{"cells":[{"metadata":{"_uuid":"8f2839f25d086af736a60e9eeb907d3b93b6e0e5","_cell_guid":"b1076dfc-b9ad-4769-8c92-a6c4dae69d19","trusted":true},"cell_type":"code","source":"import cv2\nfrom glob import glob\nimport os\nfrom sklearn.model_selection import train_test_split\nimport matplotlib.pyplot as plt\nimport numpy as np","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"images = []\nlabels = []\n\ndef get_data(clazz):\n    files = glob(os.path.join('..', 'input','state-farm-distracted-driver-detection','imgs', 'train', 'c' + str(clazz), '*.jpg'))\n    for file in files:\n        img = cv2.imread(file)\n        img = cv2.cvtColor(img, cv2.COLOR_BGR2GRAY) \n        images.append(cv2.resize(img, (225,225)))\n        labels.append(clazz)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"for clazz in range(10):\n    get_data(clazz)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"x_train, x_test, y_train, y_test = train_test_split(images, labels, test_size=0.25, random_state=0)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"from keras.utils import to_categorical\nimport numpy as np\n\ny_train = to_categorical(y_train)\ny_test = to_categorical(y_test)\n\nx_train = np.asarray(x_train)\nx_test = np.asarray(x_test)\n\nx_test = np.expand_dims(x_test, axis=3)\nx_train = np.expand_dims(x_train, axis=3)\n\nx_train.shape, x_test.shape, y_train.shape, y_test.shape","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"fig = plt.figure(figsize=(8,8))\nfor i in range(64):\n    ax = fig.add_subplot(8,8,i+1)\n    ax.imshow(x_train[i], cmap=plt.cm.bone)\nplt.show()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"from keras.models import Sequential\nfrom keras.layers import Conv2D, Dense, Activation, MaxPooling2D, Dropout, Flatten\nfrom keras.callbacks import EarlyStopping\n\nmodel = Sequential()\n\nmodel.add(Conv2D(32 ,kernel_size=(3, 3), padding='same', input_shape=(225, 225, 1), strides=(1, 1), activation='elu'))\nmodel.add(Conv2D(32, (3, 3), activation='elu'))\nmodel.add(MaxPooling2D(pool_size=(2, 2)))\nmodel.add(Dropout(0.25))\n\nmodel.add(Conv2D(64 ,kernel_size=(3, 3), padding='same', activation='elu'))\nmodel.add(Conv2D(64, (3, 3), activation='elu'))\nmodel.add(MaxPooling2D(pool_size=(2, 2)))\nmodel.add(Dropout(0.25))\n\nmodel.add(Conv2D(128 ,kernel_size=(3, 3), padding='same', activation='elu'))\nmodel.add(Conv2D(128, (3, 3), activation='elu'))\nmodel.add(MaxPooling2D(pool_size=(2, 2)))\nmodel.add(Dropout(0.25))\n\nmodel.add(Flatten())\nmodel.add(Dense(256, activation='elu'))\nmodel.add(Dropout(0.25))\n\nmodel.add(Dense(10, activation='softmax'))","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"model.summary()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"from keras.optimizers import RMSprop\n\nopt = RMSprop(lr=0.0001, decay=1e-6)\nmodel.compile(loss='categorical_crossentropy', optimizer=opt, metrics=['accuracy'])","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"model.fit(x_train, y_train, validation_data=(x_test, y_test), epochs=10, batch_size=50)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"_, acc = model.evaluate(x_test, y_test, verbose=10)\nprint(acc)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"predictions = model.predict(x_test)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"np.savetxt(fname=\"submission.csv\", X=predictions)","execution_count":null,"outputs":[]}],"metadata":{"kernelspec":{"language":"python","display_name":"Python 3","name":"python3"},"language_info":{"pygments_lexer":"ipython3","nbconvert_exporter":"python","version":"3.6.4","file_extension":".py","codemirror_mode":{"name":"ipython","version":3},"name":"python","mimetype":"text/x-python"}},"nbformat":4,"nbformat_minor":4}