MCPcopy Create free account
hub / github.com/OpenGVLab/UniFormerV2 / random_resized_crop

Function random_resized_crop

slowfast/datasets/transform.py:577–609  ·  view source on GitHub ↗

Crop the given images to random size and aspect ratio. A crop of random size (default: of 0.08 to 1.0) of the original size and a random aspect ratio (default: of 3/4 to 4/3) of the original aspect ratio is made. This crop is finally resized to given size. This is popularly used to

(
    images,
    target_height,
    target_width,
    scale=(0.8, 1.0),
    ratio=(3.0 / 4.0, 4.0 / 3.0),
)

Source from the content-addressed store, hash-verified

575
576
577def random_resized_crop(
578 images,
579 target_height,
580 target_width,
581 scale=(0.8, 1.0),
582 ratio=(3.0 / 4.0, 4.0 / 3.0),
583):
584 """
585 Crop the given images to random size and aspect ratio. A crop of random
586 size (default: of 0.08 to 1.0) of the original size and a random aspect
587 ratio (default: of 3/4 to 4/3) of the original aspect ratio is made. This
588 crop is finally resized to given size. This is popularly used to train the
589 Inception networks.
590
591 Args:
592 images: Images to perform resizing and cropping.
593 target_height: Desired height after cropping.
594 target_width: Desired width after cropping.
595 scale: Scale range of Inception-style area based random resizing.
596 ratio: Aspect ratio range of Inception-style area based random resizing.
597 """
598
599 height = images.shape[2]
600 width = images.shape[3]
601
602 i, j, h, w = _get_param_spatial_crop(scale, ratio, height, width)
603 cropped = images[:, :, i : i + h, j : j + w]
604 return torch.nn.functional.interpolate(
605 cropped,
606 size=(target_height, target_width),
607 mode="bilinear",
608 align_corners=False,
609 )
610
611
612def random_resized_crop_with_shift(

Callers

nothing calls this directly

Calls 1

_get_param_spatial_cropFunction · 0.85

Tested by

no test coverage detected