{"cells":[{"metadata":{"_uuid":"8f2839f25d086af736a60e9eeb907d3b93b6e0e5","_cell_guid":"b1076dfc-b9ad-4769-8c92-a6c4dae69d19","trusted":true},"cell_type":"code","source":"import pandas as pd\nimport numpy as np\nimport matplotlib.pyplot as plt\nimport matplotlib.image as mpimg\nimport seaborn as sns\nimport os\nimport cv2\n%matplotlib inline\n\nfrom sklearn.model_selection import train_test_split\nfrom sklearn.metrics import confusion_matrix\nimport itertools\n\nfrom keras.utils.np_utils import to_categorical # convert to one-hot-encoding\nfrom keras.models import Sequential\nfrom keras.layers import Dense, Dropout, Flatten, Conv2D, MaxPool2D\nfrom keras.optimizers import RMSprop\nfrom keras.preprocessing.image import ImageDataGenerator\nfrom keras.callbacks import ReduceLROnPlateau","execution_count":null,"outputs":[]},{"metadata":{"_cell_guid":"79c7e3d0-c299-4dcb-8224-4455121ee9b0","_uuid":"d629ff2d2480ee46fbb7e2d37f6b5fab8052498a","trusted":true},"cell_type":"code","source":"# Display 10 images\nDATA_DIR = \"../input/train/train\"\nfor file_name in os.listdir(DATA_DIR)[0:10]:\n    img_array = cv2.imread(os.path.join(DATA_DIR, file_name))\n    plt.imshow(img_array)\n    plt.show()\n    print(file_name.split('.')[0])","execution_count":null,"outputs":[]},{"metadata":{"trusted":true,"_uuid":"828f610c86decbdcc2e4a1eb9aede8ffb90992cc"},"cell_type":"code","source":"#create data\nDATA_DIR = \"../input/train/train\"\nIMG_SIZE = 28\ndef create_data():\n    x = []\n    y = []\n    for file_name in os.listdir(DATA_DIR):\n        img_array = cv2.imread(os.path.join(DATA_DIR, file_name))\n        new_array = cv2.resize(img_array, (IMG_SIZE, IMG_SIZE))\n        x.append(new_array)\n        if file_name.split('.')[0] == 'cat':\n            y.append(0)\n        else:\n            y.append(1)\n    return x, y","execution_count":null,"outputs":[]},{"metadata":{"trusted":true,"_uuid":"91e2fb9f8bac84d1fee1c4c57f794fbc27e53771"},"cell_type":"code","source":"import random\nx, y = create_data()\nx = np.array(x)\ny = np.array(y)\nprint(x.shape)\nprint(y.shape)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true,"_uuid":"e72cba40c9ac336cd2b9efd241c5156f55b7ffe6"},"cell_type":"code","source":"X_train = x / 255.0\nY_train = to_categorical(y, num_classes = 2)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true,"_uuid":"dd8c85743479ae2ab881d886754dca3fe6824404"},"cell_type":"code","source":"print(X_train.shape)\nprint(Y_train.shape)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true,"_uuid":"9c417ffc0f2e657c2b9d3d7ad3527582cd2e3ea1"},"cell_type":"code","source":"from keras import regularizers\nfrom keras.datasets import cifar10\nfrom keras.preprocessing.image import ImageDataGenerator\nfrom keras.models import Sequential\nfrom keras.optimizers import SGD\nfrom keras.callbacks import ModelCheckpoint\nfrom keras.layers.convolutional import Conv2D\nfrom keras.layers.convolutional import MaxPooling2D\nfrom keras.utils import np_utils\nfrom keras.preprocessing.image import ImageDataGenerator\nfrom keras.layers import Dense, Activation, Flatten, Dropout, BatchNormalization\nfrom keras import regularizers\nfrom keras.callbacks import LearningRateScheduler\nfrom keras import backend as K\nimport keras\nimport matplotlib.pyplot as plt\nweight_decay = 1e-4\nmodel = Sequential()\nmodel.add(Conv2D(32, (3,3), padding='same', kernel_regularizer=regularizers.l2(weight_decay), input_shape=X_train.shape[1:]))\nmodel.add(Activation('relu'))\nmodel.add(BatchNormalization())\nmodel.add(Conv2D(32, (3,3), padding='same', kernel_regularizer=regularizers.l2(weight_decay)))\nmodel.add(Activation('relu'))\nmodel.add(BatchNormalization())\nmodel.add(MaxPooling2D(pool_size=(2,2)))\nmodel.add(Dropout(0.2))\n \nmodel.add(Conv2D(64, (3,3), padding='same', kernel_regularizer=regularizers.l2(weight_decay)))\nmodel.add(Activation('relu'))\nmodel.add(BatchNormalization())\nmodel.add(Conv2D(64, (3,3), padding='same', kernel_regularizer=regularizers.l2(weight_decay)))\nmodel.add(Activation('relu'))\nmodel.add(BatchNormalization())\nmodel.add(MaxPooling2D(pool_size=(2,2)))\nmodel.add(Dropout(0.3))\n \nmodel.add(Conv2D(128, (3,3), padding='same', kernel_regularizer=regularizers.l2(weight_decay)))\nmodel.add(Activation('relu'))\nmodel.add(BatchNormalization())\nmodel.add(Conv2D(128, (3,3), padding='same', kernel_regularizer=regularizers.l2(weight_decay)))\nmodel.add(Activation('relu'))\nmodel.add(BatchNormalization())\nmodel.add(MaxPooling2D(pool_size=(2,2)))\nmodel.add(Dropout(0.4))\n \nmodel.add(Flatten())\nmodel.add(Dense(2, activation='softmax'))\nopt_rms = keras.optimizers.rmsprop(lr=0.001,decay=1e-6)\nmodel.compile(loss='categorical_crossentropy', optimizer=opt_rms, metrics=['accuracy'])","execution_count":null,"outputs":[]},{"metadata":{"trusted":true,"_uuid":"752a5117292f10ca7160e630aad6a89ab38d565c"},"cell_type":"code","source":"model.fit(x=X_train,\n          y=Y_train, epochs=100, validation_split=0.1)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true,"_uuid":"3cbfe8a4f0171d049cc9d835df427a05f12e029e"},"cell_type":"code","source":"#create data\nDATA_DIR = \"../input/test1/test1\"\nIMG_SIZE = 28\ndef create_test_data():\n    x = []\n    for i in range(1,12501):\n        img_array = cv2.imread(os.path.join(DATA_DIR, str(i) + '.jpg'))\n        new_array = cv2.resize(img_array, (IMG_SIZE, IMG_SIZE))\n        x.append(new_array)\n    return x","execution_count":null,"outputs":[]},{"metadata":{"trusted":true,"_uuid":"bbea888717572b83efb42615f9b8392f3fcbd6b8"},"cell_type":"code","source":"# predict results\ntest = create_test_data()\ntest = np.array(test) / 255.0\nresults = model.predict(test)\nprint(results.shape)\n\n","execution_count":null,"outputs":[]},{"metadata":{"trusted":true,"_uuid":"4a571d2077e1bbfb4c004adfd504025cc5ff9532"},"cell_type":"code","source":"# select the indix with the maximum probability\nresults = np.argmax(results,axis = 1)\n\nresults = pd.Series(results,name=\"label\")\nsubmission = pd.concat([pd.Series(range(1,12500),name = \"id\"),results],axis = 1)\n\nsubmission.to_csv(\"dogs_and_cats.csv\",index=False)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true,"_uuid":"174e0de2a7969f1aae6ef471bac019e9a1fe9c73"},"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}