{"cells":[{"metadata":{"_uuid":"8f2839f25d086af736a60e9eeb907d3b93b6e0e5","_cell_guid":"b1076dfc-b9ad-4769-8c92-a6c4dae69d19","trusted":true},"cell_type":"code","source":"# This Python 3 environment comes with many helpful analytics libraries installed\n# It is defined by the kaggle/python docker image: https://github.com/kaggle/docker-python\n# For example, here's several helpful packages to load in \n\nimport numpy as np # linear algebra\nimport pandas as pd # data processing, CSV file I/O (e.g. pd.read_csv)\n\n# Input data files are available in the \"../input/\" directory.\n# For example, running this (by clicking run or pressing Shift+Enter) will list all files under the input directory\n\nimport os\nfor dirname, _, filenames in os.walk('/kaggle/input'):\n    for filename in filenames:\n        print(os.path.join(dirname, filename))\n\n# Any results you write to the current directory are saved as output.\nimport matplotlib.pyplot as plt\n\nfrom tensorflow import keras\nfrom tensorflow.keras.models import Sequential\nfrom tensorflow.keras.layers import Conv2D, Dropout, Dense, Flatten, BatchNormalization, MaxPooling2D\nfrom tensorflow.keras.optimizers import RMSprop\nfrom tensorflow.keras.preprocessing.image import ImageDataGenerator\nfrom tensorflow.keras.callbacks import ReduceLROnPlateau, EarlyStopping\nfrom tensorflow.keras.utils import to_categorical\n\nfrom sklearn.model_selection import train_test_split","execution_count":null,"outputs":[]},{"metadata":{"_uuid":"d629ff2d2480ee46fbb7e2d37f6b5fab8052498a","_cell_guid":"79c7e3d0-c299-4dcb-8224-4455121ee9b0","trusted":true},"cell_type":"code","source":"sample_submission = pd.read_csv(\"../input/Kannada-MNIST/sample_submission.csv\")\ntest = pd.read_csv(\"../input/Kannada-MNIST/test.csv\")\ntrain = pd.read_csv(\"../input/Kannada-MNIST/train.csv\")\n\nx = train.iloc[:,1:].values\ny = train.iloc[:,0].values\nx_test = test.drop('id', axis=1).iloc[:,:].values\nx = x.reshape(x.shape[0], 28, 28, 1)\ny = to_categorical(y, 10)\nx_test = x_test.reshape(x_test.shape[0], 28, 28, 1)\n\nx_train, x_valid, y_train, y_valid = train_test_split(x, y, test_size = 0.10, random_state=42) \n\ntrain_datagen = ImageDataGenerator(rescale=1./255.,\n                                   rotation_range=10,\n                                   width_shift_range=0.10,\n                                   height_shift_range=0.10,\n                                   shear_range=0.1,\n                                   zoom_range=0.1,\n                                   horizontal_flip=False)\n\nvalid_datagen = ImageDataGenerator(rescale=1./255.)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"optimizer = RMSprop(lr=0.001)\n\nmodel= Sequential()\nmodel.add(Conv2D(24,kernel_size = 3, padding = \"same\", activation = \"relu\",input_shape = (28,28,1)))\nmodel.add(Conv2D(24,kernel_size = 3, padding = \"same\", activation = \"relu\"))\nmodel.add(Conv2D(48 ,kernel_size = 5, padding = \"same\", activation = \"relu\"))          \nmodel.add(MaxPooling2D(pool_size=(2,2)))\nmodel.add(BatchNormalization(momentum=0.5, epsilon=1e-5, gamma_initializer=\"uniform\"))\nmodel.add(Dropout(0.1))\nmodel.add(Conv2D(48,kernel_size = 3, padding = \"same\", activation = \"relu\"))\nmodel.add(Conv2D(48,kernel_size = 3, padding = \"same\", activation = \"relu\"))\nmodel.add(Conv2D(96 ,kernel_size = 5, padding = \"same\", activation = \"relu\"))          \nmodel.add(MaxPooling2D(pool_size=(2,2)))\nmodel.add(BatchNormalization(momentum=0.5, epsilon=1e-5, gamma_initializer=\"uniform\"))\nmodel.add(Dropout(0.1))\nmodel.add(Conv2D(96,kernel_size = 3, padding = \"same\", activation = \"relu\"))\nmodel.add(Conv2D(96,kernel_size = 3, padding = \"same\", activation = \"relu\"))\nmodel.add(Conv2D(192 ,kernel_size = 5, padding = \"same\", activation = \"relu\"))          \nmodel.add(MaxPooling2D(pool_size=(2,2)))\nmodel.add(BatchNormalization(momentum=0.5, epsilon=1e-5, gamma_initializer=\"uniform\"))\nmodel.add(Dropout(0.1))\nmodel.add(Flatten())\nmodel.add(Dense(256))\nmodel.add(Dropout(0.2))\nmodel.add(Dense(10, activation=\"softmax\"))\nmodel.compile(optimizer=optimizer,loss='categorical_crossentropy',metrics = [\"accuracy\"])","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"\nlearning_rate_reduction= ReduceLROnPlateau(monitor='val_loss', \n                                            patience=1,\n                                            verbose=1,\n                                            factor=0.5,\n                                            min_lr=0.0001)\n\n\nearly = EarlyStopping(monitor='val_loss', min_delta=0.0005, mode='min', verbose=1, patience=2)\nhistory = model.fit_generator(train_datagen.flow(x_train, y_train, batch_size=1024),\n                                  steps_per_epoch=100,\n                                  epochs=30,\n                                  validation_data=valid_datagen.flow(x_valid, y_valid),\n                                  validation_steps=50,\n                                  callbacks=[learning_rate_reduction])","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"predictions = model.predict_classes(x_test/255.)\nsubmission = pd.read_csv('../input/Kannada-MNIST/sample_submission.csv')\nsubmission['label'] = predictions\nsubmission.to_csv(\"submission.csv\", index=False)","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}