Search found 8 matches
- Mon Jun 12, 2023 9:53 pm
- Forum: Training Discussion
- Topic: Questions regarding input & output size
- Replies: 5
- Views: 6851
Re: Questions regarding input & output size
Ok, a lot of answers to these are going to be 'it depends' Does a model trade-off details (Or other things) to accommodate high resolution only if you don't have enough VRAM or does it always scale back other parts of the NN as you increase the output size? Would you get satisfactory results with l...
- Fri Jun 09, 2023 3:51 pm
- Forum: Training Discussion
- Topic: Questions regarding input & output size
- Replies: 5
- Views: 6851
Re: Questions regarding input & output size
As a general rule of thumb, I'd say that for every doubling of resolution, you need 4x the resources, be this time or VRAM etc. It is not linear, so generally you will need trade-offs in other parts of the model to get to this higher resolution. This will negatively impact the final swap, so it is ...
- Wed Jun 07, 2023 10:15 pm
- Forum: Training Discussion
- Topic: Questions regarding input & output size
- Replies: 5
- Views: 6851
Questions regarding input & output size
Hello, I am trying to understand the input size (Size of the face image that is fed to the model) and the output size (Size of the face that is generated from the model). The training documentation says "It is a common misconception that higher resolution inputs will lead to better swaps. Whils...
- Mon Feb 06, 2023 10:13 pm
- Forum: Training Support
- Topic: Everything says to switch to "No Warp" eventually, but when I to, it looks clearly like the source face again.
- Replies: 7
- Views: 2958
Re: Everything says to switch to "No Warp" eventually, but when I to, it looks clearly like the source face again.
I may have answered my own question. The training thumb looks wonky, but I tried doing an actual conversion and it's... impressive. I saved the model folders before doing no warp and might compare the two, but it looks like I just need to trust the magic. I ran into the same issue last week. I ran ...
- Fri Jan 20, 2023 3:36 pm
- Forum: Extract Support
- Topic: OOM killer kills faceswap process because it uses all 32GB of installed RAM (Not VRAM).
- Replies: 6
- Views: 2098
Re: OOM killer kills faceswap process because it uses all 32GB of installed RAM (Not VRAM).
Update : I got the extraction to work by implementing a workaround. I increased the swap to 32GB (Physical memory also 32GB). Faceswap used all 32GB of RAM. Swap was almost full (Need to increase it). It extracted the faces without running into OOM. The memory leak issue is still there. I will do a...
- Sun Jan 15, 2023 11:28 pm
- Forum: Extract Support
- Topic: OOM killer kills faceswap process because it uses all 32GB of installed RAM (Not VRAM).
- Replies: 6
- Views: 2098
Re: OOM killer kills faceswap process because it uses all 32GB of installed RAM (Not VRAM).
Memory leaks are usually always in the libraries we use (and with this only happening to you it seems exceptionally likely). I'd suggest trying to update FaceSwap using the GUI which also updates the conda environment to the latest versions. If that doesn't work you can try to reinstall so you get ...
- Sat Jan 14, 2023 8:46 pm
- Forum: Extract Support
- Topic: OOM killer kills faceswap process because it uses all 32GB of installed RAM (Not VRAM).
- Replies: 6
- Views: 2098
Re: OOM killer kills faceswap process because it uses all 32GB of installed RAM (Not VRAM).
The length of the video is 56 minutes and the resolution is 1080. I have tried different videos of different lengths and resolutions and OOM killer kills it after few hours due to high RAM usage. I even tried to extract faces from images instead of a video file and ran into the same issue. I ran the...
- Fri Jan 13, 2023 6:44 pm
- Forum: Extract Support
- Topic: OOM killer kills faceswap process because it uses all 32GB of installed RAM (Not VRAM).
- Replies: 6
- Views: 2098
OOM killer kills faceswap process because it uses all 32GB of installed RAM (Not VRAM).
Hello, I am trying to extract faces from images. My input folder contains 25,000 images. Faceswap processes around 3,000 images and then the OOM killer kills the Faceswap python process because it uses too much RAM (Not VRAM). I read in "Hardware Requirements" topic that Faceswap does not ...