Faceswap Forum

Hollywood

Yep that fixed it. I manually added the cudNN libs into the faceswap environment and it works now. Thanks for the help!

Hollywood

There's atleast part of your problem.

Yeah I was thinking that could be it. I have cudnn 8.1.1 installed but I'll try and reinstall it.

Hollywood

Unfortunately that output doesn't show any indication of why it might be exiting. Can you post your system info (output from Help > Output System Information ) Yeah here's the output from that: ============ System Information ============ encoding: cp1252 git_branch: master git_commits: 55bb723 New...

Hollywood

Note: I am using a 3000 series card and I know it isn't officially supported but I'm hoping someone may be able to help. I installed using this guide:https://forum.faceswap.dev/viewtopic.php?p=5466#p5466 When I try and extract I get this readout... Loading... Setting Faceswap backend to NVIDIA 07/19...

Hollywood

Strange my drivers are up to date and I even did a clean install. Guess I'll check out the other guide.

Hollywood

Yeah I have an RTX 3000 series which is why I was setting it to work with the CPU. Can I not use faceswap with the CPU if I have a 3000 series GPU?

Hollywood

Unfourtantly that doesn't work. It sends out this message and doesn't launch. From my limited understanding it sounds like something wrong with MiniConda but I could be wrong. "C:\Users\(removed)\Miniconda3\scripts\activate.bat" && conda activate "faceswap" && pyt...

Hollywood

Hi, I have been trying to install faceswap on a different drive and it had been working good previously. I uninstalled it on the other drive and installed it on the new one. However when I click the gui launcher file the command line opens and then immediately closes and the gui never comes up. I fo...

Hollywood

Since you say you already tried the swap model, try clicking the "generate" button and post the result in here. Oh, sorry I misread your reply. Here is the generate with swap model off (which should be the correct way) C:\Users\*****\MiniConda3\envs\Faceswap1\python.exe F:\faceswap\facesw...

Hollywood

Here is the preview result with swap model off

: swap-model-off.jpg (173.61 KiB) Viewed 11212 times

And here it is with swap model on

: swap-model-on.jpg (170.7 KiB) Viewed 11212 times

As you can see its the same result, the output is the same as the input.

Hollywood

And before you say anything, yes I have tried swap model. When I use the preview or convert function it just outputs the original video, I just wanna list my steps I'm doing to see if anything is wrong, I don't get error messages and I believe I've followed the guides to a tee, let me know if you ne...

Hollywood

Thanks for the help some combination of all of those helped to fix it.

Hollywood

That didn't help either, I even lowered it all the way down to one. It had been working before for many hours and then I shut down my computer overnight and tried to restart it and it started doing this.
I also made a trace level crash report in case that will help narrow it down.

Hollywood

deephomage wrote: ↑Fri Jun 12, 2020 9:12 pm
Your log file states "Crash report written to 'F:\Face Swap\faceswap\crash_report.2020.06.12.151752362351.log'. You MUST provide this file if seeking assistance." Post your crash report, not the log file.

I attached it in the original post.

Hollywood

torzdf wrote: ↑Fri Jun 12, 2020 8:22 am
Enable the "Allow Growth" option

That didn't work I included my log in case that helps with debugging.

Hollywood

When I try to start training I get these error message: E tensorflow/stream_executor/cuda/cuda_blas.cc:238] failed to create cublas handle: CUBLAS_STATUS_ALLOC_FAILED and E tensorflow/stream_executor/cuda/cuda_dnn.cc:329] Could not create cudnn handle: CUDNN_STATUS_ALLOC_FAILED Anyone have any idea ...

Hollywood

Thanks for the help, unfortunately it hadn't run for 25,000 iterations yet when it crashed. I'll try to decrease the learning rate and see if that works.

Hollywood

I trained my model overnight and the previews were getting better but when I woke up the previews were black and red and when I look at the graph the loss had spiked somewhere in the middle. Is there a way to revert back to that spot in the training so I don't have to do it all again? Thanks!

Faceswap Forum

Search found 18 matches

Re: Process Exited No Clear Error Message

Re: Process Exited No Clear Error Message

Re: Process Exited No Clear Error Message

Process Exited No Clear Error Message

Re: GUI Doesn't Launch

Re: GUI Doesn't Launch

Re: GUI Doesn't Launch

GUI Doesn't Launch

Re: Converted File Faces Haven't Changed

Re: Converted File Faces Haven't Changed

Converted File Faces Haven't Changed

Re: Could not create cudnn handle: CUDNN_STATUS_ALLOC_FAILED

Re: Could not create cudnn handle: CUDNN_STATUS_ALLOC_FAILED

Re: Could not create cudnn handle: CUDNN_STATUS_ALLOC_FAILED

Re: Crash While Beginning Training

Could not create cudnn handle: CUDNN_STATUS_ALLOC_FAILED

Re: Loss Spikes in Middle of Training

Loss Spikes in Middle of Training