{"cells":[{"metadata":{"_uuid":"8f2839f25d086af736a60e9eeb907d3b93b6e0e5","_cell_guid":"b1076dfc-b9ad-4769-8c92-a6c4dae69d19","trusted":true},"cell_type":"code","source":"# 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.","execution_count":null,"outputs":[]},{"metadata":{"_uuid":"d629ff2d2480ee46fbb7e2d37f6b5fab8052498a","_cell_guid":"79c7e3d0-c299-4dcb-8224-4455121ee9b0","trusted":true},"cell_type":"code","source":"import numpy as np\nimport pandas as pd\nfrom matplotlib import pyplot as plt","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"import tensorflow\nprint(tensorflow.__version__)\nimport tensorflow.keras as keras\nprint(keras.__version__)\nfrom keras import Model, Input\nfrom keras.layers import Dense, Dropout","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"def load_data(filename):\n  data = pd.read_csv(filename)\n  y_data = data['label'].values\n  data.drop(columns=['label'], inplace=True)\n  rows, columns = 4, 4\n  _, ax = plt.subplots(nrows=rows, ncols=columns, figsize=(10, 11))\n  for i, curr_ax in enumerate(ax.flat):\n    curr_ax.imshow(np.array(data.iloc[i, :]).reshape((28, 28)))\n    curr_ax.set_title(str(y_data[i]))\n  plt.show()\n  x_data = data.values\n  return x_data, y_data","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"x_train, y_train = load_data('/kaggle/input/Kannada-MNIST/train.csv')","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"# split to train and validation sets\ntrain_coef = 0.7\ntrain_size = int(x_train.shape[0]*train_coef)\nx_train, x_valid = x_train[:train_size], x_train[train_size:]\ny_train, y_valid = y_train[:train_size], y_train[train_size:]","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"# normalize data\nx_train = x_train / 255 * 2 - 1\nx_valid = x_valid / 255 * 2 - 1","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"x = Input(shape=(784,))\ny = Dense(60, activation='relu')(x)\ny = Dense(100, activation='relu')(y)\ny = Dense(100, activation='relu')(y)\ny = Dense(10, activation='softmax')(y)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"model = Model(inputs=[x], output=[y])\nmodel.compile(optimizer='SGD', loss='sparse_categorical_crossentropy', metrics=['accuracy'])","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"model.fit(x=x_train, y=y_train, batch_size=10, verbose=1, epochs=20,\n          validation_data=(x_valid, y_valid), \n          callbacks=[keras.callbacks.CSVLogger('log.csv'), \n                     keras.callbacks.ModelCheckpoint('model.h5', save_best_only=True)])","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}