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

Found bugs including GPU out of memory #26

Open
18608003987 opened this issue Dec 29, 2019 · 1 comment
Open

Found bugs including GPU out of memory #26

18608003987 opened this issue Dec 29, 2019 · 1 comment

Comments

@18608003987
Copy link

Very nice contribution from you! thanks and I find
[1] need to swith from LA to L mode in line#35 of proxyPredictor.py
img = Image.open(img_path).convert('L')
[2] can not run under Tensorflow 2.0 currently
[3] can run proxy estimation base on two priors: --FAC 1 and --emotion 1, but can not get displacementMap, normalMap successfully when I run facialDetails.py , will encounter the issue below,
File "G:\Facial_Details_Synthesis\released_v0.1\DFDN\models\networks.py", line 317, in forward
return torch.cat([self.model(x), x], 1)
RuntimeError: CUDA out of memory. Tried to allocate 800.00 MiB (GPU 0; 6.00 GiB total capacity; 3.65 GiB already allocated; 798.37 MiB free; 4.00 KiB cached)
What's the minimal GPU VRAM for it ?

@apchenstu
Copy link
Owner

Hi, you can simply reduce the batchSize for out of memory issue. Thanks.

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