Twins
Twins copied to clipboard
Meituan-AutoML
Two simple and effective designs of vision transformer, which is on par with the Swin transformer
Hi, In your paper table 5, the (G,G,G,G) uses the numbers (79.8%) from PVT paper, which uses absolution positional encoding. However, I suppose the other model variants listed in this...
In the **__init__** function of the PEG class, it seems that the **groups** parameter should be set to **in_chans** rather than **embed_dim**, since this is intended to be a depthwise...
Metadata
Owner
Metadata
Two simple and effective designs of vision transformer, which is on par with the Swin transformer