{"cells":[{"metadata":{"_uuid":"8f2839f25d086af736a60e9eeb907d3b93b6e0e5","_cell_guid":"b1076dfc-b9ad-4769-8c92-a6c4dae69d19","trusted":true},"cell_type":"code","source":"import numpy as np\nimport pandas as pd \nimport matplotlib.pyplot as plt\nfrom warnings import filterwarnings\nfilterwarnings(\"ignore\")\n\nimport os\nfor dirname, _, filenames in os.walk('/kaggle/input'):\n    for filename in filenames:\n        print(os.path.join(dirname, filename))\n","execution_count":null,"outputs":[]},{"metadata":{"_uuid":"d629ff2d2480ee46fbb7e2d37f6b5fab8052498a","_cell_guid":"79c7e3d0-c299-4dcb-8224-4455121ee9b0","trusted":true},"cell_type":"code","source":"train_data = pd.read_csv(\"/kaggle/input/digit-recognizer/train.csv\")\ntest_data = pd.read_csv(\"/kaggle/input/digit-recognizer/test.csv\")\ntrain_data.head()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"test_data.head()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"train_data.info()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"pd.get_dummies(train_data[\"label\"]).values","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"train_data_labels = pd.get_dummies(train_data[\"label\"]).values\ntrain_data_pixels = (train_data.iloc[:,1:].values)/255.0\ntest_data_pixels = (test_data.values)/255.0","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"train_data_labels","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"train_data_pixels = train_data_pixels.reshape(-1,28,28,1)\ntest_data_pixels = test_data_pixels.reshape(-1,28,28,1)\n#train_data_pixels[:1]","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"from sklearn.model_selection import train_test_split\nfrom sklearn.metrics import confusion_matrix, accuracy_score\n\nx_train,x_test,y_train,y_test = train_test_split(train_data_pixels,train_data_labels,test_size=0.2,random_state=42)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"x_train.shape","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"y_train.shape","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"fig, ax = plt.subplots(5,5,sharex=True,sharey=True)\nfig.subplots_adjust(left=0, right=1, top=1, bottom=0, wspace=0, hspace=1)\nfor f in range(5):\n    for g in range(5):\n        ranran = np.random.randint(0,len(x_train))\n        ax[f,g].imshow(x_train[ranran].reshape(28,28),cmap=\"gray\")\n        ax[f,g].set_title(\"Label:{}\".format(y_train[ranran].argmax(-1)))\n        ax[f,g].axis(\"off\")\n        ax[f,g].axis(\"tight\")\n        ax[f,g].axis(\"image\")","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"from keras.models import Sequential\nfrom keras.layers import Conv2D, MaxPool2D, Dropout, SpatialDropout2D, BatchNormalization, Input, Activation, Dense, Flatten\nfrom keras.optimizers import Adam, RMSprop\nfrom keras.callbacks import ReduceLROnPlateau\nfrom keras.preprocessing.image import ImageDataGenerator\nfrom keras.utils import plot_model\n\ndef build_model():\n        model = Sequential()\n        \n        model.add(Input(shape=(28,28,1,)))\n\n        model.add(Conv2D(filters=64,kernel_size=(3,3),padding=\"same\"))\n        model.add(Activation(\"relu\"))\n        model.add(BatchNormalization())\n        model.add(SpatialDropout2D(0.25))\n        \n        model.add(Conv2D(filters=64,kernel_size=(6,6),padding=\"same\"))\n        model.add(Activation(\"relu\"))\n        model.add(BatchNormalization())\n        \n        model.add(Conv2D(filters=64,kernel_size=(3,3),padding=\"same\"))\n        model.add(Activation(\"relu\"))\n        model.add(BatchNormalization())\n        model.add(SpatialDropout2D(0.25))\n        \n        model.add(MaxPool2D(pool_size=(2,2)))\n        model.add(Dropout(0.25))\n        \n        model.add(Conv2D(filters=128,kernel_size=(3,3),padding=\"same\"))\n        model.add(Activation(\"relu\"))\n        