search

czczup / ViT-Adapter

[ICLR 2023 Spotlight] Vision Transformer Adapter for Dense Predictions
https://arxiv.org/abs/2205.08534
Apache License 2.0
1.27k stars 140 forks source link

ModuleNotFoundError: No module named 'MultiScaleDeformableAttention' #166

Open MF-XU opened 8 months ago

MF-XU commented 8 months ago

Hello author, ModuleNotFoundError: No module named 'MultiScaleDeformableAttention' is currently experiencing this issue. Is this module a py file or from the mmcv package? I couldn't find this folder while searching for files

duanduanduanyuchen commented 8 months ago

Hi, you can refer to #142 with this problem.

LQchen1 commented 8 months ago

I have the same mistake but your solution doesn't work well

LQchen1 commented 8 months ago

image

yamyCD commented 8 months ago

me,too

LQchen1 commented 8 months ago

You can try to compile it by running make.sh in the ops directory, but this script is for the cluster environment, so change the startup script according to your needs.