{"cells":[{"metadata":{"_uuid":"8f2839f25d086af736a60e9eeb907d3b93b6e0e5","_cell_guid":"b1076dfc-b9ad-4769-8c92-a6c4dae69d19","trusted":true},"cell_type":"code","source":"import numpy as np # linear algebra\nimport pandas as pd # data processing, CSV file I/O (e.g. pd.read_csv)\n\nimport os\nfor dirname, _, filenames in os.walk('/kaggle/input'):\n    for filename in filenames:\n        print(os.path.join(dirname, filename))\n","execution_count":null,"outputs":[]},{"metadata":{"_uuid":"d629ff2d2480ee46fbb7e2d37f6b5fab8052498a","_cell_guid":"79c7e3d0-c299-4dcb-8224-4455121ee9b0","trusted":true},"cell_type":"code","source":"from keras.models import Sequential\nfrom keras.layers import Conv2D, MaxPooling2D, Dropout, Dense, Flatten, AveragePooling2D, Activation, ELU, BatchNormalization, Layer, Lambda, LeakyReLU\nfrom keras.optimizers import Adadelta, Adam, RMSprop\nfrom keras.utils import to_categorical\nfrom keras.preprocessing.image import ImageDataGenerator\nfrom keras.datasets.mnist import load_data as load\nfrom keras.models import load_model\nfrom keras.regularizers import l2\nfrom keras.callbacks import ReduceLROnPlateau, EarlyStopping\nfrom keras import backend as K\nfrom sklearn.model_selection import train_test_split","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"train = pd.read_csv('../input/Kannada-MNIST/train.csv')\ntest = pd.read_csv('../input/Kannada-MNIST/test.csv')","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"x = train.iloc[:, 1:].values.astype('float32') / 255\ny = train.iloc[:, 0]","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"x_train, x_validation, y_train, y_validation = train_test_split(x, y, test_size=0.2 , random_state=1337)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"x_train = x_train.reshape(-1, 28, 28,1)\nx_validation = x_validation.reshape(-1, 28, 28,1)\ny_train = to_categorical(y_train)\ny_validation = to_categorical(y_validation)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"def build_model():\n    model = Sequential()\n\n    model.add(Conv2D(64, kernel_size=(3, 3), padding='same', input_shape=(28,28,1)))\n    model.add(Conv2D(64, kernel_size=(3, 3), padding='same'))\n    model.add(BatchNormalization())\n    model.add(ELU(alpha=1.0))\n    model.add(MaxPooling2D(pool_size=(2,2)))\n    model.add(Dropout(0.4))\n    \n    model.add(Conv2D(128, kernel_size=(3, 3), padding='same'))\n    model.add(Conv2D(128, kernel_size=(3, 3), padding='same'))\n    model.add(BatchNormalization())\n    model.add(ELU(alpha=1.0))\n    model.add(MaxPooling2D(pool_size=(2,2)))\n    model.add(Dropout(0.4))\n    \n    model.add(Conv2D(256, kernel_size=(3, 3), padding='same'))\n    model.add(Conv2D(256, kernel_size=(3, 3), padding='same'))\n    model.add(BatchNormalization())\n    model.add(ELU(alpha=1.0))\n    model.add(MaxPooling2D(pool_size=(2,2)))\n    model.add(Dropout(0.4))\n\n    model.add(Flatten())\n    model.add(Dense(512))\n    model.add(BatchNormalization())\n    model.add(ELU(alpha=1.0))\n    model.add(Dropout(0.25))\n    model.add(Dense(10, activation='softmax'))\n    \n    return model","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"data_gen = ImageDataGenerator(\n        featurewise_center=False,\n        samplewise_center=False,\n        featurewise_std_normalization=False, \n        samplewise_std_normalization=False,\n        zca_whitening=False,  \n        rotation_range=10,  \n        zoom_range = 0.1,\n        shear_range=0.3,\n        width_shift_range=0.1,\n        height_shift_range=0.1, \n        horizontal_flip=False, \n        vertical_flip=False)  \n\ndata_gen.fit(x_train)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"learning_rate_reduction = ReduceLROnPlateau(monitor='val_accuracy', \n                                            patience=3, \n                                            verbose=1, \n                                            factor=0.5, \n                                            min_lr=0.00001)\n\nes = EarlyStopping(monitor='val_loss',\n                   min_delta=1e-1, \n                   verbose=1, \n                   patience=100,\n                   restore_best_weights=True)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"optimizer = RMSprop(learning_rate=0.002,\n    rho=0.9,\n    epsilon=1e-07,)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"model = build_model() \nmodel.compile(loss = 'categorical_crossentropy', optimizer = optimizer, metrics=['accuracy'])","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"batch_size = 1024\nepochs = 50","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"history = model.fit_generator(data_gen.flow(x_train, y_train, batch_size=batch_size), \n                              validation_data=data_gen.flow(x_validation, y_validation, batch_size=batch_size), \n                              steps_per_epoch=len(x_train)//batch_size, \n                              epochs=epochs, \n                              callbacks=[learning_rate_reduction, es])","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"raw_test = pd.read_csv('../input/Kannada-MNIST/test.csv')","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"sample_sub=pd.read_csv('../input/Kannada-MNIST/sample_submission.csv')\nraw_test_id=raw_test.id\nraw_test=raw_test.drop(\"id\",axis=\"columns\")\nraw_test=raw_test / 255\ntest=raw_test.values.reshape(-1,28,28,1)\n\nsub=model.predict(test)     \nsub=np.argmax(sub,axis=1) \n\nsample_sub['label']=sub\nsample_sub.to_csv('submission.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":1}