Swin-Transformer
Swin-Transformer copied to clipboard
Codes about using performer as the attetion module.
Thanks for the solid and great work. Could you release the codes of swin transformer with performer attention. I have tried to reproduce the results of Tab. 6, but the usage of attention mask for performer attention still confused me. So i will appreciate if any codes or advice can be provided.
Any updates on this issue? I'd also like to know how you apply Performer into your architecture, as shown in Table 5&6.