ebay-ml-lister/Shoe Classifier-Copy1.ipynb

{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 1,
   "id": "572dc7fb",
   "metadata": {},
   "outputs": [],
   "source": [
    "from matplotlib import pyplot as plt\n",
    "from matplotlib.image import imread\n",
    "import pandas as pd\n",
    "from collections import Counter\n",
    "import json\n",
    "import os\n",
    "import re\n",
    "import tempfile\n",
    "import numpy as np\n",
    "from os.path import exists\n",
    "from imblearn.under_sampling import RandomUnderSampler\n",
    "from PIL import ImageFile\n",
    "import sklearn as sk\n",
    "from sklearn.model_selection import train_test_split, StratifiedShuffleSplit\n",
    "import tensorflow as tf\n",
    "import tensorflow.keras\n",
    "from tensorflow.keras.preprocessing.image import ImageDataGenerator\n",
    "from tensorflow.keras.layers import Conv2D, MaxPooling2D, Dense, Dropout, Flatten, Activation\n",
    "from tensorflow.keras.models import Sequential\n",
    "from tensorflow.keras.optimizers import Adam\n",
    "# custom modules\n",
    "import image_faults\n",
    "\n",
    "ImageFile.LOAD_TRUNCATED_IMAGES = True"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "metadata": {},
   "outputs": [],
   "source": [
    "def add_regularization(model, regularizer=tf.keras.regularizers.l2(0.0001)):\n",
    "\n",
    "    if not isinstance(regularizer, tf.keras.regularizers.Regularizer):\n",
    "      print(\"Regularizer must be a subclass of tf.keras.regularizers.Regularizer\")\n",
    "      return model\n",
    "\n",
    "    for layer in model.layers:\n",
    "        for attr in ['kernel_regularizer']:\n",
    "            if hasattr(layer, attr):\n",
    "              setattr(layer, attr, regularizer)\n",
    "\n",
    "    # When we change the layers attributes, the change only happens in the model config file\n",
    "    model_json = model.to_json()\n",
    "\n",
    "    # Save the weights before reloading the model.\n",
    "    tmp_weights_path = os.path.join(tempfile.gettempdir(), 'tmp_weights.h5')\n",
    "    model.save_weights(tmp_weights_path)\n",
    "\n",
    "    # load the model from the config\n",
    "    model = tf.keras.models.model_from_json(model_json)\n",
    "    \n",
    "    # Reload the model weights\n",
    "    model.load_weights(tmp_weights_path, by_name=True)\n",
    "    return model"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "id": "a5c72863",
   "metadata": {},
   "outputs": [],
   "source": [
    "# image_faults.faulty_images() # removes faulty images\n",
    "df = pd.read_csv('expanded_class.csv', index_col=[0], low_memory=False)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "id": "1057a442",
   "metadata": {
    "scrolled": true
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "{source:target} dictionary created @ /tf/training_images\n"
     ]
    }
   ],
   "source": [
    "def dict_pics():\n",
    "    target_dir = os.getcwd() + os.sep + \"training_images\"\n",
    "    with open('temp_pics_source_list.txt') as f:\n",
    "        temp_pics_source_list = json.load(f)\n",
    "    dict_pics = {k:target_dir + os.sep + re.search(r'[^/]+(?=/\\$_|.jpg)', k, re.IGNORECASE).group() + '.jpg' for k in temp_pics_source_list}\n",
    "    print(\"{source:target} dictionary created @ \" + target_dir)\n",
    "    return dict_pics\n",
    "\n",
    "dict_pics = dict_pics()\n",
    "blah = pd.Series(df.PictureURL)\n",
    "df = df.drop(labels=['PictureURL'], axis=1)\n",
    "blah = blah.apply(lambda x: dict_pics[x])\n",
    "df = pd.concat([blah, df],axis=1)\n",
    "df = df.groupby('PrimaryCategoryID').filter(lambda x: len(x)>25) # removes cat outliers\n",
    "# removes non-existent image paths"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "id": "7a6146e6",
   "metadata": {},
   "outputs": [],
   "source": [
