new file: 01_simple-RNN.ipynb

new file: 02_1_simple-RNN-diffrent-sequence-length.ipynb new file: 02_2_simple-RNN-diffrent-sequence-length.ipynb new file: 03_1_Cryptocurrency-predicting.ipynb new file: 03_2_Cryptocurrency-predicting.ipynb new file: 04_simple-CNN-LSTM.ipynb new file: 05-1-video-action-recognition-train-extract-features-with-cnn.ipynb new file: 05-2_video-action-recognition-train-rnn.ipynb new file: 06_analogy-using-embeddings.ipynb new file: 07_text-classification-Emojify.ipynb new file: 08_shahnameh-text-generation-language-model.ipynb new file: 09_add-numbers-with-seq2seq.ipynb new file: 10_Neural-machine-translation-with-attention-for-date-convert.ipynb new file: 11_nmt-with-attention.ipynb new file: 12_image-captioning-with-attention.ipynb new file: TimeDistributed.ipynb new file: final_cnn_lstm.ipynb new file: images/attn_mechanism.png new file: images/attn_model.png new file: images/cosine_sim.png new file: images/data_set.png new file: images/date_attention.png new file: images/date_attention2.png new file: images/embedding1.png new file: images/emojifier-v2.png new file: images/image_1.png new file: images/poorly_trained_model.png new file: images/table.png new file: logo.png new file: nmt_utils.py
Alireza-Akhavan · Dec 2, 2019 · 341ef3e · 341ef3e
1 parent 403bd9f
commit 341ef3e
Show file tree

