Backbone Pre-train weight?

[cuiziteng]

Hello, thanks for your nice code and nice paper!

One question I wonder is that when I see the code, there are no code show that pre-train weight load to the backbone, I find the pre-train weights are only load to segmentation head, could you show me where are the code to load backbone weights of CLIP encoder? thanks

[hughsando]

I could run the zero-shot segmentation after getting the clip weights, ViT16_clip_weights.pth, with:

python tools/maskclip_utils/convert_clip_weights.py --model ViT16

ie, without the "--backbone" arg mentioned in the readme.

[111chengxuyuan]

Hello,I want to ask you a question,Which version of mmsegmentation should I install to run this code properly? I installed 0.20.0 but couldn't run it

[WilsonAir]

Hello,I want to ask you a question,Which version of mmsegmentation should I install to run this code properly? I installed 0.20.0 but couldn't run it Maybe the MMCV is the most important issue, I have tried a lot method, this is how I prepare for it: First make sure your cudatoolkit installed: I have installed cudatoolkit 11.1

install pytorch: pip install torch==1.8.0+cu111 torchvision==0.9.0+cu111 torchaudio==0.8.0 -f https://download.pytorch.org/whl/torch_stable.html

install MMCV through pip: pip install mmcv-full==1.5.0 -f https://download.openmmlab.com/mmcv/dist/cu111/torch1.8.0/index.html

install CLIP and other package: pip install git+https://github.com/openai/CLIP.git

[SetonLiang]

python tools/maskclip_utils/convert_clip_weights.py --model ViT16

After executing the statement above, l get the ViT16 clip weights,pth. However, when l run the test.py, it wil cause a problem, that is, I wonder know whether the missina weights affect the output shape or not.