{"cells":[{"cell_type":"markdown","metadata":{"_cell_guid":"192d78d5-201c-3d44-7261-7ed78f390326"},"source":""},{"cell_type":"code","execution_count":null,"metadata":{"_cell_guid":"2d510675-e138-dee0-444c-08005c246122"},"outputs":[],"source":"import os, cv2, random, csv\nimport numpy as np\nimport pandas as pd\n\nimport matplotlib.pyplot as plt\nfrom matplotlib import ticker\nimport seaborn as sns\n%matplotlib inline \n\nfrom keras.models import Sequential\nfrom keras.layers import Input, Dropout, Flatten, Convolution2D, MaxPooling2D, Dense, Activation\nfrom keras.optimizers import RMSprop\nfrom keras.callbacks import ModelCheckpoint, Callback, EarlyStopping\nfrom keras.utils import np_utils"},{"cell_type":"code","execution_count":null,"metadata":{"_cell_guid":"d2bdf7fc-4ace-0920-0274-f5a7a86a392a"},"outputs":[],"source":"TRAIN_DIR = '../input/train/'\nTEST_DIR = '../input/test/'\n\nROWS = 32\nCOLS = 32\nCHANNELS = 3\n\ntrain_images = [TRAIN_DIR+i for i in os.listdir(TRAIN_DIR)] # use this for full dataset\ntrain_dogs =   [TRAIN_DIR+i for i in os.listdir(TRAIN_DIR) if 'dog' in i]\ntrain_cats =   [TRAIN_DIR+i for i in os.listdir(TRAIN_DIR) if 'cat' in i]\n\ntest_images =  [TEST_DIR+i for i in os.listdir(TEST_DIR)]\n\n\n# slice datasets for memory efficiency on Kaggle Kernels, delete if using full dataset\ntrain_images = train_dogs[:1000] + train_cats[:1000]\nrandom.shuffle(train_images)\ntest_images =  test_images[:25]\n\ndef read_image(file_path):\n    img = cv2.imread(file_path, cv2.IMREAD_GRAYSCALE) #cv2.IMREAD_GRAYSCALE\n    return cv2.resize(img, (ROWS, COLS), interpolation=cv2.INTER_CUBIC)\n\n\ndef prep_data(images):\n    count = len(images)\n    data = np.ndarray((count, CHANNELS, ROWS, COLS), dtype=np.uint8)\n\n    for i, image_file in enumerate(images):\n        image = read_image(image_file)\n        data[i] = image.T\n        if i%250 == 0: print('Processed {} of {}'.format(i, count))\n    \n    return data\n\ntrain = prep_data(train_images)\ntest = prep_data(test_images)\n\nprint(\"Train shape: {}\".format(train.shape))\nprint(\"Test shape: {}\".format(test.shape))"},{"cell_type":"code","execution_count":null,"metadata":{"_cell_guid":"535a7889-27fe-8276-0eee-e4ed613fc0ce"},"outputs":[],"source":"labels = []\nfor i in train_images:\n    if 'dog' in i:\n        labels.append(1)\n    else:\n        labels.append(0)\n\nsns.countplot(labels)\nsns.plt.title('Cats and Dogs')"},{"cell_type":"code","execution_count":null,"metadata":{"_cell_guid":"01e04d82-3aeb-c809-ef23-07c9837d25c4"},"outputs":[],"source":"def show_cats_and_dogs(idx):\n    cat = read_image(train_cats[idx])\n    dog = read_image(train_dogs[idx])\n    pair = np.concatenate((cat, dog), axis=1)\n    plt.figure(figsize=(10,5))\n    plt.imshow(pair)\n    plt.show()\n    \nfor idx in range(0,5):\n    show_cats_and_dogs(idx)"},{"cell_type":"code","execution_count":null,"metadata":{"_cell_guid":"2a3c2129-3cb7-3d6f-5f6a-33b8a306cfde"},"outputs":[],"source":"optimizer = RMSprop(lr=1e-4)\nobjective = 'binary_crossentropy'\n\n\ndef catdog():\n    \n    model = Sequential()\n\n    model.add(Convolution2D(16, 3, 3, border_mode='same', input_shape=(3, ROWS, COLS), activation='relu'))\n    model.add(Convolution2D(16, 3, 3, border_mode='same', activation='relu'))\n    model.add(MaxPooling2D(pool_size=(1, 1)))\n\n    model.add(Convolution2D(32, 3, 3, border_mode='same', activation='relu'))\n    model.add(Convolution2D(32, 3, 3, border_mode='same', activation='relu'))\n    model.add(MaxPooling2D(pool_size=(1, 1)))\n    \n    model.add(Convolution2D(64, 3, 3, border_mode='same', activation='relu'))\n    model.add(Convolution2D(64, 3, 3, border_mode='same', activation='relu'))\n    model.add(MaxPooling2D(pool_size=(1, 1)))\n    \n    model.add(Convolution2D(128, 3, 3, border_mode='same', activation='relu'))\n    model.add(Convolution2D(128, 3, 3, border_mode='same', activation='relu'))\n    model.add(MaxPooling2D(pool_size=(1, 1)))\n\n    model.add(Flatten())\n    model.add(Dense(128, activation='relu'))\n    model.add(Dropout(0.5))\n    \n    model.add(Dense(128, activation='relu'))\n    model.add(Dropout(0.5))\n\n    model.add(Dense(1))\n    model.add(Activation('sigmoid'))\n\n    model.compile(loss=objective, optimizer=optimizer, metrics=['accuracy'])\n    return model\n\n\nmodel = catdog()"},{"cell_type":"code","execution_count":null,"metadata":{"_cell_guid":"77c0e965-30f5-00a5-7044-dca0cb7b118f"},"outputs":[],"source":"nb_epoch = 10\nbatch_size = 16\n\n## Callback for loss logging per epoch\nclass LossHistory(Callback):\n    def on_train_begin(self, logs={}):\n        self.losses = []\n        self.val_losses = []\n        \n    def on_epoch_end(self, batch, logs={}):\n        self.losses.append(logs.get('loss'))\n        self.val_losses.append(logs.get('val_loss'))\n\nearly_stopping = EarlyStopping(monitor='val_loss', patience=3, verbose=1, mode='auto')        \n        \ndef run_catdog():\n    \n    history = LossHistory()\n    model.fit(train, labels, batch_size=batch_size, nb_epoch=nb_epoch,\n              validation_split=0.25, verbose=0, shuffle=True, callbacks=[history, early_stopping])\n    \n\n    predictions = model.predict(test, verbose=0)\n    return predictions, history\n\npredictions, history = run_catdog()"},{"cell_type":"code","execution_count":null,"metadata":{"_cell_guid":"0fb0fb44-e735-56b8-a35a-872872e680e2"},"outputs":[],"source":"for i in range(0,10):\n    if predictions[i, 0] >= 0.5: \n        print('I am {:.2%} sure this is a Dog'.format(predictions[i][0]))\n    else: \n        print('I am {:.2%} sure this is a Cat'.format(1-predictions[i][0]))\n        \n    plt.imshow(test[i].T)\n    plt.show()"}],"metadata":{"_change_revision":0,"_is_fork":false,"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":"3.6.0"}},"nbformat":4,"nbformat_minor":0}