{"cells":[{"metadata":{"_uuid":"d629ff2d2480ee46fbb7e2d37f6b5fab8052498a","_cell_guid":"79c7e3d0-c299-4dcb-8224-4455121ee9b0","trusted":true},"cell_type":"code","source":"import numpy as np\nimport pandas as pd\nimport tensorflow as tf","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"from tensorflow.keras.models import Sequential\nfrom tensorflow.keras.layers import Convolution2D,Conv2D,MaxPooling2D,Input,Dense,\\\nActivation, LeakyReLU, Flatten, Dropout, BatchNormalization\nfrom tensorflow.keras.optimizers import Adam\nfrom PIL import Image\nimport matplotlib.pyplot as plt\nfrom tensorflow.keras.callbacks import LearningRateScheduler,ModelCheckpoint,EarlyStopping\nfrom tensorflow.keras.preprocessing.image import ImageDataGenerator\nimport math\nfrom sklearn.model_selection import train_test_split\nimport random","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"train_datas=pd.read_csv(\"../input/Kannada-MNIST/train.csv\")\nval_datas = pd.read_csv(\"../input/Kannada-MNIST/Dig-MNIST.csv\")","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"datas_X.shape","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"datas = pd.concat([train_datas,val_datas],axis=0)\nprint(datas.shape)\ndatas_X = np.array(datas.drop(\"label\",axis=1),dtype=np.float32)\ndatas_Y = np.array(datas[[\"label\"]],dtype=np.int32)\ntrain_X,val_X,train_Y,val_Y = train_test_split(datas_X,datas_Y,test_size=0.2,shuffle=True)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"train_X.shape","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"train_X = train_X  / 255.0\nval_X = val_X  / 255.0\n\ntrain_X = np.reshape(train_X,(-1,28,28,1))\nval_X = np.reshape(val_X,(-1,28,28,1))","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"from tensorflow.keras.layers import Activation,GlobalAveragePooling2D","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":" \n\n#nets = 3\n\n\nmodel = Sequential()\nmodel.add(Conv2D(64, (7,7), padding='same',activation='relu', input_shape=(28, 28, 1)))\nmodel.add(BatchNormalization())\n# block 1\nmodel.add(Conv2D(128,  (3,3), padding='same',activation='relu'))\nmodel.add(BatchNormalization())\nmodel.add(Dropout(0.1))\nmodel.add(Conv2D(128,  (3,3), padding='same',activation='relu'))\nmodel.add(BatchNormalization())\n\nmodel.add(MaxPooling2D(2, 2))\nmodel.add(Conv2D(256,  (1,1), padding='same',activation='relu'))\nmodel.add(BatchNormalization())\nmodel.add(Dropout(0.2))\n# Block 2\nmodel.add(Conv2D(256, (3,3), padding='same',activation='relu'))\nmodel.add(BatchNormalization())\n\nmodel.add(Conv2D(512, (3,3), padding='same',activation='relu'))\nmodel.add(BatchNormalization())\n\nmodel.add(Dropout(0.3))\nmodel.add(Conv2D(512, (1,1), padding='same',activation='relu'))\nmodel.add(BatchNormalization())\nmodel.add(Dropout(0.1))\nmodel.add(Conv2D(128, (5,5), padding='same',activation='relu'))\nmodel.add(BatchNormalization())\n\nmodel.add(GlobalAveragePooling2D())\nmodel.add(Dense(256,activation='relu'))\nmodel.add(Dropout(0.2))\nmodel.add(Dense(64,activation='relu'))\nmodel.add(Dense(10, activation='softmax'))\nmodel.compile(optimizer='adam', loss=\"sparse_categorical_crossentropy\",metrics=[\"accuracy\"])\nprint(model.summary())","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"datagen = ImageDataGenerator(\n    rotation_range = 20,\n    width_shift_range = 0.3,\n    height_shift_range = 0.3,\n    shear_range = 0.2,\n    zoom_range = 0.3,\n    horizontal_flip = False)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"annealer = LearningRateScheduler(lambda x: 0.008 * 0.95 ** x)\nepochs = 10\nbatch_size = 128","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"model.fit_generator(datagen.flow(train_X,train_Y, batch_size=batch_size),\n        epochs = epochs, steps_per_epoch = math.ceil(train_X.shape[0]*1.0/batch_size),  \n        validation_data = (val_X,val_Y), callbacks=[annealer],verbose=1)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"\ntest_csv = pd.read_csv(\"../input/Kannada-MNIST/test.csv\")","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"test_csv.shape","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"\n\ndata_test = np.array(test_csv.drop(\"id\",axis=1),dtype=np.float32)\ndata_test = np.reshape(data_test,(-1,28,28,1))\nX_test = data_test / 255.0\n#X_test = data_test\nprint(X_test.shape,X_test.dtype)\n\n","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"results = np.zeros( (X_test.shape[0],10))\nresults = model.predict(X_test)\nresults = np.argmax(results,axis = 1)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"submission = pd.read_csv(\"../input/Kannada-MNIST/sample_submission.csv\")\nsubmission['label'] = results\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}