    "df['PrimaryCategoryID'] = df['PrimaryCategoryID'].astype(str) # pandas thinks ids are ints\n",
    "\n",
    "df=df.sample(frac=1)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "metadata": {},
   "outputs": [],
   "source": [
    "undersample = RandomUnderSampler(sampling_strategy='auto')\n",
    "train, y_under = undersample.fit_resample(df, df['PrimaryCategoryID'])\n",
    "# print(Counter(train['PrimaryCategoryID']))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 7,
   "id": "506aa5cf",
   "metadata": {},
   "outputs": [],
   "source": [
    "train, test = train_test_split(train, test_size=0.1, random_state=42)\n",
    "# stratify=train['PrimaryCategoryID']\n",
    "# train['PrimaryCategoryID'].value_counts()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 8,
   "id": "4d72eb90",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Found 5110 validated image filenames belonging to 13 classes.\n",
      "Found 1277 validated image filenames belonging to 13 classes.\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "/usr/local/lib/python3.8/dist-packages/keras_preprocessing/image/dataframe_iterator.py:279: UserWarning: Found 1 invalid image filename(s) in x_col=\"PictureURL\". These filename(s) will be ignored.\n",
      "  warnings.warn(\n"
     ]
    }
   ],
   "source": [
    "datagen = ImageDataGenerator(rescale=1./255., \n",
    "                             validation_split=.2,\n",
    "                             #samplewise_std_normalization=True,\n",
    "                             #horizontal_flip= True,\n",
    "                             #vertical_flip= True,\n",
    "                             #width_shift_range= 0.2,\n",
    "                             #height_shift_range= 0.2,\n",
    "                             #rotation_range= 90,\n",
    "                             preprocessing_function=tf.keras.applications.vgg16.preprocess_input)\n",
    "train_generator=datagen.flow_from_dataframe(\n",
    "    dataframe=train[:len(train)],\n",
    "    directory='./training_images',\n",
    "    x_col='PictureURL',\n",
    "    y_col='PrimaryCategoryID',\n",
    "    batch_size=32,\n",
    "    seed=42,\n",
    "    shuffle=True,\n",
    "    target_size=(224,224),\n",
    "    subset='training'\n",
    "    )\n",
    "validation_generator=datagen.flow_from_dataframe(\n",
    "    dataframe=train[:len(train)], # is using train right?\n",
    "    directory='./training_images',\n",
    "    x_col='PictureURL',\n",
    "    y_col='PrimaryCategoryID',\n",
    "    batch_size=32,\n",
    "    seed=42,\n",
    "    shuffle=True,\n",
    "    target_size=(224,224),\n",
    "    subset='validation'\n",
    "    )"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 9,
   "id": "7b70f37f",
   "metadata": {},
   "outputs": [],
   "source": [
    "imgs, labels = next(train_generator)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 10,
   "id": "1ed54bf5",
   "metadata": {},
   "outputs": [],
   "source": [
    "def plotImages(images_arr):\n",
    "    fig, axes = plt.subplots(1, 10, figsize=(20,20))\n",
    "    axes = axes.flatten()\n",
    "    for img, ax in zip( images_arr, axes):\n",
    "        ax.imshow(img)\n",
    "        ax.axis('off')\n",
    "    plt.tight_layout()\n",
    "    plt.show()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 11,
   "id": "85934565",
   "metadata": {},
   "outputs": [],
   "source": [
    "#plotImages(imgs)\n",
    "#print(labels)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 12,
   "id": "6322bcad",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "1\n"
     ]
    }
   ],
   "source": [
    "physical_devices = tf.config.list_physical_devices('GPU')\n",
    "print(len(physical_devices))\n",
    "tf.config.experimental.set_memory_growth(physical_devices[0], True)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 13,
