Faceswap Forum

That's great! I'm going to mark this as solved and lock this thread.

Feel free to open another one with any other issues.

Yes. You've run out of system RAM. How many images are you processing?

If you check the sort section of the extraction guide you will see specific mention of this.

There appears to be an issue with the latest Tensorflow and S3FD on some setups,

It will still work if you run it with "single-process" enabled

Could you point me to where it says this? That is outdated information.

It is highly advised that you create your own image sets. For one, it will help you familiarize with the process. For another, you will need the alignments file for training/converting.

I have never seen this error before. My suspicion is that somehow the downloaded model got corrupted. If you go into your faceswap folder and delete the model file from the following location: faceswap\plugins\extract\align\.cache\face-alignment-network.pb Then try again, it will re-download the mod...

Glad you got it working

Ultimately if FS says you're out of VRAM, you're out of VRAM.

Without knowing the specifics of the model you're training, its settings, the batch size, it is impossible to give you any more than this.

See:
https://faceswap.dev/forum/app.php/faqpage#f3r10

Please provide the crash report from your faceswap folder. There isn't enough to go on here.

1) Deprecated files. Ignore that. They are warnings generated from Keras. 2) S3FD CUDNN_STATUS_ALLOC_FAILED message. There seems to be an issue somewhere with VRAM usage on this detector. Try enabling "single process" mode and seeing if it runs. 3) The "WARNING: Logging before flag pa...

Yes. See here: https://faceswap.dev/forum/viewtopic.php?f=6&t=50

Do they give better results? Yes. Do they train in a shorter time? No. They take longer because they are heavier models.

I think you found it! But for anyone else it is the "check" mark with the other buttons next to the avatar.

Get the latest code. This is a bug which has been fixed

https://faceswap.dev/forum/viewtopic.php?f=4&t=44

I do use Linux. Specifically Ubuntu 18.04

For what it's worth, I overlooked that openCV and numpy are both wrappers (in Python) for C, so they will utilize multi-processes under the hood. Ultimately, Image processing IS CPU intensive, and we augment all of our data on the fly. If you are concerned that you are being bottle-necked by the CPU...

Exactly

3) my converted faces from A with my model (so I have a set of mix faces from A to B)

This is wrong. You should not have converted faces.

You convert THE VIDEO, not THE FACES.

You don't want to swap the "faces" at the convert stage..... You need to swap the faces in the frames.... For converting: Select the video that you want to swap the faces onto as your "input" Select a location for output. Select "ffmpeg" as writer. This will swap the fa...

Hard to say, and depends on a lot of things (model, CPU/GPU, quality of data etc). Leaving it going some more and see if it's improving

Ok, 2 things:

1) Remove your system wide installed Cuda. How to do this will depend on how you installed Cuda in the first place. Basically, it will probably conflict with the Conda installed version.

2) Update your Nvidia Drivers.

Faceswap Forum

Search found 2688 matches

Re: Extraction throws InvalidArgumentError: Invalid GraphDef

Re: Sorting Tool - Critical Crash ?

Re: Some critical problems.

Re: [Request] Download links to the image sets in usage.md

Re: Extraction throws InvalidArgumentError: Invalid GraphDef

Re: Need help with depreciated files, cuDNN, and GPU Utilization

Re: Out of Memory & Python Crash

Re: Out of Memory & Python Crash

Re: Need help with depreciated files, cuDNN, and GPU Utilization

Re: my cpu is 100% usage，is it normal ？

Re: How to tune for A->B only?

Re: [AMD] AttributeError: '_Settings' object has no attribute 'prohibit_winograd'

Re: Error message/crash when converting

Re: CPU Load is 100% and ~40% GPU

Re: CPU Load is 100% and ~40% GPU

Re: Put swap faces in video ?

Re: Put swap faces in video ?

Re: Put swap faces in video ?

Re: Training Preview

Re: Status Failed - train.py