Added example jupyter notebook

example/example.ipynb

@@ -0,0 +1,194 @@
+{
+ "cells": [
+  {
+   "cell_type": "code",
+   "execution_count": 1,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from utils.one_hot_encoder import HotEncoder\n",
+    "import  numpy as np\n",
+    "import torch\n",
+    "import skimage\n",
+    "import matplotlib.pyplot as plt\n",
+    "import skimage"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 2,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "Image= skimage.io.imread(\"/home/fatjuicyboi/Downloads/kitti/training/semantic_rgb/000051_10.png\")\n",
+    "encoder= HotEncoder(dir= '/home/fatjuicyboi/Downloads/kitti/training/semantic_rgb', extension=\"png\")\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 3,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "<matplotlib.image.AxesImage at 0x7fd21271a490>"
+      ]
+     },
+     "execution_count": 3,
+     "metadata": {},
+     "output_type": "execute_result"
+    },
+    {
+     "data": {
+      "image/png": "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\n",
+      "text/plain": [
+       "<Figure size 432x288 with 1 Axes>"
+      ]
+     },
+     "metadata": {
+      "needs_background": "light"
+     },
+     "output_type": "display_data"
+    }
+   ],
+   "source": [
+    "skimage.io.imshow(Image)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 4,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "Generating Color Pallte to Hot Encode: 100%|██████████| 200/200 [05:27<00:00,  1.63s/it]\n"
+     ]
+    },
+    {
+     "data": {
+      "text/plain": [
+       "{(107, 142, 35): 1,\n",
+       " (70, 130, 180): 2,\n",
+       " (70, 70, 70): 3,\n",
+       " (153, 153, 153): 4,\n",
+       " (0, 0, 0): 5,\n",
+       " (220, 20, 60): 6,\n",
+       " (0, 0, 230): 7,\n",
+       " (119, 11, 32): 8,\n",
+       " (0, 0, 142): 9,\n",
+       " (111, 74, 0): 10,\n",
+       " (220, 220, 0): 11,\n",
+       " (244, 35, 232): 12,\n",
+       " (128, 64, 128): 13,\n",
+       " (152, 251, 152): 14,\n",
+       " (0, 0, 70): 15,\n",
+       " (255, 0, 0): 16,\n",
+       " (230, 150, 140): 17,\n",
+       " (190, 153, 153): 18,\n",
+       " (250, 170, 30): 19,\n",
+       " (250, 170, 160): 20,\n",
+       " (81, 0, 81): 21,\n",
+       " (180, 165, 180): 22,\n",
+       " (102, 102, 156): 23,\n",
+       " (150, 100, 100): 24,\n",
+       " (0, 60, 100): 25,\n",
+       " (0, 80, 100): 26,\n",
+       " (0, 0, 110): 27,\n",
+       " (0, 0, 90): 28,\n",
+       " (150, 120, 90): 29}"
+      ]
+     },
+     "execution_count": 4,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "color_dict= encoder.gen_colors()\n",
+    "color_dict"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 5,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "onehottt= encoder.PerPixelClassMatrix(Image)\n",
+    "encoded= encoder.HotEncode(onehottt)\n",
+    "ch= encoder.channelSplit(encoded)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 13,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "Lossy conversion from float64 to uint8. Range [0, 1]. Convert image to uint8 prior to saving to suppress this warning.\n",
+      "Lossy conversion from float64 to uint8. Range [0, 1]. Convert image to uint8 prior to saving to suppress this warning.\n",
+      "Lossy conversion from float64 to uint8. Range [0, 1]. Convert image to uint8 prior to saving to suppress this warning.\n",
+      "Lossy conversion from float64 to uint8. Range [0, 1]. Convert image to uint8 prior to saving to suppress this warning.\n",
+      "Lossy conversion from float64 to uint8. Range [0, 1]. Convert image to uint8 prior to saving to suppress this warning.\n",