model.add(BatchNormalization())\n        model.add(SpatialDropout2D(0.25))\n        \n        model.add(Conv2D(filters=128,kernel_size=(6,6),padding=\"same\"))\n        model.add(Activation(\"relu\"))\n        model.add(BatchNormalization())\n        \n        model.add(Conv2D(filters=128,kernel_size=(3,3),padding=\"same\"))\n        model.add(Activation(\"relu\"))\n        model.add(BatchNormalization())\n        model.add(SpatialDropout2D(0.25))\n        \n        model.add(MaxPool2D(pool_size=(2,2)))\n        model.add(Dropout(0.25))\n        \n        model.add(Conv2D(filters=256,kernel_size=(3,3),padding=\"same\"))\n        model.add(Activation(\"relu\"))\n        model.add(BatchNormalization())\n        model.add(SpatialDropout2D(0.25))\n        \n        model.add(Conv2D(filters=256,kernel_size=(6,6),padding=\"same\"))\n        model.add(Activation(\"relu\"))\n        model.add(BatchNormalization())\n        \n        model.add(Conv2D(filters=256,kernel_size=(3,3),padding=\"same\"))\n        model.add(Activation(\"relu\"))\n        model.add(BatchNormalization())\n        model.add(SpatialDropout2D(0.25))\n        \n        model.add(MaxPool2D(pool_size=(2,2),strides=(2,2),padding=\"same\"))\n        model.add(Dropout(0.25))\n        \n        model.add(Conv2D(filters=32,kernel_size=(2,2),padding=\"same\"))\n        model.add(Activation(\"relu\"))\n        model.add(BatchNormalization())\n        model.add(SpatialDropout2D(0.25))\n        \n        \n        model.add(Flatten())\n        \n        model.add(Dense(256))\n        model.add(Activation(\"relu\"))\n        model.add(BatchNormalization())\n        model.add(Dropout(0.25))\n        \n        model.add(Dense(10))\n        model.add(Activation(\"softmax\"))\n        \n        optimizer = RMSprop(lr=0.001, rho=0.9, epsilon=1e-08, decay=0.0)\n        model.compile(optimizer = optimizer ,metrics=[\"accuracy\"], loss = \"categorical_crossentropy\")\n        \n        return model","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"model = build_model()\nplot_model(model,show_shapes=True,show_layer_names=True)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"train_image_generator = ImageDataGenerator(\n    featurewise_center=False,\n    samplewise_center=False,\n    featurewise_std_normalization=False,\n    samplewise_std_normalization=False,\n    zca_whitening=False,\n    zca_epsilon=1e-06,\n    rotation_range=10,\n    width_shift_range=0.1,\n    height_shift_range=0.1,\n    brightness_range=None,\n    shear_range=0.1,\n    zoom_range=0.1,\n    channel_shift_range=0.0,\n    fill_mode=\"nearest\",\n    cval=0.0,\n    horizontal_flip=False,\n    vertical_flip=False,\n    rescale=None,\n    preprocessing_function=None,\n    data_format=None,\n    validation_split=0.0,\n    dtype=None,\n)\ntrain_image_generator.fit(x_train)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"callback_lr = ReduceLROnPlateau(monitor='val_acc',patience=2,factor=0.5,min_lr=0.00001,verbose=1)\nepochs = 50\nbatch_size = 256\nhistory = model.fit_generator(train_image_generator.flow(x_train,y_train, batch_size=batch_size),\n                              epochs = epochs, validation_data = (x_test,y_test),\n                              verbose = 1, steps_per_epoch=x_train.shape[0] // batch_size\n                              , callbacks=[callback_lr])","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"model.fit(x_test,y_test,epochs=10,batch_size=512,validation_data=(x_train,y_train),callbacks=[callback_lr])","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"ypred = model.predict(test_data_pixels)\nypred = ypred.argmax(-1)\nsubimageid = [x for x in range(1,len(test_data_pixels)+1)]\nsubmission = pd.DataFrame({\"ImageId\":subimageid,\"Label\":ypred})\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":4}