TorchVisionWrapper¶

class mmocr.datasets.transforms.TorchVisionWrapper(op, **kwargs)[source]¶

A wrapper around torchvision transforms. It applies specific transform to img and updates height and width accordingly.

Required Keys:

img (ndarray): The input image.

Modified Keys:

img (ndarray): The modified image.
img_shape (tuple(int, int)): The shape of the image in (height, width).

Warning

This transform only affects the image but not its associated annotations, such as word bounding boxes and polygons. Therefore, it may only be applicable to text recognition tasks.

Parameters

op (str) – The name of any transform class in torchvision.transforms().
**kwargs – Arguments that will be passed to initializer of torchvision transform.

Return type

None

transform(results)[source]¶

Transform the image.

Parameters: results (dict) – Result dict from the data loader.
Returns: Transformed results.
Return type: dict