{"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\nimport matplotlib.pyplot as plt\nfrom sklearn.preprocessing import OneHotEncoder\nfrom sklearn.model_selection import train_test_split\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 = pd.read_csv(\"/kaggle/input/Kannada-MNIST/train.csv\")\ntest = pd.read_csv(\"/kaggle/input/Kannada-MNIST/test.csv\")\ndig = pd.read_csv(\"/kaggle/input/Kannada-MNIST/Dig-MNIST.csv\")","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"train_copy = train.copy()\ntest_copy = test.copy()\ndig_copy = dig.copy()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"train_label = train[\"label\"].copy()\ntrain_img = train_copy.drop(\"label\",axis=1)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"train_img.head()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"images = train_img/255.0","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"images = np.array(images)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"labels = np.array(train_label)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"onehot = OneHotEncoder()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"labels = onehot.fit_transform(labels.reshape([-1,1]))","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"labels = labels.A","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"x_train, x_test, y_train, y_test = train_test_split(images, labels, test_size=0.3, random_state=42)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"x_train = tf.reshape(x_train,[-1,28,28,1])\nx_test = tf.reshape(x_test, [-1,28,28,1])","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":"tf.keras.backend.clear_session()\nmodel = tf.keras.models.Sequential([\n                                    tf.keras.layers.Conv2D(32,(5,5),padding=\"same\",activation=\"relu\"),\n                                    tf.keras.layers.MaxPool2D(pool_size=(2,2),strides=(2,2),padding=\"same\"),\n                                    tf.keras.layers.Conv2D(32,(5,5),padding=\"same\",activation=\"relu\"),\n                                    tf.keras.layers.MaxPool2D(pool_size=(2,2),strides=(2,2),padding=\"same\"),\n                                    tf.keras.layers.Flatten(),\n                                    tf.keras.layers.Dense(1024,activation=\"relu\"),\n                                    tf.keras.layers.Dropout(0.5),\n                                    tf.keras.layers.Dense(10,activation=\"softmax\")\n])","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"lr_schedule = tf.keras.callbacks.LearningRateScheduler(\n    lambda epoch: 1e-5 * 10**(epoch / 100))\noptimizer = tf.keras.optimizers.Adam(learning_rate=1e-8)\nmodel.compile(loss=tf.keras.losses.CategoricalCrossentropy(), optimizer=optimizer,metrics=[\"accuracy\"])\nhistory = model.fit(x_train,y_train,epochs=300,callbacks=[lr_schedule])","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"plt.figure(figsize=(16,12))\nplt.semilogx(history.history[\"lr\"],history.history[\"loss\"])\nplt.grid(True)\nplt.axis([1e-5,1e-2,0,0.025])","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"tf.keras.backend.clear_session()\nmodel = tf.keras.models.Sequential([\n                                    tf.keras.layers.Conv2D(32,(5,5),padding=\"same\",activation=\"relu\"),\n                                    tf.keras.layers.MaxPool2D(pool_size=(2,2),strides=(2,2),padding=\"same\"),\n                                    tf.keras.layers.Conv2D(32,(5,5),padding=\"same\",activation=\"relu\"),\n                                    tf.keras.layers.MaxPool2D(pool_size=(2,2),strides=(2,2),padding=\"same\"),\n                                    tf.keras.layers.Flatten(),\n                                    tf.keras.layers.Dense(1024,activation=\"relu\"),\n                                    tf.keras.layers.Dropout(0.5),\n                                    tf.keras.layers.Dense(10,activation=\"softmax\")\n])","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"optimizer = tf.keras.optimizers.Adam(learning_rate=2e-4)\nmodel.compile(loss=tf.keras.losses.CategoricalCrossentropy(),optimizer=optimizer,metrics=[\"accuracy\"])\nhistory = model.fit(x_train,y_train,epochs=300)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"model.summary()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"valid_lose = model.evaluate(x_test, y_test)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"test_images= test_copy.drop(\"id\",axis=1)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"test_images = test_images/255.0","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"test_images = tf.reshape(test_images,[-1,28,28,1])","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"test_ret = model.predict(test_images)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"predict = tf.argmax(test_ret,1)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"predict = predict.numpy()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"predict.shape","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"sunmission = pd.DataFrame({'id': test.id,'label': predict})","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"sunmission.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}