{"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\n\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_df = pd.read_csv('/kaggle/input/digit-recognizer/train.csv')\ntest_df = pd.read_csv('/kaggle/input/digit-recognizer/test.csv')","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"from matplotlib import pyplot as plt","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"y_train = train_df.iloc[:,0]\nX_train = train_df.iloc[:,1:]\n\nX_test = test_df.copy()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"n=10\nplt.imshow(X_train.iloc[n].values.reshape(28,28))\nplt.show()\nprint(y_train[n])\n","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"X_train = X_train / 255.0\nX_test = X_test/ 255.0\n\nX_train_im = X_train.values.reshape(-1,28,28,1)\nX_test_im = X_test.values.reshape(-1,28,28,1)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"X_test_im.shape,X_train_im.shape","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"import tensorflow as tf\nfrom tensorflow import keras\nfrom tensorflow.keras.callbacks import EarlyStopping\nfrom tensorflow.keras.models import Sequential\nfrom tensorflow.keras.layers import Conv2D,MaxPooling2D,Flatten,Dense,Dropout","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"model = Sequential()\nmodel.add(Conv2D(64 , 7 ,activation='relu', padding = \"same\" ,input_shape=[28,28,1]))\nmodel.add(MaxPooling2D(2))\nmodel.add(Conv2D(128 , 3,activation='relu', padding = \"same\" ))\nmodel.add(Conv2D(128 , 3,activation='relu', padding = \"same\" ))\nmodel.add(MaxPooling2D(2))\nmodel.add(Dropout(0.25))\nmodel.add(Conv2D(256 , 3,activation='relu', padding = \"same\" ))\nmodel.add(Conv2D(256 , 3,activation='relu', padding = \"same\" ))\nmodel.add(MaxPooling2D(2))\nmodel.add(Dropout(0.25))\nmodel.add(Flatten())\nmodel.add(Dense(128,activation='elu',kernel_initializer=\"he_normal\"))\nmodel.add(Dropout(0.5))\nmodel.add(Dense(64,activation='elu',kernel_initializer=\"he_normal\",kernel_regularizer=keras.regularizers.l2(0.01)))\nmodel.add(Dropout(0.5))\nmodel.add(Dense(10,activation='softmax'))\n","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"model.summary()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"# s = 20 * len(X_train) // 32\n# learning_rate = keras.optimizers.schedules.ExponentialDecay(0.01, s, 0.1)\ndef exponential_decay(lr0, s):\n    def exponential_decay_fn(epoch):\n        return lr0 * 0.1**(epoch / s)\n    return exponential_decay_fn\n\nexponential_decay_fn = exponential_decay(lr0=0.01, s=20)\nlr_scheduler = keras.callbacks.LearningRateScheduler(exponential_decay_fn)\noptimizer=keras.optimizers.SGD(lr=0.01,momentum=0.9, nesterov=True)\nmodel.compile(loss=\"sparse_categorical_crossentropy\",optimizer=optimizer,metrics=['accuracy'])","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"checkpoint_cb = keras.callbacks.ModelCheckpoint(\"my_keras_model.h5\",save_best_only=True)\nhistory = model.fit(X_train_im, y_train, epochs=100,batch_size=32,validation_split=0.1,callbacks=[EarlyStopping(patience=8),lr_scheduler,checkpoint_cb])","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"pd.DataFrame(history.history).plot(figsize=(16, 10))\nplt.grid(True)\nplt.gca().set_ylim(0, 1) # set the vertical range to [0-1]\nplt.show()\n","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"model = keras.models.load_model(\"my_keras_model.h5\")\n","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"y_test = model.predict(X_test_im)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"submission = pd.read_csv('/kaggle/input/digit-recognizer/sample_submission.csv')","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"results = np.argmax(y_test,axis = 1)\nresults = pd.Series(results,name=\"Label\")\n\nsubmission['Label'] =results\n\nsubmission.head()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"submission.to_csv(\"cnn_mnist_datagen.csv\",index=False)\n","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":4}