Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

HF #11

Open
Inferencer opened this issue Jun 18, 2024 · 2 comments
Open

HF #11

Inferencer opened this issue Jun 18, 2024 · 2 comments

Comments

@Inferencer
Copy link

Inferencer commented Jun 18, 2024

If it's not too much trouble could somebody put this on HuggingFace Spaces on CPU hardware so I can duplicate and change to GPU
HF does not like env yamls i fear so a requirements text is all i really need

I did attempt this myself but ran into issues with
detectron2==0.6
and im assuming once it's fixed i would run into with
detectron2-densepose==0.6
and perhaps some of the rest

@lhd777
Copy link
Collaborator

lhd777 commented Jun 19, 2024

We apologize for any inconvenience caused. Installing detectron2 and densepose is not an easy task. Therefore, we have set up detectron2 as a submodule. You can follow these steps for installation:

@bboylalu
Copy link

I also had lots of issues with it and what I ended up doing was to start a new conda environment,

conda install pytorch==2.0.0 torchvision==0.15.0 torchaudio==2.0.0 pytorch-cuda=11.7 -c pytorch -c nvidia
conda install -c conda-forge pybind11
conda install -c conda-forge gxx
conda install -c conda-forge gcc_linux-64==11.*
pip install 'git+https://github.com/facebookresearch/[email protected]'
cd detectron2/projects/DensePose
pip install .

Then manually install of the dependencies as results of the errors I got when running python demo/run_gradio.py.
It's a pain, but it worked for me.

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

No branches or pull requests

3 participants