get_dataset.py 文件源码

def get_dataset(dataset_path='Data/Train_Data'):
    # Getting all data from data path:
    try:
        X = np.load('Data/npy_train_data/X.npy')
        Y = np.load('Data/npy_train_data/Y.npy')
    except:
        labels = listdir(dataset_path) # Geting labels
        X = []
        Y = []
        for label in labels:
            datas_path = dataset_path+'/'+label
            for data in listdir(datas_path):
                img = get_img(datas_path+'/'+data)
                X.append(img)
                Y.append(int(label))
        # Create dateset:
        X = np.array(X).astype('float32')/255.
        Y = np.array(Y).astype('float32')
        Y = to_categorical(Y, 2)
        if not os.path.exists('Data/npy_train_data/'):
            os.makedirs('Data/npy_train_data/')
        np.save('Data/npy_train_data/X.npy', X)
        np.save('Data/npy_train_data/Y.npy', Y)
    X, X_test, Y, Y_test = train_test_split(X, Y, test_size=0.1, random_state=42)
    return X, X_test, Y, Y_test