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

mmcv and mmsegmentation versions incompatability in Docker environment #183

Open kaavyyaashri opened 3 months ago

kaavyyaashri commented 3 months ago

I am trying to run the code in a docker container, using the pytorch image of version 1.11.0-cuda11.3-cudnn8 the error: Traceback (most recent call last):
File "SRRM.py", line 20, in from vit_adapter import build_vit_adapter File "/app/ViT-Adapter/segmentation/mmseg_custom/models/backbones/vit_adapter.py", line 8, in from mmseg.models.builder import BACKBONES File "/opt/conda/lib/python3.8/site-packages/mmseg/init.py", line 61, in assert (mmcv_min_version <= mmcv_version < mmcv_max_version), \ AssertionError: MMCV==2.2.0 is used but incompatible. Please install mmcv>=2.0.0rc4.

I am trying to use the semantic segmentation which is pre-trained on the ADE20K dataset on the custom dataset Please help me with this issue.