BEiTMaskGenerator

class mmpretrain.datasets.transforms.BEiTMaskGenerator(input_size, num_masking_patches, min_num_patches=4, max_num_patches=None, min_aspect=0.3, max_aspect=None)

Generate mask for image.

Added Keys:

• mask

This module is borrowed from https://github.com/microsoft/unilm/tree/master/beit

Parameters:

• input_size (int) – The size of input image.

• num_masking_patches (int) – The number of patches to be masked.

• min_num_patches (int) – The minimum number of patches to be masked in the process of generating mask. Defaults to 4.

• max_num_patches (int, optional) – The maximum number of patches to be masked in the process of generating mask. Defaults to None.

• min_aspect (float, optional) – The minimum aspect ratio of mask blocks. Defaults to 0.3.

• min_aspect – The minimum aspect ratio of mask blocks. Defaults to None.

transform(results)

Method to generate random block mask for each Image in BEiT.

Parameters:

results (dict) – Result dict from previous pipeline.

Returns:

Result dict with added key mask.

Return type:

dict