{"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 seaborn as sns\n\nfrom sklearn.model_selection import train_test_split\nfrom sklearn.metrics import confusion_matrix\n\nfrom keras.utils.np_utils import to_categorical\nfrom keras.preprocessing.image import ImageDataGenerator\nfrom keras.models import Sequential\nfrom keras import layers\nfrom keras.optimizers import RMSprop,Adam\n\nfrom keras.callbacks import ReduceLROnPlateau, EarlyStopping\n\ntrain = pd.read_csv('/kaggle/input/Kannada-MNIST/train.csv')\ntest = pd.read_csv('/kaggle/input/Kannada-MNIST/test.csv')\n\ndef load_dataset(filename, limit=None):\n    csv_data = pd.read_csv(filename, nrows=limit)\n    \n    x_data = csv_data.drop('label',axis=1)\n    y_data = csv_data.label\n    \n    x_data = x_data.values.astype('float32') / 255   \n    x_data = x_data.reshape(-1, 28, 28,1)\n    \n    y_data = to_categorical(y_data)\n    \n    return x_data, y_data\n\n# X_train_with_val, y_train_with_val = load_dataset('/kaggle/input/Kannada-MNIST/train.csv', limit=100)\nX_train_with_val, y_train_with_val = load_dataset('/kaggle/input/Kannada-MNIST/train.csv')\nX_train, X_val, y_train, y_val = train_test_split(X_train_with_val, y_train_with_val, random_state=1, test_size=0.15)\n\ndef build_lenet_model():\n    model = Sequential()\n\n    model.add(layers.Conv2D(filters=7, kernel_size=(5, 5), activation='relu', input_shape=(28, 28, 1)))\n    model.add(layers.AveragePooling2D(strides=2))\n\n    model.add(layers.Conv2D(filters=19, kernel_size=(5, 5), activation='relu', padding='same'))\n    model.add(layers.AveragePooling2D(strides=2))\n\n    model.add(layers.Conv2D(filters=199, kernel_size=(5, 5), activation='relu'))\n    model.add(layers.Flatten())\n\n    model.add(layers.Dense(units=84, activation='relu'))\n\n    model.add(layers.Dense(units=10, activation = 'softmax'))\n\n    return model\n\nmodel = build_lenet_model()\n  \nmodel.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    \nmodel.fit(X_train, y_train, batch_size=32,\n                    epochs=60,\n                    validation_data=(X_val, y_val),\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 = 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","_cell_guid":"79c7e3d0-c299-4dcb-8224-4455121ee9b0","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}