Class SlidingCrop

utils/joint_transforms.py:202–245

class SlidingCrop(object):
    def __init__(self, crop_size, stride_rate, ignore_label):
        self.crop_size = crop_size
        self.stride_rate = stride_rate
        self.ignore_label = ignore_label

    def _pad(self, img, mask):
        h, w = img.shape[: 2]
        pad_h = max(self.crop_size - h, 0)
        pad_w = max(self.crop_size - w, 0)
        img = np.pad(img, ((0, pad_h), (0, pad_w), (0, 0)), 'constant')
        mask = np.pad(mask, ((0, pad_h), (0, pad_w)), 'constant', constant_values=self.ignore_label)
        return img, mask, h, w

    def __call__(self, img, mask):
        assert img.size == mask.size

        w, h = img.size
        long_size = max(h, w)

        img = np.array(img)
        mask = np.array(mask)

        if long_size > self.crop_size:
            stride = int(math.ceil(self.crop_size * self.stride_rate))
            h_step_num = int(math.ceil((h - self.crop_size) / float(stride))) + 1
            w_step_num = int(math.ceil((w - self.crop_size) / float(stride))) + 1
            img_slices, mask_slices, slices_info = [], [], []
            for yy in range(h_step_num):
                for xx in range(w_step_num):
                    sy, sx = yy * stride, xx * stride
                    ey, ex = sy + self.crop_size, sx + self.crop_size
                    img_sub = img[sy: ey, sx: ex, :]
                    mask_sub = mask[sy: ey, sx: ex]
                    img_sub, mask_sub, sub_h, sub_w = self._pad(img_sub, mask_sub)
                    img_slices.append(Image.fromarray(img_sub.astype(np.uint8)).convert('RGB'))
                    mask_slices.append(Image.fromarray(mask_sub.astype(np.uint8)).convert('P'))
                    slices_info.append([sy, ey, sx, ex, sub_h, sub_w])
            return img_slices, mask_slices, slices_info
        else:
            img, mask, sub_h, sub_w = self._pad(img, mask)
            img = Image.fromarray(img.astype(np.uint8)).convert('RGB')
            mask = Image.fromarray(mask.astype(np.uint8)).convert('P')
            return [img], [mask], [[0, sub_h, 0, sub_w, sub_h, sub_w]]