+      "Lossy conversion from float64 to uint8. Range [0, 1]. Convert image to uint8 prior to saving to suppress this warning.\n",
+      "Lossy conversion from float64 to uint8. Range [0, 1]. Convert image to uint8 prior to saving to suppress this warning.\n",
+      "Lossy conversion from float64 to uint8. Range [0, 1]. Convert image to uint8 prior to saving to suppress this warning.\n",
+      "Lossy conversion from float64 to uint8. Range [0, 1]. Convert image to uint8 prior to saving to suppress this warning.\n",
+      "Lossy conversion from float64 to uint8. Range [0, 1]. Convert image to uint8 prior to saving to suppress this warning.\n",
+      "Lossy conversion from float64 to uint8. Range [0, 1]. Convert image to uint8 prior to saving to suppress this warning.\n",
+      "Lossy conversion from float64 to uint8. Range [0, 1]. Convert image to uint8 prior to saving to suppress this warning.\n",
+      "Lossy conversion from float64 to uint8. Range [0, 1]. Convert image to uint8 prior to saving to suppress this warning.\n",
+      "Lossy conversion from float64 to uint8. Range [0, 1]. Convert image to uint8 prior to saving to suppress this warning.\n",
+      "Lossy conversion from float64 to uint8. Range [0, 1]. Convert image to uint8 prior to saving to suppress this warning.\n",
+      "Lossy conversion from float64 to uint8. Range [0, 1]. Convert image to uint8 prior to saving to suppress this warning.\n",
+      "Lossy conversion from float64 to uint8. Range [0, 1]. Convert image to uint8 prior to saving to suppress this warning.\n",
+      "Lossy conversion from float64 to uint8. Range [0, 1]. Convert image to uint8 prior to saving to suppress this warning.\n",
+      "Lossy conversion from float64 to uint8. Range [0, 1]. Convert image to uint8 prior to saving to suppress this warning.\n",
+      "Lossy conversion from float64 to uint8. Range [0, 1]. Convert image to uint8 prior to saving to suppress this warning.\n",
+      "Lossy conversion from float64 to uint8. Range [0, 1]. Convert image to uint8 prior to saving to suppress this warning.\n",
+      "Lossy conversion from float64 to uint8. Range [0, 1]. Convert image to uint8 prior to saving to suppress this warning.\n",
+      "Lossy conversion from float64 to uint8. Range [0, 1]. Convert image to uint8 prior to saving to suppress this warning.\n",
+      "Lossy conversion from float64 to uint8. Range [0, 1]. Convert image to uint8 prior to saving to suppress this warning.\n",
+      "Lossy conversion from float64 to uint8. Range [0, 1]. Convert image to uint8 prior to saving to suppress this warning.\n",
+      "Lossy conversion from float64 to uint8. Range [0, 1]. Convert image to uint8 prior to saving to suppress this warning.\n",
+      "Lossy conversion from float64 to uint8. Range [0, 1]. Convert image to uint8 prior to saving to suppress this warning.\n",
+      "Lossy conversion from float64 to uint8. Range [0, 1]. Convert image to uint8 prior to saving to suppress this warning.\n",
+      "Lossy conversion from float64 to uint8. Range [0, 1]. Convert image to uint8 prior to saving to suppress this warning.\n"
+     ]
+    }
+   ],
+   "source": [
+    "for _ in range(29):\n",
+    "    skimage.io.imsave(arr= ch[_], fname= str(_)+\".jpeg\")\n"
+   ]
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": "Python 3",
+   "language": "python",
+   "name": "python3"
+  },
+  "language_info": {
+   "codemirror_mode": {
+    "name": "ipython",
+    "version": 3
+   },
+   "file_extension": ".py",
+   "mimetype": "text/x-python",
+   "name": "python",
+   "nbconvert_exporter": "python",
+   "pygments_lexer": "ipython3",
+   "version": "3.7.4"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 2
+}