Search found 802 matches

by bryanlyon
Tue Mar 11, 2025 3:40 pm
Forum: Training Discussion
Topic: question about batch size
Replies: 1
Views: 7482

Re: question about batch size

It might make more sense to think of it as a "forest for the trees" sort of thing. Low batch sizes will get a single tree looking better, while high batch sizes will get the whole forest looking better. Larger batch sizes do train faster, but they can't necessarily train better. I did a te...
by bryanlyon
Tue Mar 11, 2025 3:32 pm
Forum: Hardware
Topic: Scaled Memory - Apple Silicone vs Nvidia
Replies: 2
Views: 9955

Re: Scaled Memory - Apple Silicone vs Nvidia

A basic rule of thumb is that doubling the resolution multiplies by 4 the amount of memory required. if 256x256 is taking 20gb, then 512 would take 80gb and 1024 would take 320gb. So, no, 256gb of ram wouldn't be able to handle 1024x1024 training out of the box. However, another key point is that re...
by bryanlyon
Fri Jan 17, 2025 8:11 pm
Forum: Convert Support
Topic: Error: 0 state model found
Replies: 3
Views: 18842

Re: Error: 0 state model found

Your model has probably corrupted. Probably due to running out of storage or something similar. Try using one of the backups.

by bryanlyon
Wed Jan 15, 2025 6:31 am
Forum: Installation Support
Topic: Intel Mac with AMD GPU running in CPU mode
Replies: 1
Views: 11572

Re: Intel Mac with AMD GPU running in CPU mode

Intel macs are very different from the Apple silicon and aren't supported the same way. Since you have an AMD card you should try the amd install. But you could also try using ROCM.

by bryanlyon
Wed Jan 15, 2025 6:24 am
Forum: Training Support
Topic: Low EG/s even after fresh install.
Replies: 2
Views: 18663

Re: Low EG/s even after fresh install.

That could be a perfectly normal speed. It depends on which model you're using, larger models run slower and will take longer to process.

by bryanlyon
Fri Sep 20, 2024 3:51 pm
Forum: Convert Discussion
Topic: conversion problem
Replies: 3
Views: 17673

Re: conversion problem

Unfortunately I can't be sure what is happening here with this report. You may need to enable "trace" logging and send the log over to see what is actually causing the freeze.

by bryanlyon
Fri Sep 20, 2024 3:50 pm
Forum: Installation Support
Topic: Intel NPU / OpenVINO support
Replies: 1
Views: 16214

Re: Intel NPU / OpenVINO support

NPUs can't generally be used to train. The Intel one included with that CPU is the same issue. Basically, Faceswap itself needs to train a model and while that NPU could help with tasks like extracting, those are a tiny part of what FaceSwap does, so we wont be supporting NPUs as the gains would be ...
by bryanlyon
Wed Aug 28, 2024 6:34 pm
Forum: Training Support
Topic: Am I using it properly?
Replies: 2
Views: 15628

Re: Am I using it properly?

So, it seems you've gotten going. A few pieces of advice: It looks like you'll need to clean up your data more. Side A is very lacking in variety, while Side B has a number of non-face objects you'll probably want to clean.

Welcome to the group and feel free to ask any questions.

by bryanlyon
Mon Aug 19, 2024 4:49 pm
Forum: Training Support
Topic: HELP !!! After reinstall the OS and Faceswap, relocate all folder files, it does not work as it used to!
Replies: 1
Views: 13143

Re: HELP !!! After reinstall the OS and Faceswap, relocate all folder files, it does not work as it used to!

