{"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\n%matplotlib inline\n\nfrom keras.models import Sequential\nfrom keras.layers.core import  Lambda , Dense, Flatten, Dropout\nfrom keras.callbacks import EarlyStopping\nfrom keras.layers import BatchNormalization, Convolution2D , MaxPooling2D\nfrom keras.optimizers import Adam ,RMSprop\nfrom sklearn.model_selection import train_test_split\nfrom keras import  backend as K\nfrom keras.preprocessing.image import ImageDataGenerator\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":"train = pd.read_csv(\"/kaggle/input/Kannada-MNIST/train.csv\")\nprint('Train:', train.shape)\ntest = pd.read_csv('/kaggle/input/Kannada-MNIST/test.csv')\nprint('Test:', test.shape)\nX_train = (train.iloc[:,1:].values)\ny_train = train.iloc[:,0].values\nX_test = (test.iloc[:,1:].values)\nX_train = X_train.reshape(X_train.shape[0], 28, 28,1)\nprint('X_train:', X_train.shape)\nX_test = X_test.reshape(X_test.shape[0], 28, 28,1)\nprint('X_test:', X_test.shape)\nfrom keras.utils.np_utils import to_categorical\ny_train= to_categorical(y_train)\nprint('y_train:', y_train.shape)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"from sklearn.model_selection import train_test_split\nfrom keras.preprocessing import image\n\nX_train, X_val, y_train, y_val = train_test_split(X_train, y_train, test_size=0.05, random_state=42)\nprint('train size: ', X_train.shape)\nprint('val size: ', X_val.shape)\ngen =ImageDataGenerator(rescale=1/255., rotation_range=8, width_shift_range=0.08, shear_range=0.3,\n                               height_shift_range=0.08, zoom_range=0.08)\n\nval_gen = image.ImageDataGenerator(rescale=1/255.)\n\nbatches = gen.flow(X_train, y_train, batch_size=64)\nval_batches = val_gen.flow(X_val, y_val, batch_size=64)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"model = Sequential([\n    Convolution2D(32,(3,3), activation='relu', input_shape=(28,28,1)),\n    BatchNormalization(axis=1),\n    Convolution2D(32,(3,3), activation='relu'),\n    MaxPooling2D(),\n    BatchNormalization(axis=1),\n    Convolution2D(64,(3,3), activation='relu'),\n    BatchNormalization(axis=1),\n    Convolution2D(64,(3,3), activation='relu'),\n    MaxPooling2D(),\n    Flatten(),\n    BatchNormalization(),\n    Dense(512, activation='relu'),\n    BatchNormalization(),\n    Dense(10, activation='softmax')\n    ])\nmodel.summary()\nmodel.compile(Adam(lr=0.01), loss='categorical_crossentropy', metrics=['acc'])","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"history=model.fit_generator(generator=batches, steps_per_epoch=batches.n, epochs=3, validation_data=val_batches, validation_steps=val_batches.n)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"acc      = history.history[     'acc' ]\nval_acc  = history.history[ 'val_acc' ]\nloss     = history.history[    'loss' ]\nval_loss = history.history['val_loss' ]\n\nepochs   = range(len(acc)) # Get number of epochs\n\nplt.plot  ( epochs,     acc )\nplt.plot  ( epochs, val_acc )\nplt.title ('Training and validation accuracy')\nplt.figure()\n\nplt.plot  ( epochs,     loss )\nplt.plot  ( epochs, val_loss )\nplt.title ('Training and validation loss'   )","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"test_batches = val_gen.flow(X_test, shuffle=False, batch_size=1)\npredictions = model.predict_generator(test_batches, steps=X_test.shape[0])","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"submissions=pd.DataFrame({\"ImageId\": list(range(1,len(predictions)+1)), \"Label\": np.argmax(predictions, axis=1)})\nprint(submissions)\nsubmissions.to_csv(\"submission.csv\", index=False, header=True)","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}