{"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\nimport tensorflow as tf\nfrom tensorflow import keras\nimport numpy as np # linear algebra\nimport pandas as pd # data processing, CSV file I/O (e.g. pd.read_csv)\nimport matplotlib.pyplot as plt\n\n# Input data files are available in the read-only \"../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# You can write up to 5GB to the current directory (/kaggle/working/) that gets preserved as output when you create a version using \"Save & Run All\" \n# You can also write temporary files to /kaggle/temp/, but they won't be saved outside of the current session","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')\nprint(train_df.shape)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"X_train = train_df.iloc[:,1:].values\ny_train = train_df.iloc[:,0].values","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"N = X_train.shape[0]\nX_train = X_train.reshape(N,28,28,1)\nX_train = X_train.astype('float32')\nX_train /= 255.\n\ny_train = tf.one_hot(y_train, 10)\nX_train.shape, y_train.shape","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"def make_model(inputs):\n    x = tf.keras.layers.Conv2D(filters=32,kernel_size=(3,3))(inputs)\n    x = tf.keras.layers.BatchNormalization()(x)\n    x = tf.keras.layers.ReLU()(x)\n    # 26,26,32\n    x = tf.keras.layers.MaxPool2D()(x)\n    # 12,12,32\n    x = tf.keras.layers.Conv2D(filters=64,kernel_size=(3,3))(x)\n    x = tf.keras.layers.BatchNormalization()(x)\n    x = tf.keras.layers.ReLU()(x)\n    # 10,10,64\n    x = tf.keras.layers.MaxPool2D()(x)\n    # 5,5,64\n    x = tf.keras.layers.Conv2D(filters=1024,kernel_size=(5,5))(x)\n    x = tf.keras.layers.BatchNormalization()(x)\n    x = tf.keras.layers.ReLU()(x)\n    #1,1,1024\n    x = tf.keras.layers.Conv2D(filters=256,kernel_size=(1,1))(x)\n    x = tf.keras.layers.BatchNormalization()(x)\n    x = tf.keras.layers.ReLU()(x)\n    #1,1,256\n    x = tf.keras.layers.Conv2D(filters=10,kernel_size=(1,1))(x)\n    x = tf.keras.layers.BatchNormalization()(x)\n    x = tf.keras.layers.Softmax()(x)\n    #1,1,10\n    x = tf.keras.layers.Reshape((10,))(x)\n    return x","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"tf.keras.backend.clear_session()\ninputs = tf.keras.Input(shape=(28,28,1))\n\noutputs = make_model(inputs)\n\nmodel = tf.keras.Model(\n    inputs=inputs,\n    outputs=outputs,\n    name=\"simple\"\n)\n\nmodel.compile(optimizer='adam', loss='categorical_crossentropy')","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"model.summary()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"history = model.fit(X_train,y_train, validation_split=0.2,epochs=10)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"X_test = pd.read_csv('/kaggle/input/digit-recognizer/test.csv').values\n\nN_test = X_test.shape[0]\nX_test = X_test.reshape(N_test,28,28,1)\nX_test = X_test.astype('float32')\nX_test /= 255.\n\nX_test.shape","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"pred = model.predict(X_test)\npred.shape","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"submissions=pd.DataFrame({\"ImageId\": list(range(1,len(pred)+1)),\n                         \"Label\": np.argmax(pred, axis=1)})\nsubmissions.to_csv(\"my_submissions.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":4}