-
Notifications
You must be signed in to change notification settings - Fork 379
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
[F glutil.cpp:338] eglInitialize() failed #115
Comments
Hi @tcabezon , I've met the same problem, and I solved it by replacing "dr.RasterizeGLContext" with "dr.RasterizeCudaContext" when doing inference. You can find it in training/networks_get3d.py, line 385, and uni_rep/render/neural_render.py, line 59. |
Thank you @buptzh111 for providing the fix! Yes, changing from GL to Cuda in Nvdiffrast would fix the problem |
Works for me too! |
does it mean i need to change all the GL to cuda in Nvdiffrast file? |
I get this comment when I try to run inference on the model. I even get the error when I run the 'GET3D-pretrain-inference.ipynb' google colab that is provided as example.
[F glutil.cpp:338] eglInitialize() failed
The text was updated successfully, but these errors were encountered: