{"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)\nimport seaborn as sns # data visualization\nimport matplotlib.pyplot as plt\n\nfrom sklearn.model_selection import train_test_split\nfrom keras.utils.np_utils import to_categorical\n\nimport tensorflow as tf\nfrom tensorflow.keras import Sequential\nfrom tensorflow.keras.layers import Conv2D, Dropout, Dense, Flatten, BatchNormalization, MaxPooling2D,LeakyReLU\nfrom tensorflow.keras.optimizers import RMSprop,Nadam,Adadelta\nfrom tensorflow.keras.preprocessing.image import ImageDataGenerator\nfrom tensorflow.keras.callbacks import ReduceLROnPlateau, EarlyStopping\nfrom tensorflow.keras.utils import to_categorical\nfrom tensorflow.keras.regularizers import l2\n\nimport warnings\nwarnings.filterwarnings('ignore')\n\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.","execution_count":null,"outputs":[]},{"metadata":{"_uuid":"d629ff2d2480ee46fbb7e2d37f6b5fab8052498a","_cell_guid":"79c7e3d0-c299-4dcb-8224-4455121ee9b0","trusted":true},"cell_type":"code","source":"raw_train = pd.read_csv('../input/Kannada-MNIST/train.csv')\nraw_test = pd.read_csv('../input/Kannada-MNIST/test.csv')","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"num = raw_train.label.value_counts()\nsns.barplot(num.index,num)\nnumbers = num.index.values","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"x = raw_train.iloc[:, 1:].values.astype('float32') / 255\ny = raw_train.iloc[:, 0] # labels","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"x_train, x_val, y_train, y_val = train_test_split(x, y, test_size = 0.2, random_state=42)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"x_train = x_train.reshape(-1, 28, 28,1)\nx_val = x_val.reshape(-1, 28, 28,1)\ny_train = to_categorical(y_train)\ny_val = to_categorical(y_val)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"model = tf.keras.models.Sequential([\n    tf.keras.layers.Conv2D(64, (3,3), padding='same', input_shape=(28, 28, 1)),\n    tf.keras.layers.BatchNormalization(momentum=0.9, epsilon=1e-5, gamma_initializer=\"uniform\"),\n    tf.keras.layers.LeakyReLU(alpha=0.1),\n    tf.keras.layers.Conv2D(64,  (3,3), padding='same'),\n    tf.keras.layers.BatchNormalization(momentum=0.9, epsilon=1e-5, gamma_initializer=\"uniform\"),\n    tf.keras.layers.LeakyReLU(alpha=0.1),\n    tf.keras.layers.Conv2D(64,  (3,3), padding='same'),\n    tf.keras.layers.BatchNormalization(momentum=0.9, epsilon=1e-5, gamma_initializer=\"uniform\"),\n    tf.keras.layers.LeakyReLU(alpha=0.1),\n\n    tf.keras.layers.MaxPooling2D(2, 2),\n    tf.keras.layers.Dropout(0.25),\n    \n    tf.keras.layers.Conv2D(128, (3,3), padding='same'),\n    tf.keras.layers.BatchNormalization(momentum=0.9, epsilon=1e-5, gamma_initializer=\"uniform\"),\n    tf.keras.layers.LeakyReLU(alpha=0.1),\n    tf.keras.layers.Conv2D(128, (3,3), padding='same'),\n    tf.keras.layers.BatchNormalization(momentum=0.9, epsilon=1e-5, gamma_initializer=\"uniform\"),\n    tf.keras.layers.LeakyReLU(alpha=0.1),\n    tf.keras.layers.Conv2D(128, (3,3), padding='same'),\n    tf.keras.layers.BatchNormalization(momentum=0.9, epsilon=1e-5, gamma_initializer=\"uniform\"),\n    tf.keras.layers.LeakyReLU(alpha=0.1),\n    \n    tf.keras.layers.MaxPooling2D(2,2),\n    tf.keras.layers.Dropout(0.25),    \n    \n    tf.keras.layers.Conv2D(256, (3,3), padding='same'),\n    tf.keras.layers.BatchNormalization(momentum=0.9, epsilon=1e-5, gamma_initializer=\"uniform\"),\n    tf.keras.layers.LeakyReLU(alpha=0.1),\n    tf.keras.layers.Conv2D(256, (3,3), padding='same'),\n    tf.keras.layers.BatchNormalization(momentum=0.9, epsilon=1e-5, gamma_initializer=\"uniform\"),##\n    tf.keras.layers.LeakyReLU(alpha=0.1),\n\n    tf.keras.layers.MaxPooling2D(2,2),\n    tf.keras.layers.Dropout(0.25),\n    \n    \n    tf.keras.layers.Flatten(),\n    tf.keras.layers.Dense(256),\n    tf.keras.layers.LeakyReLU(alpha=0.1),\n \n    tf.keras.layers.BatchNormalization(),\n    tf.keras.layers.Dense(10, activation='softmax')\n])","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"optimizer = RMSprop(learning_rate=0.002,\n    rho=0.9,\n    momentum=0.1,\n    epsilon=1e-07,\n    centered=True,\n    name='RMSprop')\nmodel.compile(loss='categorical_crossentropy',\n              optimizer=optimizer,\n              metrics=['accuracy'])","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"batch_size = 1024\nnum_classes = 10\nepochs = 40","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"history = model.fit(x_train, y_train, batch_size=batch_size,\n                              epochs=15,\n                              validation_data=(x_val, y_val))","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"plt.plot(history.history['accuracy'])\nplt.plot(history.history['val_accuracy'])\nplt.title('Model accuracy')\nplt.ylabel('Accuracy')\nplt.xlabel('Epoch')\nplt.legend(['Train', 'Validation'], loc='upper left')\nplt.show()\n\n# Plot training & validation loss values\nplt.plot(history.history['loss'])\nplt.plot(history.history['val_loss'])\nplt.title('Model loss')\nplt.ylabel('Loss')\nplt.xlabel('Epoch')\nplt.legend(['Train', 'Validation'], loc='upper left')\nplt.show()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"sample_sub=pd.read_csv('../input/Kannada-MNIST/sample_submission.csv')\nraw_test = pd.read_csv('../input/Kannada-MNIST/test.csv')\nraw_test_id=raw_test.id\nraw_test=raw_test.drop(\"id\",axis=\"columns\")\nraw_test=raw_test / 255\ntest=raw_test.values.reshape(-1,28,28,1)\ntest.shape","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"sub=model.predict(test)     ##making prediction\nsub=np.argmax(sub,axis=1) ##changing the prediction intro labels\n\nsample_sub['label']=sub\nsample_sub.to_csv('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}