swin layer

[ByL&YY]

In swin transformer, self attention module conclude two subnet, one is simple windows self attention, another is shifted windows.in that code, in normal first windows self attention, there is no attn_mask, second shifted windows have mask. but in your code, seemly every self-attention layers have the attn_mask. that means every swin layer dont have windows self-attn, instead by all shifted windows in every layer? thank you

[Jingyun Liang]

For non-shift layers, we set attn_mask=None. See

SwinIR/models/network_swinir.py

Line 211 in 5bd10ce

 attn_mask = None 

[Jingyun Liang]

Feel free to open it if you have more questions.