vgg16 pretrained model.ipynb

{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "from keras.applications import VGG16\n",
    "\n",
    "\n",
    "img_rows = 224\n",
    "img_cols = 224 \n",
    "\n",
    "model = VGG16(weights = 'imagenet', \n",
    "                 include_top = False, \n",
    "                 input_shape = (img_rows, img_cols, 3))\n",
    "for (i,layer) in enumerate(model.layers):\n",
    "    print(str(i) + \" \"+ layer.__class__.__name__, layer.trainable)\n",
    "from keras.applications import VGG16\n",
    "\n",
    "\n",
    "img_rows = 224\n",
    "img_cols = 224 \n",
    "\n",
    "\n",
    "model = VGG16(weights = 'imagenet', \n",
    "                 include_top = False, \n",
    "                 input_shape = (img_rows, img_cols, 3))\n",
    "\n",
    "\n",
    "for layer in model.layers:\n",
    "    layer.trainable = False\n",
    "    \n",
    " \n",
    "for (i,layer) in enumerate(model.layers):\n",
    "    print(str(i) + \" \"+ layer.__class__.__name__, layer.trainable)\n",
    "def addinglayer(bottom_model, num_classes):\n",
    "    \"\"\"creates the top or head of the model that will be \n",
    "    placed ontop of the bottom layers\"\"\" \n",
    "    top_model = bottom_model.output\n",
    "    top_model = GlobalAveragePooling2D()(top_model)\n",
    "    top_model = Dense(1024,activation='relu')(top_model)\n",
    "    top_model = Dense(1024,activation='relu')(top_model)\n",
    "    top_model = Dense(512,activation='relu')(top_model)\n",
    "    top_model = Dense(num_classes,activation='softmax')(top_model)\n",
    "    return top_model\n",
    "from keras.models import Sequential\n",
    "from keras.layers import Dense, Dropout, Activation, Flatten, GlobalAveragePooling2D\n",
    "from keras.layers import Conv2D, MaxPooling2D, ZeroPadding2D\n",
    "from keras.layers.normalization import BatchNormalization\n",
    "from keras.models import Model\n",
    "\n",
    "num_classes = 2\n",
    "\n",
    "FC_Head = addinglayer(model, num_classes)\n",
    "\n",
    "modelnew = Model(inputs=model.input, outputs=FC_Head)\n",
    "\n",
    "print(modelnew.summary())\n",
    "from keras.preprocessing.image import ImageDataGenerator\n",
    "\n",
    "train_data_dir = 'faces1/training/'\n",
    "validation_data_dir = 'faces1/testing/'\n",
    "\n",
    "train_datagen = ImageDataGenerator(\n",
    "      rescale=1./255,\n",
    "      rotation_range=20,\n",
    "      width_shift_range=0.2,\n",
    "      height_shift_range=0.2,\n",
    "      horizontal_flip=True,\n",
    "      fill_mode='nearest')\n",
    " \n",
    "validation_datagen = ImageDataGenerator(rescale=1./255)\n",
    " \n",
    "\n",
    "train_batchsize = 16\n",
    "val_batchsize = 10\n",
    " \n",
    "train_generator = train_datagen.flow_from_directory(\n",
    "        train_data_dir,\n",
    "        target_size=(img_rows, img_cols),\n",
    "        batch_size=train_batchsize,\n",
    "        class_mode='categorical')\n",
    " \n",
    "validation_generator = validation_datagen.flow_from_directory(\n",
    "        validation_data_dir,\n",
    "        target_size=(img_rows, img_cols),\n",
    "        batch_size=val_batchsize,class_mode='categorical',\n",
    "        shuffle=False)\n",
    "from keras.optimizers import RMSprop\n",
    "from keras.callbacks import ModelCheckpoint, EarlyStopping\n",
    "                   \n",
    "checkpoint = ModelCheckpoint(\"face_vgg.h5\",\n",
    "                             monitor=\"val_loss\",\n",
    "                             mode=\"min\",\n",
    "                             save_best_only = True,\n",
    "                             verbose=1)\n",
    "\n",
    "earlystop = EarlyStopping(monitor = 'val_loss', \n",
    "                          min_delta = 0, \n",
    "                          patience = 3,\n",
    "                          verbose = 1,\n",
    "                          restore_best_weights = True)\n",
    "\n",
    "\n",
    "callbacks = [earlystop, checkpoint]\n",
    "\n",
    " \n",
    "modelnew.compile(loss = 'categorical_crossentropy',\n",
    "              optimizer = RMSprop(lr = 0.001),\n",
    "              metrics = ['accuracy'])\n",
    "\n",
    "nb_train_samples = 1190\n",
    "nb_validation_samples = 170\n",
    "epochs = 3\n",
    "batch_size = 16\n",
    "\n",
    "history = modelnew.fit_generator(\n",
    "    train_generator,\n",
    "    steps_per_epoch = nb_train_samples // batch_size,\n",
    "    epochs = epochs,\n",
    "    callbacks = callbacks,\n",
    "    validation_data = validation_generator,\n",
    "    validation_steps = nb_validation_samples // batch_size)\n",
    "\n",
    "modelnew.save(\"face_vgg.h5\")"
   ]
  }
 ],
 "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
}