{"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)\nimport matplotlib.pyplot as plt\n%matplotlib notebook\nimport seaborn as sns\nimport tensorflow as tf\ntf.random.set_seed(42)\nnp.random.seed(43)\n#from sklearn.model_selection import train_test_split","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"!nvidia-smi","execution_count":null,"outputs":[]},{"metadata":{"_uuid":"d629ff2d2480ee46fbb7e2d37f6b5fab8052498a","_cell_guid":"79c7e3d0-c299-4dcb-8224-4455121ee9b0","trusted":true},"cell_type":"code","source":"df_train = pd.read_csv('/kaggle/input/Kannada-MNIST/train.csv')\ndf_val = pd.read_csv('/kaggle/input/Kannada-MNIST/Dig-MNIST.csv')\ndf_test = pd.read_csv('/kaggle/input/Kannada-MNIST/test.csv')","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"y = tf.keras.utils.to_categorical(df_train['label'].values)\ny_val = tf.keras.utils.to_categorical(df_val['label'].values)\ny_not_enc = df_train['label'].values\n\ndf_train = df_train.drop(['label'], axis=1)\ndf_val = df_val.drop(['label'], axis=1)\n\nX = df_train.values.reshape(-1, 28, 28, 1)\nX_val = df_val.values.reshape(-1, 28, 28, 1)\n\n#X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.05, stratify=y_not_enc, random_state=42)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"datagen = tf.keras.preprocessing.image.ImageDataGenerator(rescale=1./255.,\n                                   rotation_range=15,\n                                   width_shift_range=0.25,\n                                   height_shift_range=0.25,\n                                   shear_range=0.2,\n                                   zoom_range=0.2,\n                                   horizontal_flip=False)\ndatagen.fit(X)\nvalid_datagen = tf.keras.preprocessing.image.ImageDataGenerator(rescale=1./255.)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"model = tf.keras.models.Sequential()\n\nmodel.add(tf.keras.layers.Conv2D(filters = 16, kernel_size = 3, strides = 1, activation = 'selu', kernel_initializer='glorot_normal', input_shape = (28, 28, 1)))\nmodel.add(tf.keras.layers.Conv2D(filters = 16, kernel_size = 3, strides = 1, activation = 'selu', kernel_initializer='glorot_normal', padding='same', input_shape = (28, 28, 1)))\nmodel.add(tf.keras.layers.BatchNormalization())\nmodel.add(tf.keras.layers.MaxPooling2D(pool_size = 2, strides = 2))\nmodel.add(tf.keras.layers.Dropout(0.2))\n\nmodel.add(tf.keras.layers.Conv2D(filters = 32, kernel_size = 3, strides = 1, activation = 'selu', kernel_initializer='glorot_normal', padding='same'))\nmodel.add(tf.keras.layers.Conv2D(filters = 32, kernel_size = 3, strides = 1, activation = 'selu', kernel_initializer='glorot_normal', padding='same'))\nmodel.add(tf.keras.layers.BatchNormalization())\nmodel.add(tf.keras.layers.MaxPooling2D(pool_size = 2, strides = 2))\n#model.add(tf.keras.layers.Dropout(0.2))\nmodel.add(tf.keras.layers.AlphaDropout(0.25))\n\nmodel.add(tf.keras.layers.Conv2D(filters = 64, kernel_size = 3, strides = 1, activation = 'selu', kernel_initializer='glorot_normal', padding='same'))\nmodel.add(tf.keras.layers.Conv2D(filters = 64, kernel_size = 3, strides = 1, activation = 'selu', kernel_initializer='glorot_normal', padding='same'))\nmodel.add(tf.keras.layers.BatchNormalization())\nmodel.add(tf.keras.layers.MaxPooling2D(pool_size = 2, strides = 2))\nmodel.add(tf.keras.layers.AlphaDropout(0.25))\n#model.add(tf.keras.layers.Dropout(0.2))\n\nmodel.add(tf.keras.layers.Flatten())\nmodel.add(tf.keras.layers.Dense(units = 1024, activation = 'relu'))\nmodel.add(tf.keras.layers.Dense(units = 10, activation = 'softmax'))\n\nmodel.compile(optimizer = tf.keras.optimizers.RMSprop(lr=0.001, rho=0.9, epsilon=1e-08, decay=0.0), \n              loss = 'categorical_crossentropy', metrics = ['accuracy'])\nmodel.summary()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"reduce_lr = tf.keras.callbacks.ReduceLROnPlateau(monitor='val_loss', factor=0.2, patience=5, min_lr=0.0001)\nhistory = model.fit_generator(datagen.flow(X, y, batch_size=256), \n                              steps_per_epoch=256, epochs=50, \n                              validation_data=valid_datagen.flow(X_val, y_val),\n                              validation_steps=50,\n                              callbacks=[reduce_lr]).history","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"plt.plot(history['accuracy'])\nplt.plot(history['val_accuracy'])\nplt.title('model accuracy')\nplt.ylabel('accuracy')\nplt.xlabel('epoch')\nplt.legend(['train'], loc='upper left') # 'val'\nplt.show()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"sub = pd.DataFrame(df_test['id'], columns=['id'])\ndf_test = df_test.drop(columns=['id'])\nX_val = df_test.values.reshape(-1, 28, 28, 1) / 255\nsub['label'] = np.argmax(model.predict(tf.cast(X_val, tf.float32)), axis=1)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"sub.to_csv('/kaggle/working/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}