{"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_minor":4,"nbformat":4,"cells":[{"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)\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 20GB 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","metadata":{"_uuid":"8f2839f25d086af736a60e9eeb907d3b93b6e0e5","_cell_guid":"b1076dfc-b9ad-4769-8c92-a6c4dae69d19","execution":{"iopub.status.busy":"2022-05-09T13:45:14.399962Z","iopub.execute_input":"2022-05-09T13:45:14.400743Z","iopub.status.idle":"2022-05-09T13:45:14.409997Z","shell.execute_reply.started":"2022-05-09T13:45:14.400693Z","shell.execute_reply":"2022-05-09T13:45:14.409103Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"from __future__ import print_function\nimport keras\nfrom keras.datasets import cifar10\nfrom keras.preprocessing.image import ImageDataGenerator\nfrom keras.models import Sequential\nfrom keras.layers import Dense, Dropout, Activation, Flatten\nfrom keras.layers import Conv2D, MaxPooling2D\nimport os\n\nimport numpy as np\n\nimport seaborn as sns\nimport matplotlib\nimport matplotlib.pyplot as plt\n\nfrom sklearn.metrics import confusion_matrix, classification_report\nimport itertools\nfrom keras.callbacks import ReduceLROnPlateau\n\n\n%matplotlib inline","metadata":{"execution":{"iopub.status.busy":"2022-05-09T13:45:14.411548Z","iopub.execute_input":"2022-05-09T13:45:14.411964Z","iopub.status.idle":"2022-05-09T13:45:14.421765Z","shell.execute_reply.started":"2022-05-09T13:45:14.411924Z","shell.execute_reply":"2022-05-09T13:45:14.420824Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"(x_train, y_train), (x_test, y_test) = cifar10.load_data()\nprint('x_train shape:', x_train.shape)\nprint('y_train shape:', y_train.shape)\nprint(x_train.shape[0], 'train samples')\nprint(x_test.shape[0], 'test samples')","metadata":{"execution":{"iopub.status.busy":"2022-05-09T13:45:14.42347Z","iopub.execute_input":"2022-05-09T13:45:14.424026Z","iopub.status.idle":"2022-05-09T13:45:15.166318Z","shell.execute_reply.started":"2022-05-09T13:45:14.423986Z","shell.execute_reply":"2022-05-09T13:45:15.16526Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"from keras.utils import np_utils\n\n# Normalize the data. Before we need to connvert data type to float for computation.\nx_train = x_train.astype('float32')\nx_test = x_test.astype('float32')\nx_train /= 255\nx_test /= 255\n\n\nnum_classes = 10\n# Convert class vectors to binary class matrices. This is called one hot encoding.\ny_train = keras.utils.np_utils.to_categorical(y_train, num_classes)\ny_test = keras.utils.np_utils.to_categorical(y_test, num_classes)","metadata":{"execution":{"iopub.status.busy":"2022-05-09T13:45:15.16798Z","iopub.execute_input":"2022-05-09T13:45:15.168197Z","iopub.status.idle":"2022-05-09T13:45:15.424637Z","shell.execute_reply.started":"2022-05-09T13:45:15.168169Z","shell.execute_reply":"2022-05-09T13:45:15.423885Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"model = Sequential()\n\nmodel.add(Conv2D(32, (3, 3), padding = 'SAME', input_shape = x_train.shape[1:]))\nmodel.add(Activation('relu'))\n\nmodel.add(Conv2D(32, (3, 3)))\nmodel.add(Activation('relu'))\nmodel.add(MaxPooling2D(pool_size = (2, 2)))\nmodel.add(Dropout(0.25))\n\nmodel.add(Conv2D(64, (3, 3), padding = 'SAME'))\nmodel.add(Activation('relu'))\n\nmodel.add(Conv2D(64, (3, 3)))\nmodel.add(Activation('relu'))\nmodel.add(MaxPooling2D(pool_size = (2, 