VNext icon indicating copy to clipboard operation
VNext copied to clipboard

Published 20 hours ago • verified publisher icon wjf5203

Seqformer pretrained models

Open lywang76 opened this issue 2 years ago • 1 comments

Hello, can you provide the pre-trained models of SeqFormer?

Thanks,

lywang76 avatar Aug 20 '22 00:08 lywang76

Hello, can you provide the pre-trained models of SeqFormer?

Thanks,

https://github.com/wjf5203/SeqFormer

There are some models, but detectron2 is not used in this project and may not be used directly by SeqFormer in VNext. I have tried to reason with these models, but the following error appears: Missing the key (s) in state_dict: "detr. Transformer. The decoder. The layers. 0. Self_attn_attention_weights. Weight", you can try if you can run successfully.

unihornWwan avatar Dec 23 '22 06:12 unihornWwan