This really isn't enough information to know what's going on. Please tell us what problems you're seeing and include any crash logs if present so we can troubleshoot.

by bryanlyon
Thu Aug 01, 2024 4:16 pm
Forum: Extract Discussion
Topic: Faceswap face extraction
Replies: 1
Views: 16899

Re: Faceswap face extraction

No, we extract for use in the AI which is at a far lower resolution in almost all cases. If you're trying to extract for some other usage it'll be best to find a different face extractor (or write your own).

by bryanlyon
Thu Aug 01, 2024 4:14 pm
Forum: Training Discussion
Topic: Question about convergence
Replies: 1
Views: 12044

Re: Question about convergence

The only ways to know are to try it or find someone with experience to examine the dataset to give advice. I suggest trying it. Start with a small model until you can learn the processes.

by bryanlyon
Mon Mar 11, 2024 9:27 pm
Forum: General Discussion
Topic: Will installing new Python version mess with app?
Replies: 1
Views: 13843

Re: Will installing new Python version mess with app?

If you installed Faceswap properly (using the installer or proper guide) then installing other Python instances shouldn't do anything to FaceSwap. However, since you've already got Conda installed with Faceswap I suggest that you install that other application in a proper conda environment. See the ...
by bryanlyon
Mon Feb 12, 2024 11:52 pm
Forum: Training Discussion
Topic: A Short Hello with some questions
Replies: 3
Views: 12053

Re: A Short Hello with some questions

Hello and Welcome. * if one has a video of oneself and wants to put their face onto an "original" where the person is wearing glasses, does the software recognize it? Or does it pixelate the object (the glasses), or even cause image distortions? As long as a decent chunk of the training da...
by bryanlyon
Fri Jan 05, 2024 8:25 pm
Forum: Installation Support
Topic: GUI Glitching
Topic: GUI Glitching
Replies: 5
Views: 19309

Re: GUI Glitching

This actually is not a problem with FaceSwap but instead originates on your system. I'm assuming it's something due to drivers or the specific setup of Kali, WSL, Windows and your local system. Since there are so many variables there I wouldn't even know where to begin to find the cause. This is why...
by bryanlyon
Thu Nov 30, 2023 10:12 pm
Forum: Installation Support
Topic: FaceSwap Linux running, but suddenly stops "Proces Exited" with no Errors
Replies: 4
Views: 31487

Re: FaceSwap Linux running, but suddenly stops "Proces Exited" with no Errors

"Violation of the segment ('core' generated)" This implies that something is failing to get a memory allocation it's seeking. It's also clearly outside of python and in the realm of compiled code. Probably high up in a library. Unfortunately without more information the best we can do is g...
by bryanlyon
Mon Nov 20, 2023 4:49 pm
Forum: Hardware
Topic: Hardware best practices
Replies: 86
Views: 389235

Re: Hardware best practices

The only 30xx card with the nvlink fingers is the 3090. All others cannot do any sort of "linking". That said, you can still use multiple GPUs in Faceswap. It is diminishing returns where each additional GPU slows down the collective more, and like torzdf says, only the batch size can be i...
by bryanlyon
Mon Nov 13, 2023 11:26 pm
Forum: Hardware
Topic: Hardware best practices
Replies: 86
Views: 389235

Re: Hardware best practices

The trouble with hardware recommendations since the 20xx series has been that you always have to add "if you can get it for a good price" to the end of ANY recommendation. Will a 4060 TI with 16gb of vram work? Definitely. Will it beat a $100 1080? Yes. Is it worthwhile to buy it for FaceS...
by bryanlyon
Tue Oct 31, 2023 11:52 pm
Forum: Training Discussion
Topic: Location of “forward pass” and/or Where to implement a Custom Training Loop
Replies: 6
Views: 14196

Re: Location of “forward pass” and/or Where to implement a Custom Training Loop

You don't have to hook into the passes at all to add your own architecture. You can add new models by following the plugin architecture here: https://github.com/deepfakes/faceswap/tree/master/plugins/train/model or add a new training paradigm following the plugins here: https://github.com/deepfakes/...
by bryanlyon
Tue Oct 17, 2023 11:29 pm
Forum: Training Support
Topic: Tensorflow error happens randomly while training
Replies: 1
Views: 11245

Re: Tensorflow error happens randomly while training

As the previous message said, this is a driver issue. Nothing to do with Faceswap and nothing we can do to prevent or work around it. As far as I've been able to find on it though, it's almost 100% an overclocking issue. Chances are the card you have is factory overclocked and it's hitting instabili...