2)))\nmodel.add(Dropout(0.25))\n\nmodel.add(Flatten())\nmodel.add(Dense(512))\nmodel.add(Activation('relu'))\nmodel.add(Dropout(0.5))\n\nmodel.add(Dense(10))\nmodel.add(Activation('softmax'))","metadata":{"execution":{"iopub.status.busy":"2022-05-09T13:45:15.4265Z","iopub.execute_input":"2022-05-09T13:45:15.426951Z","iopub.status.idle":"2022-05-09T13:45:15.509061Z","shell.execute_reply.started":"2022-05-09T13:45:15.426911Z","shell.execute_reply":"2022-05-09T13:45:15.508436Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"from tensorflow import keras\nfrom keras import optimizers\n\nopt = keras.optimizers.Adam(learning_rate = 0.001)\n\nmodel.compile(loss = 'categorical_crossentropy',\n             optimizer = opt,\n             metrics = ['accuracy'])","metadata":{"execution":{"iopub.status.busy":"2022-05-09T13:45:15.51109Z","iopub.execute_input":"2022-05-09T13:45:15.511351Z","iopub.status.idle":"2022-05-09T13:45:15.521426Z","shell.execute_reply.started":"2022-05-09T13:45:15.511306Z","shell.execute_reply":"2022-05-09T13:45:15.520799Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"datagen = ImageDataGenerator(\n        featurewise_center=False,  \n        samplewise_center=False,   \n        zca_whitening=False,  \n        rotation_range=10,  \n        width_shift_range=0.1,\n        height_shift_range=0.1,\n        zoom_range=0.,  \n        channel_shift_range=0.,\n        horizontal_flip=True,  \n        vertical_flip=False,\n        rescale=None,\n        preprocessing_function=None,\n        data_format=None,\n        validation_split=0.0)\n\ndatagen.fit(x_train)\n","metadata":{"execution":{"iopub.status.busy":"2022-05-09T13:45:15.52291Z","iopub.execute_input":"2022-05-09T13:45:15.523236Z","iopub.status.idle":"2022-05-09T13:45:15.749551Z","shell.execute_reply.started":"2022-05-09T13:45:15.523134Z","shell.execute_reply":"2022-05-09T13:45:15.748761Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"reduceLROnPlateau = ReduceLROnPlateau(monitor='val_acc', \n                                patience=3,\n                                verbose=1, \n                                factor=0.1,\n                                min_lr=0.00001)","metadata":{"execution":{"iopub.status.busy":"2022-05-09T13:45:15.750975Z","iopub.execute_input":"2022-05-09T13:45:15.75125Z","iopub.status.idle":"2022-05-09T13:45:15.75623Z","shell.execute_reply.started":"2022-05-09T13:45:15.751211Z","shell.execute_reply":"2022-05-09T13:45:15.755136Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"model.fit_generator(datagen.flow(x_train, y_train,\n                                    batch_size=128),\n                                    epochs=5,\n                                    validation_data=(x_test, y_test),\n                                )","metadata":{"execution":{"iopub.status.busy":"2022-05-09T13:45:15.757669Z","iopub.execute_input":"2022-05-09T13:45:15.757916Z","iopub.status.idle":"2022-05-09T13:47:33.600213Z","shell.execute_reply.started":"2022-05-09T13:45:15.75788Z","shell.execute_reply":"2022-05-09T13:47:33.599509Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"y_pred = model.predict(x_test)","metadata":{"execution":{"iopub.status.busy":"2022-05-09T13:47:33.601319Z","iopub.execute_input":"2022-05-09T13:47:33.601582Z","iopub.status.idle":"2022-05-09T13:47:34.615905Z","shell.execute_reply.started":"2022-05-09T13:47:33.601532Z","shell.execute_reply":"2022-05-09T13:47:34.615111Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"","metadata":{},"execution_count":null,"outputs":[]}]}