{"cells":[{"cell_type":"code","execution_count":null,"metadata":{"_cell_guid":"dabec4c7-a758-3d8e-d5a2-fff8ae8522f0"},"outputs":[],"source":"# This Python 3 environment comes with many helpful analytics libraries installed\n# It is defined by the kaggle/python docker image: https://github.com/kaggle/docker-python\n# For example, here's several helpful packages to load in \n\nimport numpy as np # linear algebra\nimport pandas as pd # data processing, CSV file I/O (e.g. pd.read_csv)\n\n# Input data files are available in the \"../input/\" directory.\n# For example, running this (by clicking run or pressing Shift+Enter) will list the files in the input directory\n\nfrom subprocess import check_output\nprint(check_output([\"ls\", \"../input\"]).decode(\"utf8\"))\n\n# Any results you write to the current directory are saved as output."},{"cell_type":"code","execution_count":null,"metadata":{"_cell_guid":"0192ecd2-4851-d015-728a-9cf4c0d41e0a"},"outputs":[],"source":"import os, cv2, random\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":"f9e9f1bd-5d2b-9312-111f-baa02f2132d4"},"outputs":[],"source":"TRAIN_DIR = '../input/train/'\nTEST_DIR = '../input/test/'\n\nROWS = 64\nCOLS = 64\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_COLOR) #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":"65a0e8ed-28d6-dd54-43ab-4f0689715068"},"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":"06a6934b-142c-dfb7-c919-d886e8a092e7"},"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":"34dd48c7-b55b-3de2-d7f1-c6c3d9091e30"},"outputs":[],"source":"dog_avg = np.array([dog[0].T for i, dog in enumerate(train) if labels[i]==1]).mean(axis=0)\nplt.imshow(dog_avg)\nplt.title('Your Average Dog')"},{"cell_type":"code","execution_count":null,"metadata":{"_cell_guid":"0ae648cf-83cb-b7fc-d7f6-e386dcfb53a8"},"outputs":[],"source":"cat_avg = np.array([cat[0].T for i, cat in enumerate(train) if labels[i]==0]).mean(axis=0)\nplt.imshow(cat_avg)\nplt.title('Your Average Cat')"},{"cell_type":"code","execution_count":null,"metadata":{"_cell_guid":"9c391016-80c9-4273-56ab-2bfda0e794b2"},"outputs":[],"source":"optimizer = RMSprop(lr=1e-4)\nobjective = 'binary_crossentropy'\n\ndef catdog():\n    model = Sequential()\n\n    model.add(Convolution2D(32, 3, 3, border_mode='same', input_shape=(3, ROWS, COLS), activation='relu'))\n    model.add(Convolution2D(32, 3, 3, border_mode='same', activation='relu'))\n    #model.add(MaxPooling2D(pool_size=(2, 2), strides=None, border_mode='valid', dim_ordering='default'))\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=(2, 2), strides=None, border_mode='valid', dim_ordering='default'))\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=(2, 2), strides=None, border_mode='valid', dim_ordering='default'))\n    model.add(Convolution2D(256, 3, 3, border_mode='same', activation='relu'))\n    model.add(Convolution2D(256, 3, 3, border_mode='same', activation='relu'))\n#     model.add(Convolution2D(256, 3, 3, border_mode='same', activation='relu'))\\n\",\n    model.add(MaxPooling2D(pool_size=(2, 2)))\n\n#     model.add(Convolution2D(256, 3, 3, border_mode='same', activation='relu'))\\n\",\n#     model.add(Convolution2D(256, 3, 3, border_mode='same', activation='relu'))\\n\",\n#     model.add(Convolution2D(256, 3, 3, border_mode='same', activation='relu'))\\n\",\n#     model.add(MaxPooling2D(pool_size=(2, 2)))\\n\",\n\n    model.add(Flatten())\n    model.add(Dense(256, activation='relu'))\n    model.add(Dropout(0.5))\n\n    model.add(Dense(256, activation='relu'))\n    model.add(Dropout(0.5))\n\n    model.add(Dense(1))\n    model.add(Activation('sigmoid'))\n    model.compile(loss=objective, optimizer=optimizer, metrics=['accuracy'])\n    return model\n\nmodel = catdog()"},{"cell_type":"code","execution_count":null,"metadata":{"_cell_guid":"21b11a96-1a1e-884a-5160-f3702cd48e59"},"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":"a559e475-97db-2799-5afa-84d96137163f"},"outputs":[],"source":"loss = history.losses\nval_loss = history.val_losses\n\nplt.xlabel('Epochs')\nplt.ylabel('Loss')\nplt.title('VGG-16 Loss Trend')\nplt.plot(loss, 'blue', label='Training Loss')\nplt.plot(val_loss, 'green', label='Validation Loss')\nplt.xticks(range(0,nb_epoch)[0::2])\nplt.legend()\nplt.show()"},{"cell_type":"code","execution_count":null,"metadata":{"_cell_guid":"6bf3e2a5-f05a-0a02-66e0-856fa8d90a91"},"outputs":[],"source":"for i in range(0,len(predictions)):\n    print(predictions[i][0])"}],"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}