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

Recommend replacing RasterizeGLContext withRasterizeCudaContext #3

Open
Assassin-plus opened this issue Sep 27, 2023 · 1 comment
Open

Comments

@Assassin-plus
Copy link

Since the nvdiffast developr mentioned in sicxu/Deep3DFaceRecon_pytorch#108

Also, the current version of nvdiffrast includes a Cuda-based rasterizer that doesn't require OpenGL. You may want to consider switching to that by default, as setting up OpenGL can be tricky on some platforms.

I recommend to replace the RasterizeGLContext() function in core/NvDiffRastRenderer.py line 25 to RasterizeCudaContext().

It should be fine since I can run the code after the replacement, and if I don't replace it, I came up with the same problem in sicxu/Deep3DFaceRecon_pytorch#2

$ python experiments/smpl/optim.py
Setting up [LPIPS] perceptual loss: trunk [alex], v[0.1], spatial [off]
Loading model from: /usr/local/miniconda3/envs/DROT/lib/python3.8/site-packages/lpips/weights/v0.1/alex.pth
[F glutil.cpp:332] eglGetDisplay() failed
Aborted

@jkxing
Copy link
Owner

jkxing commented Oct 17, 2023

Thanks! I'll check it.

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

2 participants