   "id": "07fd25c6",
   "metadata": {},
   "outputs": [],
   "source": [
    "# see https://www.kaggle.com/dmitrypukhov/cnn-with-imagedatagenerator-flow-from-dataframe for train/test/val split \n",
    "# example\n",
    "\n",
    "# may need to either create a test dataset from the original dataset or just download a new one"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 14,
   "id": "b31af79e",
   "metadata": {},
   "outputs": [],
   "source": [
    "vgg19_model = tf.keras.applications.vgg16.VGG16(weights='imagenet')\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 15,
   "id": "fe06f2bf",
   "metadata": {},
   "outputs": [],
   "source": [
    "model = Sequential()\n",
    "for layer in vgg19_model.layers[:-1]:\n",
    "    model.add(layer)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 21,
   "id": "7d3cc82c",
   "metadata": {},
   "outputs": [],
   "source": [
    "for layer in model.layers:\n",
    "    layer.trainable = True"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 22,
   "id": "ea620129",
   "metadata": {},
   "outputs": [],
   "source": [
    "#model.add(Dropout(.5))\n",
    "#model.add(Dense(64, activation='softmax'))\n",
    "# model.add(Dropout(.25))\n",
    "model.add(Dense(units=13, activation='softmax'))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 23,
   "id": "c774d787",
   "metadata": {
    "scrolled": true
   },
   "outputs": [],
   "source": [
    "model = add_regularization(model)\n",
    "#model.summary()\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 24,
   "id": "fd5d1246",
   "metadata": {},
   "outputs": [],
   "source": [
    "model.compile(optimizer=Adam(learning_rate=1e-5), loss='categorical_crossentropy',\n",
    "              metrics=['accuracy'])\n",
    "# sparse_categorical_crossentropy"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 25,
   "id": "9cd2ba27",
   "metadata": {
    "scrolled": false
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Epoch 1/30\n",
      "160/160 [==============================] - 59s 360ms/step - loss: 2.7627 - accuracy: 0.1125 - val_loss: 2.7406 - val_accuracy: 0.1237\n",
      "Epoch 2/30\n",
      "160/160 [==============================] - 56s 351ms/step - loss: 2.7151 - accuracy: 0.1399 - val_loss: 2.7219 - val_accuracy: 0.1402\n",
      "Epoch 3/30\n",
      "160/160 [==============================] - 56s 351ms/step - loss: 2.6875 - accuracy: 0.1566 - val_loss: 2.6897 - val_accuracy: 0.1629\n",
      "Epoch 4/30\n",
      "160/160 [==============================] - 56s 353ms/step - loss: 2.6820 - accuracy: 0.1726 - val_loss: 2.6867 - val_accuracy: 0.1684\n",
      "Epoch 5/30\n",
      "160/160 [==============================] - 57s 355ms/step - loss: 2.6579 - accuracy: 0.1771 - val_loss: 2.6919 - val_accuracy: 0.1558\n",
      "Epoch 6/30\n",
      "160/160 [==============================] - 56s 353ms/step - loss: 2.6361 - accuracy: 0.1994 - val_loss: 2.6813 - val_accuracy: 0.1832\n",
      "Epoch 7/30\n",
      "160/160 [==============================] - 56s 352ms/step - loss: 2.6196 - accuracy: 0.2084 - val_loss: 2.6592 - val_accuracy: 0.1950\n",
      "Epoch 8/30\n",
      "160/160 [==============================] - 57s 353ms/step - loss: 2.6031 - accuracy: 0.2172 - val_loss: 2.6693 - val_accuracy: 0.1770\n",
      "Epoch 9/30\n",
      "160/160 [==============================] - 57s 355ms/step - loss: 2.5878 - accuracy: 0.2274 - val_loss: 2.6543 - val_accuracy: 0.2091\n",
      "Epoch 10/30\n",
      "160/160 [==============================] - 56s 350ms/step - loss: 2.5687 - accuracy: 0.2450 - val_loss: 2.6551 - val_accuracy: 0.1942\n",
      "Epoch 11/30\n",
      "160/160 [==============================] - 57s 354ms/step - loss: 2.5543 - accuracy: 0.2568 - val_loss: 2.6591 - val_accuracy: 0.2020\n",
      "Epoch 12/30\n",
