KeyError: "EncoderDecoder: 'VisionTransformer is not in the backbone registry'"

fudan-zvg / SETR

[CVPR 2021] Rethinking Semantic Segmentation from a Sequence-to-Sequence Perspective with Transformers

MIT License

1.05k stars 150 forks source link

KeyError: "EncoderDecoder: 'VisionTransformer is not in the backbone registry'" #16

Closed amiltonwong closed 3 years ago

amiltonwong commented 3 years ago

Hi, authors,

I got this error: KeyError: "EncoderDecoder: 'VisionTransformer is not in the backbone registry'" when I run the command: python tools/train.py configs/SETR/SETR_PUP_768x768_40k_cityscapes_bs_8.py. The error in details is listed here: https://gist.github.com/amiltonwong/476e04e81e33b3cf8c4cb3f28ee01ddd

Any hints to solve this issue?

THX!

VictorLlu commented 3 years ago

This is probably resulted from the incorrect installation. Please double check whether you have correctly installed SETR. Please try the following

cd SETR && pip install -e .

amiltonwong commented 3 years ago

@VictorLlu, Thanks a lot. It works :)