SimMIMMaskGenerator

class mmpretrain.datasets.transforms.SimMIMMaskGenerator(input_size=192, mask_patch_size=32, model_patch_size=4, mask_ratio=0.6)

Generate random block mask for each Image.

Added Keys:

• mask

This module is used in SimMIM to generate masks.

Parameters:

• input_size (int) – Size of input image. Defaults to 192.

• mask_patch_size (int) – Size of each block mask. Defaults to 32.

• model_patch_size (int) – Patch size of each token. Defaults to 4.

• mask_ratio (float) – The mask ratio of image. Defaults to 0.6.

transform(results)

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

Parameters:

results (dict) – Result dict from previous pipeline.

Returns:

Result dict with added key mask.

Return type:

dict