      "160/160 [==============================] - 56s 352ms/step - loss: 2.5403 - accuracy: 0.2685 - val_loss: 2.6513 - val_accuracy: 0.1973\n",
      "Epoch 13/30\n",
      "160/160 [==============================] - 56s 352ms/step - loss: 2.5311 - accuracy: 0.2695 - val_loss: 2.6445 - val_accuracy: 0.2060\n",
      "Epoch 14/30\n",
      "160/160 [==============================] - 56s 351ms/step - loss: 2.5217 - accuracy: 0.2775 - val_loss: 2.6476 - val_accuracy: 0.2044\n",
      "Epoch 15/30\n",
      "160/160 [==============================] - 56s 351ms/step - loss: 2.5147 - accuracy: 0.2830 - val_loss: 2.6419 - val_accuracy: 0.2036\n",
      "Epoch 16/30\n",
      "160/160 [==============================] - 56s 351ms/step - loss: 2.5084 - accuracy: 0.2851 - val_loss: 2.6396 - val_accuracy: 0.2200\n",
      "Epoch 17/30\n",
      "160/160 [==============================] - 56s 348ms/step - loss: 2.5025 - accuracy: 0.2879 - val_loss: 2.6463 - val_accuracy: 0.2302\n",
      "Epoch 18/30\n",
      "160/160 [==============================] - 56s 350ms/step - loss: 2.4971 - accuracy: 0.2918 - val_loss: 2.6346 - val_accuracy: 0.2208\n",
      "Epoch 19/30\n",
      "160/160 [==============================] - 56s 353ms/step - loss: 2.4924 - accuracy: 0.2967 - val_loss: 2.6366 - val_accuracy: 0.2208\n",
      "Epoch 20/30\n",
      "160/160 [==============================] - 57s 354ms/step - loss: 2.4882 - accuracy: 0.2988 - val_loss: 2.6317 - val_accuracy: 0.2271\n",
      "Epoch 21/30\n",
      "160/160 [==============================] - 56s 349ms/step - loss: 2.4854 - accuracy: 0.3004 - val_loss: 2.6431 - val_accuracy: 0.2240\n",
      "Epoch 22/30\n",
      "160/160 [==============================] - 56s 352ms/step - loss: 2.4784 - accuracy: 0.3068 - val_loss: 2.6345 - val_accuracy: 0.2114\n",
      "Epoch 23/30\n",
      "160/160 [==============================] - 57s 354ms/step - loss: 2.4722 - accuracy: 0.3106 - val_loss: 2.6276 - val_accuracy: 0.2294\n",
      "Epoch 24/30\n",
      "160/160 [==============================] - 57s 354ms/step - loss: 2.4687 - accuracy: 0.3100 - val_loss: 2.6383 - val_accuracy: 0.2177\n",
      "Epoch 25/30\n",
      "160/160 [==============================] - 57s 354ms/step - loss: 2.4649 - accuracy: 0.3108 - val_loss: 2.6322 - val_accuracy: 0.2122\n",
      "Epoch 26/30\n",
      "160/160 [==============================] - 57s 354ms/step - loss: 2.4644 - accuracy: 0.3141 - val_loss: 2.6243 - val_accuracy: 0.2247\n",
      "Epoch 27/30\n",
      "160/160 [==============================] - 56s 352ms/step - loss: 2.4599 - accuracy: 0.3188 - val_loss: 2.6332 - val_accuracy: 0.2138\n",
      "Epoch 28/30\n",
      "160/160 [==============================] - 57s 353ms/step - loss: 2.4550 - accuracy: 0.3229 - val_loss: 2.6287 - val_accuracy: 0.2232\n",
      "Epoch 29/30\n",
      "160/160 [==============================] - 57s 354ms/step - loss: 2.4502 - accuracy: 0.3217 - val_loss: 2.6216 - val_accuracy: 0.2287\n",
      "Epoch 30/30\n",
      "160/160 [==============================] - 56s 351ms/step - loss: 2.4506 - accuracy: 0.3190 - val_loss: 2.6329 - val_accuracy: 0.1793\n"
     ]
    },
    {
     "data": {
      "text/plain": [
       "<keras.callbacks.History at 0x7f7803569ac0>"
      ]
     },
     "execution_count": 25,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "model.fit(x=train_generator,\n",
    "          steps_per_epoch=len(train_generator),\n",
    "          validation_data=validation_generator,\n",
    "          validation_steps=len(validation_generator),\n",
    "          epochs=30,\n",
    "          verbose=1)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "63f791af",
   "metadata": {},
   "outputs": [],
   "source": []
  }
 ],
 "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": "3.8.10"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 5
}