{"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\n\nimport numpy as np # linear algebra\nimport pandas as pd # data processing, CSV file I/O (e.g. pd.read_csv)\nimport tensorflow as tf\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_data = pd.read_csv(\"/kaggle/input/Kannada-MNIST/train.csv\")\ntest_data = pd.read_csv(\"/kaggle/input/Kannada-MNIST/test.csv\")\nval_data = pd.read_csv(\"/kaggle/input/Kannada-MNIST/Dig-MNIST.csv\")","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"train_data.shape, val_data.shape, test_data.shape","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"train_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":"label_train = train_data[\"label\"]\ntrain_data = train_data.drop(\"label\", axis= 1)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"label_val = val_data[\"label\"]\nval_data = val_data.drop(\"label\", axis=1)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"test_data = test_data.drop(\"id\", axis=1)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"train_data.shape, val_data.shape, test_data.shape","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"train_data = train_data / 255.0\nval_data = val_data / 255.0\ntest_data = test_data / 255.0","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"train_data = train_data.values.reshape(-1,28,28,1)\nval_data = val_data.values.reshape(-1,28,28,1)\ntest_data = test_data.values.reshape(-1,28,28,1)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"train_data.shape, val_data.shape, test_data.shape","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"def build_model():\n    model = tf.keras.models.Sequential()\n    \n    model.add(tf.keras.layers.Conv2D(filters = 32, kernel_size = (5,5), activation = \"relu\",\n                                    input_shape = (28,28,1), padding = \"same\"))\n    model.add(tf.keras.layers.BatchNormalization())\n    model.add(tf.keras.layers.Conv2D(filters = 32, kernel_size = (5,5), activation = \"relu\", padding = \"same\"))\n    #model.add(tf.keras.layers.BatchNormalization())\n    model.add(tf.keras.layers.MaxPool2D(pool_size = (2,2)))\n    model.add(tf.keras.layers.Dropout(0.25))\n\n    model.add(tf.keras.layers.Conv2D(filters = 64, kernel_size = (3,3), activation = \"relu\", padding = \"same\"))\n    model.add(tf.keras.layers.BatchNormalization())\n    model.add(tf.keras.layers.Conv2D(filters = 64, kernel_size = (3,3), activation = \"relu\", padding = \"same\"))\n    #model.add(tf.keras.layers.BatchNormalization())\n    model.add(tf.keras.layers.MaxPool2D(pool_size = (2,2)))\n    model.add(tf.keras.layers.Dropout(0.25))\n    \n    model.add(tf.keras.layers.Conv2D(filters = 128, kernel_size = (3,3), activation = \"relu\", padding = \"same\"))\n    model.add(tf.keras.layers.BatchNormalization())\n    model.add(tf.keras.layers.Conv2D(filters = 128, kernel_size = (3,3), activation = \"relu\", padding = \"same\"))\n    #model.add(tf.keras.layers.BatchNormalization())\n    model.add(tf.keras.layers.MaxPool2D(pool_size = (2,2)))\n    model.add(tf.keras.layers.Dropout(0.25))\n    \n    model.add(tf.keras.layers.Flatten())\n    model.add(tf.keras.layers.Dense(units = 256, activation = \"relu\"))\n    model.add(tf.keras.layers.Dropout(0.25))\n    model.add(tf.keras.layers.Dense(units = 10, activation = \"softmax\"))\n              \n    return model\n","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"label_train = tf.keras.utils.to_categorical(label_train, num_classes=10)\nlabel_val = tf.keras.utils.to_categorical(label_val, num_classes= 10)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"model = build_model()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"model.summary()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"model.compile(optimizer= \"adam\", loss= \"categorical_crossentropy\", metrics= [\"accuracy\"])","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"learn_rate_red = tf.keras.callbacks.ReduceLROnPlateau(monitor=\"val_loss\", verbose=1, patience=3, factor= 0.3,\n                                                     min_lr= 0.00001)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"history = model.fit(train_data, label_train, validation_data= (val_data, label_val), batch_size= 64, \n          epochs= 3, callbacks= [learn_rate_red])","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"import matplotlib.pyplot as plt","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"plt.plot(history.history['loss'], color='b')\nplt.plot(history.history['val_loss'], color='r')\nplt.show()\nplt.plot(history.history['accuracy'], color='b')\nplt.plot(history.history['val_accuracy'], color='r')\nplt.show()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"pred = model.predict(test_data)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"pred.shape","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"pred = np.argmax(pred, axis=1)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"pred_df = pd.DataFrame(data= pred)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"pred_df.head()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"pred_df = pred_df.reset_index()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"pred_df.columns = [\"id\", \"label\"]","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"pred_df.head()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"pred_df.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":4}