pytorch-image-models icon indicating copy to clipboard operation
pytorch-image-models copied to clipboard

[FEATURE] Feature only support for Twins-PVT and Mvitv2

Open L-Reichardt opened this issue 2 years ago • 1 comments

Both are pyramid networks and can be used for multi-scale feature extraction, but to my knowledge do not support it like similar architectures such as PVT or Swin.

L-Reichardt avatar Dec 18 '23 09:12 L-Reichardt

@L-Reichardt the efficient mechanism for feature extraction relies on sequential stack at the stage level of the pyramid network, many pure vit / vit-hybrid need nn.ModuleList (and have extra args) or have extra root level modules in the model that can't be sequentialized... I have a very rough draft for another approach that'd address these but have another project in the way right now...

rwightman avatar Feb 16 '24 16:02 rwightman