n",
            " 67% 20200/30001 [2:22:56<41:04,  3.98it/s]1072 1920\n",
            "num_valid_points=27809;\n",
            "num_over_reconstructed: 12, num_under_reconstructed: 12\n",
            "total valid points: 27809 -> 27731, num_densify_points: 24, num_fillable_densify_points: 24\n",
            "num_transparent_points: 94, num_floaters_points: 8\n",
            " 68% 20300/30001 [2:23:36<48:00,  3.37it/s]num_valid_points=27731;\n",
            "num_over_reconstructed: 28, num_under_reconstructed: 9\n",
            "total valid points: 27731 -> 27690, num_densify_points: 37, num_fillable_densify_points: 37\n",
            "num_transparent_points: 64, num_floaters_points: 14\n",
            " 68% 20400/30001 [2:24:07<40:30,  3.95it/s]1072 1920\n",
            "num_valid_points=27690;\n",
            "num_over_reconstructed: 26, num_under_reconstructed: 7\n",
            "total valid points: 27690 -> 27643, num_densify_points: 33, num_fillable_densify_points: 33\n",
            "num_transparent_points: 78, num_floaters_points: 2\n",
            " 68% 20500/30001 [2:24:45<1:11:19,  2.22it/s]num_valid_points=27643;\n",
            "num_over_reconstructed: 13, num_under_reconstructed: 11\n",
            "total valid points: 27643 -> 27577, num_densify_points: 24, num_fillable_densify_points: 24\n",
            "num_transparent_points: 84, num_floaters_points: 6\n",
            " 69% 20600/30001 [2:25:17<46:07,  3.40it/s]1072 1920\n",
            "num_valid_points=27577;\n",
            "num_over_reconstructed: 24, num_under_reconstructed: 30\n",
            "total valid points: 27577 -> 27541, num_densify_points: 54, num_fillable_densify_points: 54\n",
            "num_transparent_points: 75, num_floaters_points: 15\n",
            " 69% 20700/30001 [2:25:52<41:42,  3.72it/s]num_valid_points=27541;\n",
            "num_over_reconstructed: 19, num_under_reconstructed: 37\n",
            "total valid points: 27541 -> 27512, num_densify_points: 56, num_fillable_densify_points: 56\n",
            "num_transparent_points: 80, num_floaters_points: 5\n",
            " 69% 20800/30001 [2:26:25<48:08,  3.18it/s]1072 1920\n",
            "num_valid_points=27512;\n",
            "num_over_reconstructed: 23, num_under_reconstructed: 15\n",
            "total valid points: 27512 -> 27448, num_densify_points: 38, num_fillable_densify_points: 38\n",
            "num_transparent_points: 76, num_floaters_points: 26\n",
            " 70% 20900/30001 [2:27:01<40:06,  3.78it/s]num_valid_points=27448;\n",
            "num_over_reconstructed: 35, num_under_reconstructed: 38\n",
            "total valid points: 27448 -> 27444, num_densify_points: 73, num_fillable_densify_points: 73\n",
            "num_transparent_points: 71, num_floaters_points: 6\n",
            " 70% 21000/30001 [2:27:32<40:06,  3.74it/s]1072 1920\n",
            "num_valid_points=27444;\n",
            "num_over_reconstructed: 14, num_under_reconstructed: 9\n",
            "total valid points: 27444 -> 27365, num_densify_points: 23, num_fillable_densify_points: 23\n",
            "num_transparent_points: 92, num_floaters_points: 10\n",
            "=========================================================================\n",
            "Kernel Profiler(count, default) @ CUDA on Tesla T4\n",
            "=========================================================================\n",
            "[      %     total   count |      min       avg       max   ] Kernel name\n",
            "-------------------------------------------------------------------------\n",
            "[ 80.60% 155.866 s   1000x |  103.858   155.866   271.551 ms] gaussian_point_rasterisation_backward_c96_0_kernel_1_range_for\n",
            "[  8.13%  15.730 s   1000x |    1.805    15.730    70.767 ms] generate_point_sort_key_by_num_overlap_tiles_c88_0_kernel_1_range_for\n",
            "[  7.88%  15.239 s   1000x |    1.686    15.239    68.526 ms] generate_num_overlap_tiles_c86_0_kernel_1_range_for\n",
            "[  2.32%   4.492 s   1000x |    3.883     4.492    11.985 ms] gaussian_point_rasterisation_c94_0_kernel_1_range_for\n",
            "[  0.90%   1.734 s   1000x |    1.716     1.734     1.892 ms] gaussian_point_rasterisation_backward_c96_0_kernel_3_range_for\n",
            "[  0.03%   0.055 s   1000x |    0.049     0.055     0.627 ms] generate_point_attributes_in_camera_plane_c92_0_kernel_1_range_for\n",
