72%

homework1.py

def homework(train_X, train_y, test_X):
    import keras
    from keras.models import Sequential
    from keras.layers import Dense, Conv2D, MaxPooling2D, Flatten, Input, Activation, Dropout
    from keras.layers.normalization import BatchNormalization
    from keras import optimizers
    from keras.preprocessing.image import ImageDataGenerator

    gcn_whitening = ImageDataGenerator(samplewise_center=True, samplewise_std_normalization=True)
    gcn_whitening.fit(train_X)

    model = Sequential()

    model.add(Conv2D(3, kernel_size=(3, 3), activation='relu', input_shape=(32, 32, 3)))
    model.add(BatchNormalization())

    for i in range(3):
        model.add(Conv2D(32, kernel_size=(3, 3), activation='relu'))
        model.add(MaxPooling2D(pool_size=(2, 2)))
        model.add(BatchNormalization())

    model.add(Flatten())
    model.add(Dense(units=512, activation='relu'))
    model.add(Dropout(0.25))
    model.add(Dense(10, activation='softmax'))
    
    model.compile(loss=keras.losses.categorical_crossentropy, optimizer='adam')
    model.fit(x=train_X, y=train_y, batch_size=128, epochs=100, validation_split=0.1)

    pred_y = model.predict(test_X)
    pred_y = np.argmax(pred_y, 1)
    
    return pred_y