{"cells":[{"metadata":{"_uuid":"8f2839f25d086af736a60e9eeb907d3b93b6e0e5","_cell_guid":"b1076dfc-b9ad-4769-8c92-a6c4dae69d19","trusted":true},"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\"))\nimport matplotlib.pyplot as plt\n\nimport 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\n# Any results you write to the current directory are saved as output.","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)]","execution_count":null,"outputs":[]},{"metadata":{"trusted":true,"_uuid":"544b53e826e40e83843c25d81aa11177c68eec36"},"cell_type":"code","source":"train_images = train_dogs[:1000] + train_cats[:1000]","execution_count":null,"outputs":[]},{"metadata":{"trusted":true,"_uuid":"2ece49d92592999687e4dcf2905369f64ee681d7"},"cell_type":"code","source":"random.shuffle(train_images)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true,"_uuid":"e72204239c952955e9e79b6b5447e18adcbb21ea"},"cell_type":"code","source":"test_images =  test_images[:25]","execution_count":null,"outputs":[]},{"metadata":{"trusted":true,"_uuid":"bac658581925463f3b36958431a97bd737a4fe3d"},"cell_type":"code","source":"img=cv2.imread(train_images)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true,"_uuid":"9992b71e3fce1d637c16f527eadd68b6daf372c8"},"cell_type":"code","source":"def read_image(path):\n    a=cv2.imread(path)\n    a=cv2.resize(a, (ROWS, COLS), interpolation=cv2.INTER_CUBIC)\n    return a.T\ndef load(z):\n    l=len(z)\n    arr=np.ndarray((l, CHANNELS, ROWS, COLS), dtype=np.uint8)\n    for i,img in enumerate(z):\n        arr[i]=read_image(img)\n        if i%250==0:\n            print('till'+str(i)+'done')\n    return arr","execution_count":null,"outputs":[]},{"metadata":{"trusted":true,"_uuid":"b12d94118bdd8b1c00bbefcb8e89d927b2242035"},"cell_type":"code","source":"train=load(train_images)\ntest=load(test_images)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true,"_uuid":"efa851a9e93d1c39571fc409cf7ce3da9342206c"},"cell_type":"code","source":"labels=[]\nfor i in train_images:\n    if 'dog' in i:\n        labels.append(1)\n    else:\n        labels.append(0)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true,"_uuid":"1ca14f82b294286750d7a6fe9bbfcb97f575720b"},"cell_type":"code","source":"sns.countplot(labels)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true,"_uuid":"87dfa2a5aa3c7170c4e7957907595adc36694bec"},"cell_type":"code","source":"","execution_count":null,"outputs":[]},{"metadata":{"trusted":true,"_uuid":"2438de844a7a4ab5ecc1b035b3c488aa89b51f3f"},"cell_type":"code","source":"optimizer = RMSprop(lr=1e-4)\nobjective = 'binary_crossentropy'\n\n\ndef catdog():\n    \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)))\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,\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=(2, 2)))\n    \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    model.add(MaxPooling2D(pool_size=(2, 2)))\n\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 #    model.add(MaxPooling2D(pool_size=(2, 2)))\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\n    model.compile(loss=objective, optimizer=optimizer, metrics=['accuracy'])\n    return model\n\n\nmodel = catdog()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true,"_uuid":"c34005c09530cb6911cd951609dab885ad2ae92f"},"cell_type":"code","source":"nb_epoch = 10\nbatch_size = 16\ndef run_catdog():\n    \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 = run_catdog()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true,"_uuid":"8be5b5d524bc9130c25fc491916b271eb0015f53"},"cell_type":"code","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()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true,"_uuid":"77f6ff3e7708bed33aaf65864aec020a9bb73b44"},"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}