CenterCrop¶
- class mmpretrain.datasets.transforms.CenterCrop(crop_size, auto_pad=False, pad_cfg={'type': 'Pad'}, clip_object_border=True)[源代码]¶
裁剪一张图像的中心区域(同时处理分割图、bbox、关键点等)。如果裁剪尺寸超出原图区域,并且指定了
auto_pad=True
,则会在裁剪之前扩充原图至合适大小Required Keys:
img
gt_seg_map (optional)
gt_bboxes (optional)
gt_keypoints (optional)
Modified Keys:
img
img_shape
gt_seg_map (optional)
gt_bboxes (optional)
gt_keypoints (optional)
Added Key:
pad_shape
- 参数:
crop_size (Union[int, Tuple[int, int]]) – Expected size after cropping with the format of (w, h). If set to an integer, then cropping width and height are equal to this integer.
auto_pad (bool) – Whether to pad the image if it’s smaller than the
crop_size
. Defaults to False.pad_cfg (dict) – Base config for padding. Refer to
mmcv.Pad
for detail. Defaults todict(type='Pad')
.clip_object_border (bool) – Whether to clip the objects outside the border of the image. In some dataset like MOT17, the gt bboxes are allowed to cross the border of images. Therefore, we don’t need to clip the gt bboxes in these cases. Defaults to True.