            "[  0.02%   0.039 s   1000x |    0.008     0.039     6.933 ms] gaussian_point_rasterisation_c94_0_kernel_0_serial\n",
            "[  0.02%   0.039 s   1000x |    0.012     0.039     9.069 ms] gaussian_point_rasterisation_backward_c96_0_kernel_2_serial\n",
            "[  0.02%   0.035 s   1000x |    0.025     0.035     1.882 ms] find_tile_start_and_end_c90_0_kernel_1_range_for\n",
            "[  0.02%   0.031 s   1000x |    0.010     0.031     9.325 ms] filter_point_in_camera_c82_0_kernel_0_serial\n",
            "[  0.01%   0.027 s   1000x |    0.021     0.027     1.141 ms] filter_point_in_camera_c82_0_kernel_1_range_for\n",
            "[  0.01%   0.025 s   1000x |    0.009     0.025    10.003 ms] generate_point_sort_key_by_num_overlap_tiles_c88_0_kernel_0_serial\n",
            "[  0.01%   0.023 s   1000x |    0.007     0.023     6.386 ms] generate_num_overlap_tiles_c86_0_kernel_0_serial\n",
            "[  0.01%   0.022 s   1000x |    0.008     0.022     3.262 ms] generate_point_attributes_in_camera_plane_c92_0_kernel_0_serial\n",
            "[  0.00%   0.009 s   1000x |    0.005     0.009     0.119 ms] find_tile_start_and_end_c90_0_kernel_2_serial\n",
            "[  0.00%   0.006 s   1000x |    0.003     0.006     0.038 ms] find_tile_start_and_end_c90_0_kernel_0_serial\n",
            "[  0.00%   0.005 s   1000x |    0.004     0.005     0.024 ms] gaussian_point_rasterisation_backward_c96_0_kernel_0_serial\n",
            "[  0.00%   0.000 s     20x |    0.010     0.016     0.023 ms] sample_from_point_c100_0_kernel_0_serial\n",
            "[  0.00%   0.000 s     20x |    0.007     0.015     0.033 ms] sample_from_point_c100_0_kernel_1_range_for\n",
            "-------------------------------------------------------------------------\n",
            "[100.00%] Total execution time: 193.378 s   number of results: 19\n",
            "=========================================================================\n",
            "=========================================================================\n",
            "Kernel Profiler(count, default) @ CUDA on Tesla T4\n",
            "=========================================================================\n",
            "[      %     total   count |      min       avg       max   ] Kernel name\n",
            "-------------------------------------------------------------------------\n",
            "-------------------------------------------------------------------------\n",
            "[100.00%] Total execution time:   0.000 s   number of results: 0\n",
            "=========================================================================\n",
            "\n",
            "  0% 0/22 [00:00<?, ?it/s]\u001b[A\n",
            "  5% 1/22 [00:06<02:12,  6.31s/it]\u001b[A\n",
            "  9% 2/22 [00:10<01:35,  4.78s/it]\u001b[A\n",
            " 14% 3/22 [00:13<01:21,  4.28s/it]\u001b[A\n",
            " 18% 4/22 [00:18<01:23,  4.66s/it]\u001b[A\n",
            " 23% 5/22 [00:24<01:22,  4.85s/it]\u001b[A\n",
            " 27% 6/22 [00:29<01:18,  4.92s/it]\u001b[A\n",
            " 32% 7/22 [00:33<01:11,  4.74s/it]\u001b[A\n",
            " 36% 8/22 [00:37<01:02,  4.43s/it]\u001b[A\n",
            " 41% 9/22 [00:43<01:06,  5.12s/it]\u001b[A\n",
            " 45% 10/22 [00:48<01:00,  5.08s/it]\u001b[A\n",
            " 50% 11/22 [00:55<00:59,  5.44s/it]\u001b[A\n",
            " 55% 12/22 [00:58<00:48,  4.82s/it]\u001b[A\n",
            " 59% 13/22 [01:06<00:50,  5.62s/it]\u001b[A\n",
            " 64% 14/22 [01:13<00:48,  6.02s/it]\u001b[A\n",
            " 68% 15/22 [01:19<00:44,  6.31s/it]\u001b[A\n",
            " 73% 16/22 [01:24<00:35,  5.89s/it]\u001b[A\n",
            " 77% 17/22 [01:28<00:25,  5.10s/it]\u001b[A\n",
            " 82% 18/22 [01:34<00:21,  5.43s/it]\u001b[A\n",
            " 86% 19/22 [01:44<00:20,  6.88s/it]\u001b[A\n",
            " 91% 20/22 [01:51<00:13,  6.75s/it]\u001b[A\n",
            " 95% 21/22 [01:55<00:06,  6.11s/it]\u001b[A\n",
            "100% 22/22 [02:01<00:00,  5.52s/it]\n",
            "=========================================================================\n",
            "Kernel Profiler(count, default) @ CUDA on Tesla T4\n",
            "=========================================================================\n",
            "[      %     total   count |      min       avg       max   ] Kernel name\n",
