{"cells":[{"metadata":{"_uuid":"8f2839f25d086af736a60e9eeb907d3b93b6e0e5","_cell_guid":"b1076dfc-b9ad-4769-8c92-a6c4dae69d19","trusted":true},"cell_type":"code","source":"\nfrom keras.datasets import cifar10\n\n#----\n# Input data files are available in the \"../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# Any results you write to the current directory are saved as output.","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"import pandas as pd\nimport keras\nimport mne\nimport numpy as np\nimport matplotlib.pyplot as plt\nfrom keras.models import Sequential\nfrom keras import backend as K \nfrom keras.constraints import maxnorm\nfrom keras.layers import Dense,Dropout,Flatten,Conv2D,MaxPooling2D\nfrom sklearn.model_selection import StratifiedKFold\nfrom sklearn.metrics import accuracy_score\nfrom keras.callbacks import EarlyStopping, ModelCheckpoint\nfrom keras.layers import Input, Dense, Conv2D, Flatten,Dropout\nfrom keras.models import Model\nfrom keras.optimizers import SGD\nfrom keras.utils import np_utils","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"from keras.datasets import cifar10\n(X_train, y_train), (X_test, y_test) = cifar10.load_data()","execution_count":null,"outputs":[]},{"metadata":{"_uuid":"d629ff2d2480ee46fbb7e2d37f6b5fab8052498a","_cell_guid":"79c7e3d0-c299-4dcb-8224-4455121ee9b0","trusted":true},"cell_type":"code","source":"# import and read data sampleSubmission using panda library\nsample = pd.read_csv(\"../input/cifar-10/sampleSubmission.csv\")\n# import and read data trainLabels using panda library\ntrain = pd.read_csv(\"../input/cifar-10/trainLabels.csv\")","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"# show informantion content in sample ()\nprint(sample.info())\n","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"\nX_train = X_train.astype('float32') \nX_test = X_test.astype('float32') \nX_train = X_train / 255.0 \nX_test = X_test / 255.0","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"y_train = np_utils.to_categorical(y_train) \ny_test = np_utils.to_categorical(y_test) \nnum_classes = y_test.shape[1]","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"model = Sequential()\nmodel.add(Conv2D(32, (3, 3), input_shape=(32,32,3), activation='relu', padding='same')) \nmodel.add(Dropout(0.2)) \nmodel.add(Conv2D(32, (3, 3), activation='relu', padding='same')) \nmodel.add(MaxPooling2D(pool_size=(2, 2))) \nmodel.add(Conv2D(64, (3, 3), activation='relu', padding='same')) \nmodel.add(Dropout(0.2)) \nmodel.add(Conv2D(64, (3, 3), activation='relu', padding='same')) \nmodel.add(MaxPooling2D(pool_size=(2, 2))) \nmodel.add(Conv2D(128, (3, 3), activation='relu', padding='same')) \nmodel.add(Dropout(0.2)) \nmodel.add(Conv2D(128, (3, 3), activation='relu', padding='same')) \nmodel.add(MaxPooling2D(pool_size=(2, 2))) \nmodel.add(Flatten()) \nmodel.add(Dropout(0.2)) \nmodel.add(Dense(1024, activation='relu', kernel_constraint=maxnorm(3))) \nmodel.add(Dropout(0.2)) \nmodel.add(Dense(512, activation='relu', kernel_constraint=maxnorm(3))) \nmodel.add(Dropout(0.2)) \nmodel.add(Dense(num_classes, activation='softmax'))\n","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"print(model.summary())","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":" epochs=10\nlrate = 0.01 \ndecay = lrate/epochs \nsgd = SGD(lr=lrate, momentum=0.9, decay=decay, nesterov=False) \nmodel.compile(loss='categorical_crossentropy', optimizer=sgd, metrics=['accuracy'])","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"model.fit(X_train, y_train, validation_data=(X_test, y_test), epochs=10, batch_size=32) \n# Final evaluation of the mode\nscores = model.evaluate(X_test, y_test, verbose=0) \nprint(\"Accuracy: %.2f%%\" % (scores[1]*100))","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"from keras.models import load_model \nmodel.save('project_model.h5')\nmodel = load_model('project_model.h5')","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"import numpy as np \nfrom keras.preprocessing import image\ntest1 =image.load_img('../input/cifar-10/test',target_size =(32,32))","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"test_image =image.img_to_array(test1) \ntest_image =np.expand_dims(test_image, axis =0) \nresult = model.predict(test_image) \nprint(result) \nif result[0][0]==1: \n    print(\"Aeroplane\") \nelif result[0][1]==1: \n    print('Automobile') \nelif result[0][2]==1: \n    print('Bird') \nelif result[0][3]==1: \n    print('Cat') \nelif result[0][4]==1: \n    print('Deer') \nelif result[0][5]==1: \n    print('Dog') \nelif result[0][6]==1: \n    print('Frog') \nelif result[0][7]==1: \n    print('Horse') \nelif result[0][8]==1: \n    print('Ship') \nelif result[0][9]==1: \n    print('Truck') \nelse: \n    print('Error')","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":1}