mindformers.models.mae.ViTMAEImageProcessor¶

class mindformers.models.mae.ViTMAEImageProcessor(size=224, patch_size=16, mask_ratio=0.75)[源代码]¶

ViTMAEImageProcessor.

参数: image_resolution (int) – the target size.

preprocess(images, **kwargs)[源代码]¶

Preprocess required by base processor.

参数: images (tensor, PIL.Image, numpy.array, list) – a batch of images.
返回: A 4-rank tensor for a batch of images.