Hide file tree

Showing 30 changed files with 13,675 additions and 0 deletions.
diff --git a/01_simple-RNN.ipynb b/01_simple-RNN.ipynb
diff --git a/02_1_simple-RNN-diffrent-sequence-length.ipynb b/02_1_simple-RNN-diffrent-sequence-length.ipynb
diff --git a/02_2_simple-RNN-diffrent-sequence-length.ipynb b/02_2_simple-RNN-diffrent-sequence-length.ipynb
diff --git a/03_1_Cryptocurrency-predicting.ipynb b/03_1_Cryptocurrency-predicting.ipynb
diff --git a/03_2_Cryptocurrency-predicting.ipynb b/03_2_Cryptocurrency-predicting.ipynb
diff --git a/04_simple-CNN-LSTM.ipynb b/04_simple-CNN-LSTM.ipynb
diff --git a/05-1-video-action-recognition-train-extract-features-with-cnn.ipynb b/05-1-video-action-recognition-train-extract-features-with-cnn.ipynb
@@ -0,0 +1,326 @@
+{
+ "cells": [
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "<center><div style=\"direction:rtl;font-family:B Lotus, B Nazanin, Tahoma\">به نام خدا</div></center>\n",
+    "<img src=\"./logo.png\" alt=\"class.vision\" style=\"width: 200px;\"/>\n",
+    "<h1><center><div style=\"direction:rtl;font-family:B Lotus, B Nazanin, Tahoma\">طبقه بندی ویدیو با شبکه‌های بازگشتی - استخراج ویژگی</div></center></h1>"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## <div style=\"direction:rtl;text-align:right;font-family:B Lotus, B Nazanin, Tahoma\">مجموعه داده</div>\n",
+    "\n",
+    "\n",
+    "<div style=\"direction:rtl;text-align:right;font-family:Tahoma\">\n",
+    "قبلا  6 کلاس از دیتاست  UCF-101 را به عنوان نمونه انتخاب و فریم‌های ویدیوهای متعلق به این 6 کلاس از این مجموعه داده را استخراج کرده ایم و اطلاعات هر ویدیو نظیر اسم - کلاس و تعداد فریم را در یک فایل متنی قرار داده ایم.\n",
+    "<br/>\n",
+    "    \n",
+    "این 6 کلاس که برای این آموزش آماده شده است را از اینجا دانلود کنید: \n",
+    "</div>\n",
+    "\n",
+    "http://dataset.class.vision/rnn/RNN-Video-6action.zip\n",
+    "\n",
+    "<br/>\n",
+    "<div style=\"direction:rtl;text-align:right;font-family:Tahoma\">\n",
+    "    همچنین\n",
+    "    دیتاست اصلی شامل 101 کلاس مختلف را می‌توانید از لینک زیر دانلود کنید:\n",
+    "</div>\n",
+    "\n",
+    "<strong>UCF-101</strong>\n",
+    "[https://www.crcv.ucf.edu/data/UCF101.php](https://www.crcv.ucf.edu/data/UCF101.php)\n",
+    "\n",
+    "\n",
+    "\n",
+    "\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 1,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "Using TensorFlow backend.\n"
+     ]
+    }
+   ],
+   "source": [
+    "from keras.preprocessing import image\n",
+    "from keras.applications.inception_v3 import InceptionV3, preprocess_input\n",
+    "from keras.models import Model, load_model\n",
+    "from keras.layers import Input\n",
+    "import numpy as np\n",
+    "import os.path\n",
+    "from tqdm import tqdm\n",
+    "import csv\n",
+    "import random\n",
+    "import glob\n",
+    "import os.path\n",
+    "import sys\n",
+    "import operator\n",
+    "import threading\n",
+    "from keras.utils import to_categorical\n",
+    "from keras.preprocessing.image import img_to_array, load_img"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 2,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "seq_length= 40\n",
+    "max_frames = 300\n",
+    "image_shape=(224, 224, 3)\n",
+    "base_path = \"D:/dataset/RNN-Video\"\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 3,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "with open(os.path.join('D:/dataset/RNN-Video/data_file_5class.csv'), 'r') as fin:\n",
+    "    reader = csv.reader(fin)\n",
+    "    data = list(reader)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 4,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "['CricketBowling',\n",
+       " 'CricketShot',\n",
+       " 'FieldHockeyPenalty',\n",
+       " 'HandstandPushups',\n",
+       " 'HandstandWalking',\n",
+       " 'SoccerPenalty']"
+      ]
+     },
+     "execution_count": 4,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "train_path = os.path.join(base_path, 'train')\n",
+    "classes =os.listdir(train_path)\n",
+    "classes = sorted(classes)\n",
+    "classes"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "<div style=\"direction:rtl;text-align:right;font-family:Tahoma\">\n",
+    "    در اینجا آن ویدیوهایی که حداقل 40 فریم و حداکثر 300 فریم دارند را لود می‌کنیم.\n",
+    "</div>"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 6,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "data_clean = []\n",
+    "for item in data:\n",
+    "    if int(item[3]) >= seq_length and int(item[3]) <= max_frames:\n",
+    "        data_clean.append(item)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 7,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "439"
+      ]
+     },
+     "execution_count": 7,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "len(data_clean)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 8,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "def get_n_sample_from_video(sample, seq_length):\n",
+    "    path = os.path.join(base_path, sample[0], sample[1])\n",
+    "    filename = sample[2]\n",
+    "    images = sorted(glob.glob(os.path.join(path, filename + '*jpg')))\n",
+    "\n",
+    "    #Given a list and a size, return a rescaled/samples list. For example,\n",
+    "    #if we want a list of size 5 and we have a list of size 25, return a new\n",
+    "    #list of size five which is every 5th element of the origina list.\n",
+    "    # Get the number to skip between iterations.\n",
+    "    skip = len(images) // seq_length\n",
+    "\n",
+    "    # Build our new output.\n",
+    "    output = [images[i] for i in range(0, len(images), skip)]\n",
+    "\n",
+    "    # Cut off the last one if needed.\n",
+    "    return output[:seq_length]"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 9,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "['train', 'HandstandWalking', 'v_HandstandWalking_g24_c06', '151']"
+      ]
+     },
+     "execution_count": 9,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "data_clean[3]"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 10,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "40"
+      ]
+     },
+     "execution_count": 10,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "len(get_n_sample_from_video(data_clean[3], 40))"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 11,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# Get model with pretrained weights.\n",
+    "base_model = InceptionV3(weights='imagenet', include_top=True)\n",
+    "\n",
+    "# We'll extract features at the final pool layer.\n",
+    "model = Model(inputs=base_model.input,\n",
+    "        outputs=base_model.get_layer('avg_pool').output)\n",
+    "\n",
+    "def model_predict(image_path):\n",
+    "    img = image.load_img(image_path, target_size=(299, 299))\n",
+    "    x = image.img_to_array(img)\n",
+    "    x = np.expand_dims(x, axis=0)\n",
+    "    x = preprocess_input(x)\n",
+    "\n",
+    "    # Get the prediction.\n",
+    "    features = model.predict(x)\n",
+    "    return features[0]"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 12,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "100%|████████████████████████████████████████████████████████████████████████████████| 439/439 [18:31<00:00,  2.85s/it]\n"
+     ]
+    }
+   ],
+   "source": [
+    "os.makedirs('sequences', exist_ok=True)\n",
+    "for video in tqdm(data_clean):\n",
+    "\n",
+    "    # Get the path to the sequence for this video.\n",
+    "    path = os.path.join('sequences', video[2] + '-' + str(seq_length) + \\\n",
+    "        '-features')  # numpy will auto-append .npy\n",
+    "\n",
+    "    # Check if we already have it.\n",
+    "    if os.path.isfile(path + '.npy'):\n",
+    "        continue\n",
+    "\n",
+    "    # Get the frames for this video.\n",
+    "    frames = get_n_sample_from_video(video, seq_length)\n",
+    "\n",
+    "    # Now loop through and extract features to build the sequence.\n",
+    "    sequence = []\n",
+    "    for frame in frames:\n",
+    "        features = model_predict(frame)\n",
+    "        sequence.append(features)\n",
+    "\n",
+    "    # Save the sequence.\n",
+    "    np.save(path, sequence)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "<div class=\"alert alert-block alert-info\">\n",
+    "<div style=\"direction:rtl;text-align:right;font-family:B Lotus, B Nazanin, Tahoma\"> دوره پیشرفته یادگیری عمیق<br>علیرضا اخوان پور<br>  آبان و آذر 1399<br>\n",
+    "</div>\n",
+    "<a href=\"http://class.vision\">Class.Vision</a> - <a href=\"http://AkhavanPour.ir\">AkhavanPour.ir</a> - <a href=\"https://github.com/Alireza-Akhavan/\">GitHub</a>\n",
+    "\n",
+    "</div>"
+   ]
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": "tensorflow",
+   "language": "python",
+   "name": "tensorflow"
+  },
+  "language_info": {
+   "codemirror_mode": {
+    "name": "ipython",
+    "version": 3
+   },
+   "file_extension": ".py",
+   "mimetype": "text/x-python",
+   "name": "python",
+   "nbconvert_exporter": "python",
+   "pygments_lexer": "ipython3",
+   "version": "3.6.8"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 2
+}