{"cells":[{"metadata":{"_uuid":"8f2839f25d086af736a60e9eeb907d3b93b6e0e5","_cell_guid":"b1076dfc-b9ad-4769-8c92-a6c4dae69d19","trusted":true,"_kg_hide-output":false},"cell_type":"code","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\nimport os\nprint(os.listdir(\"../input/train/\"))\n\n# Any results you write to the current directory are saved as output.","execution_count":null,"outputs":[]},{"metadata":{"trusted":true,"_uuid":"7c125fca535d9f25433f60656e2a36d051157005"},"cell_type":"code","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","execution_count":null,"outputs":[]},{"metadata":{"_cell_guid":"79c7e3d0-c299-4dcb-8224-4455121ee9b0","_uuid":"d629ff2d2480ee46fbb7e2d37f6b5fab8052498a","trusted":true},"cell_type":"code","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\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\nimg = read_image(train_images[0])\n\nprint(\"Train shape: {}\".format(train.shape))\nprint(\"Test shape: {}\".format(test.shape))","execution_count":null,"outputs":[]},{"metadata":{"trusted":true,"_uuid":"808b31b7a0c620c7e2520ba1ccec014eb837dd56"},"cell_type":"code","source":"img = read_image(train_images[0])","execution_count":null,"outputs":[]},{"metadata":{"trusted":true,"_uuid":"85731ae4ae002742f27f3fb535cd61e067bbbb11"},"cell_type":"code","source":"from keras import layers\nfrom keras import models\n\nmodel = models.Sequential()\nmodel.add(layers.Conv2D(32, (3, 3), activation='relu',\ninput_shape=(150, 150, 3)))\nmodel.add(layers.MaxPooling2D((2, 2)))\nmodel.add(layers.Conv2D(64, (3, 3), activation='relu'))\nmodel.add(layers.MaxPooling2D((2, 2)))\nmodel.add(layers.Conv2D(128, (3, 3), activation='relu'))\nmodel.add(layers.MaxPooling2D((2, 2)))\nmodel.add(layers.Conv2D(128, (3, 3), activation='relu'))\nmodel.add(layers.MaxPooling2D((2, 2)))\nmodel.add(layers.Flatten())\nmodel.add(layers.Dense(512, activation='relu'))\nmodel.add(layers.Dense(1, activation='sigmoid'))\n","execution_count":null,"outputs":[]},{"metadata":{"trusted":true,"_uuid":"b006e766b6036eddba4a8212dfc4c730d1e4cdb0"},"cell_type":"code","source":"model.summary()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true,"_uuid":"0446dee8856085d7e3d5502bd23f753e9c86e00b"},"cell_type":"code","source":"from keras import optimizers\nmodel.compile(loss='binary_crossentropy',\n              optimizer=optimizers.RMSprop(lr=1e-4),\n              metrics=['acc'])","execution_count":null,"outputs":[]},{"metadata":{"trusted":true,"_uuid":"50b7cc9fc16bdc51278c45f489c4297c5f8f37db"},"cell_type":"code","source":"","execution_count":null,"outputs":[]},{"metadata":{"trusted":true,"_uuid":"64cdcc5cfac08eba75df18fd777f50c77d7d3053"},"cell_type":"code","source":"","execution_count":null,"outputs":[]},{"metadata":{"trusted":true,"_uuid":"0e5cd1c0d2cd532b9a734c3bfeac904a4c197432"},"cell_type":"code","source":"","execution_count":null,"outputs":[]},{"metadata":{"trusted":true,"_uuid":"1566ae6982dd4d9f64d9e05c04c6481100519e48"},"cell_type":"code","source":"","execution_count":null,"outputs":[]},{"metadata":{"trusted":true,"_uuid":"d57dca8d6edea624f47525126b4573433f16da90"},"cell_type":"code","source":"","execution_count":null,"outputs":[]},{"metadata":{"trusted":true,"_uuid":"9d485c2656e447940e5b793db455f0bf6e6e788a"},"cell_type":"code","source":"","execution_count":null,"outputs":[]}],"metadata":{"kernelspec":{"display_name":"Python 3","language":"python","name":"python3"},"language_info":{"name":"python","version":"3.6.6","mimetype":"text/x-python","codemirror_mode":{"name":"ipython","version":3},"pygments_lexer":"ipython3","nbconvert_exporter":"python","file_extension":".py"}},"nbformat":4,"nbformat_minor":1}