            "-------------------------------------------------------------------------\n",
            "[ 45.30%   0.946 s     22x |    5.214    42.992   134.748 ms] generate_num_overlap_tiles_c86_0_kernel_1_range_for\n",
            "[ 42.90%   0.896 s     22x |    5.685    40.714   112.901 ms] generate_point_sort_key_by_num_overlap_tiles_c88_0_kernel_1_range_for\n",
            "[ 11.51%   0.240 s     22x |    5.302    10.920    13.468 ms] gaussian_point_rasterisation_c94_0_kernel_1_range_for\n",
            "[  0.10%   0.002 s     22x |    0.088     0.098     0.115 ms] generate_point_attributes_in_camera_plane_c92_0_kernel_1_range_for\n",
            "[  0.04%   0.001 s     22x |    0.031     0.040     0.050 ms] find_tile_start_and_end_c90_0_kernel_1_range_for\n",
            "[  0.04%   0.001 s     22x |    0.036     0.039     0.061 ms] filter_point_in_camera_c82_0_kernel_1_range_for\n",
            "[  0.02%   0.000 s     22x |    0.015     0.019     0.037 ms] filter_point_in_camera_c82_0_kernel_0_serial\n",
            "[  0.02%   0.000 s     22x |    0.014     0.017     0.030 ms] generate_point_attributes_in_camera_plane_c92_0_kernel_0_serial\n",
            "[  0.02%   0.000 s     22x |    0.013     0.016     0.027 ms] generate_point_sort_key_by_num_overlap_tiles_c88_0_kernel_0_serial\n",
            "[  0.02%   0.000 s     22x |    0.012     0.015     0.031 ms] generate_num_overlap_tiles_c86_0_kernel_0_serial\n",
            "[  0.01%   0.000 s     22x |    0.010     0.014     0.023 ms] gaussian_point_rasterisation_c94_0_kernel_0_serial\n",
            "[  0.01%   0.000 s     22x |    0.006     0.010     0.020 ms] find_tile_start_and_end_c90_0_kernel_2_serial\n",
            "[  0.01%   0.000 s     22x |    0.006     0.009     0.028 ms] find_tile_start_and_end_c90_0_kernel_0_serial\n",
            "-------------------------------------------------------------------------\n",
            "[100.00%] Total execution time:   2.088 s   number of results: 13\n",
            "=========================================================================\n",
            " 70% 21042/30001 [2:29:54<40:37,  3.68it/s]/usr/local/lib/python3.10/site-packages/torch/utils/data/dataloader.py:560: UserWarning: This DataLoader will create 4 worker processes in total. Our suggested max number of worker in current system is 2, which is smaller than what this DataLoader is going to create. Please be aware that excessive worker creation might get DataLoader running slow or even freeze, lower the worker number to avoid potential slowness/freeze if necessary.\n",
            "  warnings.warn(_create_warning_msg(\n",
            " 70% 21100/30001 [2:30:14<44:27,  3.34it/s]num_valid_points=27365;\n",
            "num_over_reconstructed: 7, num_under_reconstructed: 38\n",
            "total valid points: 27365 -> 27287, num_densify_points: 45, num_fillable_densify_points: 45\n",
            "num_transparent_points: 110, num_floaters_points: 13\n",
            " 71% 21200/30001 [2:30:44<39:39,  3.70it/s]1072 1920\n",
            "num_valid_points=27287;\n",
            "num_over_reconstructed: 11, num_under_reconstructed: 32\n",
            "total valid points: 27287 -> 27241, num_densify_points: 43, num_fillable_densify_points: 43\n",
            "num_transparent_points: 76, num_floaters_points: 13\n",
            " 71% 21201/30001 [2:30:49<3:34:10,  1.46s/it]"
          ]
        }
      ]
    },
    {
      "cell_type": "markdown",
      "source": [
        "## Run the following code to show the tensorboard.\n",
        "Note: replace the LOG_PATH to your log path."
      ],
      "metadata": {
        "id": "RO-Y1CNcZ8t9"
      }
    },
    {
      "cell_type": "code",
      "source": [
        "from google.colab import drive\n",
        "from tensorboard import notebook\n",
        "\n",
        "LOG_PATH = '/content/drive/MyDrive/AI/taichi_3d_gaussian_splatting/logs/boots_super_sparse_experiment_1'\n",
        "\n",
        "# Open TensorBoard inside colab\n",
        "%load_ext tensorboard\n",
        "notebook.start(\"--logdir \" + LOG_PATH)\n",
        "notebook.display(port=6006, height=800)"
      ],
      "metadata": {
        "id": "GFAt5F-ndNnP"
      },
      "execution_count": 7,
      "outputs": []
    },
    {
      "cell_type": "code",
      "source": [],
      "metadata": {
        "id": "SB3cG3qfXcYN"
      },
      "execution_count": null,
      "outputs": []
    }
  ]
}