{"cells":[{"metadata":{"_uuid":"8f2839f25d086af736a60e9eeb907d3b93b6e0e5","_cell_guid":"b1076dfc-b9ad-4769-8c92-a6c4dae69d19","trusted":true},"cell_type":"code","source":"import time\nimport pandas as pd\nimport numpy as np\nimport seaborn as sns\n\nfrom sklearn.model_selection import train_test_split\n\nfrom tensorflow.keras.utils import to_categorical\nfrom tensorflow.keras.models import Sequential, Model\nfrom tensorflow.keras.layers import Dense, Dropout, Flatten, Conv2D, AveragePooling2D, MaxPool2D, Input, BatchNormalization, ReLU\nfrom tensorflow.keras.callbacks import EarlyStopping, ReduceLROnPlateau, ModelCheckpoint\nfrom tensorflow.keras.preprocessing.image import ImageDataGenerator\n\ntrain = pd.read_csv('/kaggle/input/Kannada-MNIST/train.csv')\ntest = pd.read_csv('/kaggle/input/Kannada-MNIST/test.csv')\n\nX = train.drop('label',axis=1)\ny = train.label\n    \nX = X.values.astype('float32') / 255   \nX = X.reshape(-1, 28, 28,1)\n    \ny = to_categorical(y)\n\nX_train, X_valid, y_train, y_valid = train_test_split(X, y, test_size=0.15, random_state=1) \n\ndef group_layers(model, filters, kernel, count):\n    for i in range(count):\n        model.add(Conv2D(filters, kernel, padding='same'))\n        model.add(BatchNormalization(momentum=0.9, epsilon=1e-5))\n        model.add(ReLU())\n        \ncustom_model = Sequential()\ncustom_model.add(Conv2D(32, (3, 3), padding='same', input_shape=(28, 28, 1)))\ncustom_model.add(BatchNormalization(momentum=0.9, epsilon=1e-5, gamma_initializer=\"uniform\"))\ncustom_model.add(ReLU())\n\ngroup_layers(custom_model, 32, (3,3), 2)\n\ncustom_model.add(AveragePooling2D(strides=2))\ncustom_model.add(Dropout(0.25))\n\ngroup_layers(custom_model, 64, (3,3), 2)\n\ncustom_model.add(AveragePooling2D(strides=2))\ncustom_model.add(Dropout(0.25))\n        \ncustom_model.add(Flatten())\ncustom_model.add(Dense(64))\ncustom_model.add(ReLU())\n    \ncustom_model.add(BatchNormalization())\ncustom_model.add(Dense(10, activation='softmax'))\n\ncustom_model.compile(loss='categorical_crossentropy', optimizer='Adam', metrics=['accuracy'])\n\nlearning_rate_reduction = ReduceLROnPlateau(monitor='val_accuracy', \n                                patience=3, \n                                verbose=1, \n                                factor=0.2, \n                                min_lr=1e-6)\n    \nes = EarlyStopping(monitor='val_loss', mode='min', verbose=1, patience=300, restore_best_weights=True)\n\ncustom_model.fit(X_train, y_train, batch_size=64,\n                    epochs=60,\n                    validation_data=(X_valid, y_valid),\n                    callbacks=[learning_rate_reduction, es],\n                    verbose=2)\n\ntest = test.drop('id',axis=1)\nX_test = test.values.astype('float32') / 255\nX_test = X_test.reshape(-1, 28, 28,1)\n\nsample_sub=pd.read_csv('../input/Kannada-MNIST/sample_submission.csv')\nsub = custom_model.predict(X_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":{"_uuid":"d629ff2d2480ee46fbb7e2d37f6b5fab8052498a","collapsed":true,"_cell_guid":"79c7e3d0-c299-4dcb-8224-4455121ee9b0","trusted":false},"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}