小编doy*_*yle的帖子

我有从512x512图像制作补丁的问题.我试图用stride 32提取64x64补丁,这是补丁wid大小的一半.

我发现scikit-learn extract_patches_2d函数可以从原始图像中提取2d补丁.

当我使用这个功能时,似乎功能提取补丁步幅1.

有什么方法可以提取32个补丁吗？

def load_train_data(self):
    imgs_row, imgs_col = 512,512
    train_list = []
    train_img = []
    label_list = []
    label_img = []
    train_path = 'C:\\Users\\Lee Doyle\\unet\\data\\Train'
    label_path = 'C:\\Users\\Lee Doyle\\unet\\data\\Label'

    ######################Traindata################################

    print('-' * 30)
    print('load train images...')
    print('-' * 30)
    for i in glob.glob(train_path + '/*.[tT][iI][fF]'):
        train_list.append(abspath(i))
    print(len(train_list))
    for i in train_list:
        # print(i)
        img = cv2.imread(i, cv2.IMREAD_GRAYSCALE)
        # img=cv2.resize(img,(512,512))

        #train_img = image.extract_patches_2d(img, (64,64))

        train_img.append(img.astype(np.float32)/255.0)
        #train_img.append(img.astype(np.float32)/255.0)

    train_img = image.extract_patches_2d(img, (64,64))

    train_img = np.array(train_img[i])

谢谢您的帮助!