I'm not sure whether 8GB of GPU is enough or do I need something bigger?
What is the size of the GPU needed to train the Villain model?
Read the FAQs and search the forum before posting a new topic.
This forum is for discussing tips and understanding the process involved with Training a Faceswap model.
If you have found a bug are having issues with the Training process not working, then you should post in the Training Support forum.
Please mark any answers that fixed your problems so others can find the solutions.
- LonelyAsteroid
- Posts: 5
- Joined: Mon Apr 06, 2020 4:44 pm
- Has thanked: 2 times
Re: What is the size of the GPU needed to train the Villain model?
I have trained Villain at a very low batchsize (4 iirc) on a GTX 1080.
This was on Linux, so will be tougher with Windows, which holds back more of your GPU RAM.
You should be able to get it going with some of the VRAM saving options though.
My word is final
Re: What is the size of the GPU needed to train the Villain model?
FYI
Windows, 32Gb
4 batch size with single GTX1070ti (8GB)
8 batch size with 2 x 1070ti's in SLI. (16GB)
Takes a long time !
Re: What is the size of the GPU needed to train the Villain model?
I'll second that. Took me over 10 days to train Villain to convergence
My word is final
Re: What is the size of the GPU needed to train the Villain model?
How do you know when Villain has achieved convergence and can it handle 512px?
Re: What is the size of the GPU needed to train the Villain model?
See the training guide. Specifically the section "Monitoring Training". viewtopic.php?f=6&t=146#monitor
No. It's a 128px model
My word is final