{"cells":[{"metadata":{"trusted":true},"cell_type":"code","source":"import numpy as np\nfrom keras import layers\nfrom keras.layers import Input, Add, Dense,Dropout, Activation, ZeroPadding2D, BatchNormalization, Flatten, Conv2D, AveragePooling2D, MaxPooling2D, GlobalMaxPooling2D\nfrom keras.models import Model, load_model\nfrom keras.preprocessing import image\nfrom keras.utils import layer_utils\nfrom keras.utils.data_utils import get_file\nfrom keras.applications.imagenet_utils import preprocess_input\nimport pydot\nfrom IPython.display import SVG\nfrom keras.utils.vis_utils import model_to_dot\nfrom keras.utils import plot_model\nfrom keras.initializers import glorot_uniform\nimport scipy.misc\nimport matplotlib.pyplot as plt\nfrom sklearn.model_selection import train_test_split\n\n%matplotlib inline\n\nimport keras.backend as K\nK.set_image_data_format('channels_last')\nK.set_learning_phase(1)","execution_count":null,"outputs":[]},{"metadata":{"_uuid":"d629ff2d2480ee46fbb7e2d37f6b5fab8052498a","_cell_guid":"79c7e3d0-c299-4dcb-8224-4455121ee9b0","trusted":true},"cell_type":"code","source":"import pandas as pd\nfrom keras.utils.np_utils import to_categorical\ndef load_data():\n    filename = \"/kaggle/input/digit-recognizer/train.csv\"\n    df = pd.read_csv(filename)\n    y_train_set_orig, x_train_set_orig = np.array(df.loc[:,'label']),np.array(df.loc[:,'pixel0':])\n\n    filename = \"/kaggle/input/digit-recognizer/test.csv\"\n    df = pd.read_csv(filename)\n    x_test_set_orig = np.array(df.loc[:,'pixel0':])\n    y_train= to_categorical(y_train_set_orig)\n    classes = y_train.shape[1]\n    return x_train_set_orig,y_train,x_test_set_orig,classes","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"X_train_orig, Y_train,X_test_orig, Classes = load_data()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"Y_train","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"X_test_orig.shape\n# X_train = X_train_orig.reshape(X_train_orig.shape[0], 28, 28)\n\n","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"X_train = X_train_orig.reshape(-1,28,28,1)\nX_test = X_test_orig.reshape(-1,28,28,1)\n\nprint(X_train.shape)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"X_train = X_train/255.0\nX_test = X_test/255.0\n","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"X_train, X_val, Y_train, Y_val = train_test_split(X_train, Y_train, test_size = 0.1, random_state=1)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"plt.imshow(X_train[100][:,:,0],cmap='gray')\nplt.show()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"def cnn(input_shape,classes):\n    \n    X_input = Input(input_shape)\n    \n    X = ZeroPadding2D((3, 3))(X_input)\n    X = Conv2D(32, (3,3),padding = 'same',kernel_initializer = glorot_uniform(seed=0))(X)\n    X = BatchNormalization(axis = 3)(X)\n    X =  Activation('relu')(X)\n    \n    X = Conv2D(32, (3,3),padding = 'same',kernel_initializer = glorot_uniform(seed=0))(X)\n    X = BatchNormalization(axis = 3)(X)\n    X =  Activation('relu')(X)\n    \n    X = Conv2D(64, (3,3),padding = 'same',kernel_initializer = glorot_uniform(seed=0))(X)\n    X = BatchNormalization(axis = 3)(X)\n    X = Activation('relu')(X)\n   \n    \n    X = Conv2D(64, (3,3),padding = 'same',kernel_initializer = glorot_uniform(seed=0))(X)\n    X = BatchNormalization(axis = 3)(X)\n    X = Activation('relu')(X)\n    \n    X = Conv2D(128, (3,3),padding = 'same',kernel_initializer = glorot_uniform(seed=0))(X)\n    X = BatchNormalization(axis = 3)(X)\n    X = Activation('relu')(X)\n   \n    \n    X = Conv2D(128, (3,3),padding = 'same',kernel_initializer = glorot_uniform(seed=0))(X)\n    X = BatchNormalization(axis = 3)(X)\n    X = Activation('relu')(X)\n    \n    X = MaxPooling2D(pool_size=(2,2))(X)\n    X = Flatten()(X)\n    X = Dense(classes, activation='softmax', kernel_initializer = glorot_uniform(seed=0))(X)\n    \n    model = Model(inputs = X_input, outputs = X)\n    return model\n","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"model = cnn(input_shape = (28, 28, 1), classes = 10)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"model.compile(optimizer='adam', loss='categorical_crossentropy', metrics=['accuracy'])\n","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"model.fit(X_train, Y_train, epochs = 10, batch_size = 32)\n","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"preds = model.evaluate(X_val, Y_val)\nprint (\"Loss = \" + str(preds[0]))\nprint (\"Test Accuracy = \" + str(preds[1]))","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"results = model.predict(X_test)\n","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"results = np.argmax(results,axis = 1)\n\nresults = pd.Series(results,name=\"Label\")\nsubmission = pd.concat([pd.Series(range(1,28001),name = \"ImageId\"),results],axis = 1)\n\nsubmission.to_csv(\"cnn_mnist_datagen.csv\",index=False)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"","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}