{"cells":[{"metadata":{"_uuid":"8f2839f25d086af736a60e9eeb907d3b93b6e0e5","_cell_guid":"b1076dfc-b9ad-4769-8c92-a6c4dae69d19","trusted":true},"cell_type":"code","source":"import numpy as np\nimport pandas as pd\nimport matplotlib.pyplot as plt\nimport zipfile\nimport os\nfrom keras.preprocessing.image import load_img, ImageDataGenerator\nfrom keras.utils import to_categorical\n\nwith zipfile.ZipFile('../input/dogs-vs-cats/train.zip', 'r') as Z:\n    Z.extractall('.')","execution_count":null,"outputs":[]},{"metadata":{"_uuid":"d629ff2d2480ee46fbb7e2d37f6b5fab8052498a","_cell_guid":"79c7e3d0-c299-4dcb-8224-4455121ee9b0","trusted":true},"cell_type":"code","source":"os.listdir('./train/')","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"import random\n\nfile_names = list(os.listdir('./train/'))\nsample = random.choice(file_names)\n\nimg = load_img('./train/' + sample)\nplt.imshow(img)\nplt.axis('off')\nprint('Img type of Keras: {}'.format(type(img)))\nprint('Img shape and Mode: {}, {}'.format(img.size, img.mode))","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"# create vgg model\nfrom keras.layers import Conv2D, Dense, Flatten, BatchNormalization, MaxPool2D, Dropout\nfrom keras.models import Sequential\nfrom keras.layers.core import Activation\nfrom keras.optimizers import Nadam\n\ndef create_vgg(image_shape, lr=0.01):\n    model = Sequential()\n    \n    # block1\n    model.add(Conv2D(64, kernel_size=(3,3), padding='same', kernel_initializer='he_normal', input_shape=(image_shape[0], image_shape[1], 3), name='block1_conv1'))\n    model.add(BatchNormalization())\n    model.add(Activation('relu'))\n    model.add(Conv2D(64, kernel_size=(3,3), padding='same', kernel_initializer='he_normal', name='block1_conv2'))\n    model.add(BatchNormalization())\n    model.add(Activation('relu'))\n    model.add(MaxPool2D(pool_size=(2,2)))\n    \n    # block2\n    model.add(Conv2D(128, kernel_size=(3,3), padding='same', kernel_initializer='he_normal', name='block2_conv1'))\n    model.add(BatchNormalization())\n    model.add(Activation('relu'))\n    model.add(Conv2D(128, kernel_size=(3,3), padding='same', kernel_initializer='he_normal', name='block2_conv2'))\n    model.add(BatchNormalization())\n    model.add(Activation('relu'))\n    model.add(MaxPool2D(pool_size=(2,2)))\n    \n    # block3\n    model.add(Conv2D(256, kernel_size=(3,3), padding='same', kernel_initializer='he_normal', name='block3_conv1'))\n    model.add(BatchNormalization())\n    model.add(Activation('relu'))\n    model.add(Conv2D(256, kernel_size=(3,3), padding='same', kernel_initializer='he_normal', name='block3_conv2'))\n    model.add(BatchNormalization())\n    model.add(Activation('relu'))\n    model.add(Conv2D(256, kernel_size=(3,3), padding='same', kernel_initializer='he_normal', name='block3_conv3'))\n    model.add(BatchNormalization())\n    model.add(Activation('relu'))\n    model.add(MaxPool2D(pool_size=(2,2)))\n    \n    # block4\n    model.add(Conv2D(512, kernel_size=(3,3), padding='same', kernel_initializer='he_normal', name='block4_conv1'))\n    model.add(BatchNormalization())\n    model.add(Activation('relu'))\n    model.add(Conv2D(512, kernel_size=(3,3), padding='same', kernel_initializer='he_normal', name='block4_conv2'))\n    model.add(BatchNormalization())\n    model.add(Activation('relu'))\n    model.add(Conv2D(512, kernel_size=(3,3), padding='same', kernel_initializer='he_normal', name='block4_conv3'))\n    model.add(BatchNormalization())\n    model.add(Activation('relu'))\n    model.add(MaxPool2D(pool_size=(2,2)))\n    \n    # block5\n    model.add(Conv2D(512, kernel_size=(3,3), padding='same', kernel_initializer='he_normal', name='block5_conv1'))\n    model.add(BatchNormalization())\n    model.add(Activation('relu'))\n    model.add(Conv2D(512, kernel_size=(3,3), padding='same', kernel_initializer='he_normal', name='block5_conv2'))\n    model.add(BatchNormalization())\n    model.add(Activation('relu'))\n    model.add(Conv2D(512, kernel_size=(3,3), padding='same', kernel_initializer='he_normal', name='block5_conv3'))\n    model.add(BatchNormalization())\n    model.add(Activation('relu'))\n    model.add(MaxPool2D(pool_size=(2,2)))\n              \n    # fully connected \n    model.add(Flatten())\n    model.add(Dense(512))\n    model.add(BatchNormalization())\n    model.add(Activation('relu'))\n    model.add(Dropout(0.5))\n    model.add(Dense(512))\n    model.add(BatchNormalization())\n    model.add(Activation('relu'))\n    model.add(Dropout(0.5))\n    model.add(Dense(2, activation='softmax'))\n    \n    model.compile(loss='categorical_crossentropy', optimizer=Nadam(lr=lr), metrics=['accuracy'])\n    \n    model.summary()\n    \n    return model\n\nmodel = create_vgg(img.size)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"# callbacks\nfrom keras.callbacks import ModelCheckpoint, EarlyStopping, ReduceLROnPlateau\n\ncb_es = EarlyStopping(monitor='val_loss', patience=3)\ncb_mc = ModelCheckpoint('vgg.h5', save_best_only=True)\ncb_rl = ReduceLROnPlateau(monitor='val_loss', factor=0.5, patience=2)\n\ncallbacks = [cb_es, cb_mc, cb_rl]","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"from sklearn.model_selection import train_test_split\n\nfilenames = os.listdir(\"./train/\")\ncategories = []\nfor filename in filenames:\n    category = filename.split('.')[0]\n    if category == 'dog':\n        categories.append('dog')\n    else:\n        categories.append('cat')\n\ndf = pd.DataFrame({\n    'filename': filenames,\n    'category': categories\n})\n\ntrain_df, validate_df = train_test_split(df, test_size=0.20, random_state=42)\ntrain_df = train_df.reset_index(drop=True)\nvalidate_df = validate_df.reset_index(drop=True)\n\ntrain_datagen = ImageDataGenerator(\n    rotation_range=15, # range of random rotation\n    rescale=1./255, # rescale input\n    shear_range=0.1, \n    zoom_range=0.2, \n    horizontal_flip=True, \n    width_shift_range=0.1,\n    height_shift_range=0.1\n)\n\ntrain_generator = train_datagen.flow_from_dataframe(\n    train_df, \n    \"./train/\", \n    x_col='filename',\n    y_col='category',\n    target_size=img.size, #(224,224),\n    class_mode='categorical',\n    batch_size=32\n)\n\nvalidation_datagen = ImageDataGenerator(rescale=1./255)\nvalidation_generator = validation_datagen.flow_from_dataframe(\n    validate_df, \n    \"./train/\", \n    x_col='filename',\n    y_col='category',\n    target_size=img.size, #(224, 224),\n    class_mode='categorical',\n    batch_size=32\n)\n\nhistory = model.fit_generator(\n    train_generator, \n    epochs=50,\n    validation_data=validation_generator,\n    #validation_steps=len(train_df)//128,\n    #steps_per_epoch=len(validate_df)//128,\n    callbacks=callbacks\n)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"","execution_count":null,"outputs":[]}],"metadata":{"kernelspec":{"language":"python","display_name":"Python 3","name":"python3"},"language_info":{"pygments_lexer":"ipython3","nbconvert_exporter":"python","version":"3.6.4","file_extension":".py","codemirror_mode":{"name":"ipython","version":3},"name":"python","mimetype":"text/x-python"}},"nbformat":4,"nbformat_minor":4}