Search found 1838 matches

by torzdf
Tue Jul 19, 2022 10:08 pm
Forum: Extract Support
Topic: "Skip Existing" vs. "Skip Existing Faces"
Replies: 2
Views: 82

Re: "Skip Existing" vs. "Skip Existing Faces"

That sounds about right to me. Skip Existing - Will not process any frame that exists in alignments file. Would be used for re-generating alignments for a file where "Extract Every N" was used in the past. Skip Existing Faces - Will attempt to find faces in any frame where faces were not f...
by torzdf
Tue Jul 19, 2022 10:06 pm
Forum: Cloud Discussion
Topic: AWS gpu instance error
Replies: 2
Views: 56

Re: AWS gpu instance error

Not an AWS expert by any means, but just don't pass in the -p flag when launching faceswap. Use the -w flag to write out a preview image to the faceswap folder instead.

by torzdf
Mon Jul 18, 2022 1:47 am
Forum: Training Discussion
Topic: Potential VRAM Saving techniques
Replies: 11
Views: 229

Potential VRAM Saving techniques

[Topic split from: https://forum.faceswap.dev/viewtopic.php?t=2058] I have done a not inconsiderable amount of testing around NaNs recently, really hoping I would find a solve, and I have drawn a blank. Where they get introduced in a model is inconsistent, although they nearly always seem to appear ...
by torzdf
Mon Jul 18, 2022 1:36 am
Forum: Training Discussion
Topic: Latest with "Learn Mask"
Replies: 1
Views: 103

Re: Latest with "Learn Mask"

The recent pushes around learn mask were due to a regression introduced with the new Phaze-A preset, so they were to fix those bugs rather than any feature adds... Re: Bisenet-face mask. An unintended consequence of full face masking was that when swapping someone with a lower hairline onto someone ...
by torzdf
Sun Jul 17, 2022 5:42 pm
Forum: Training Support
Topic: Error code viewing graph whilst training.
Replies: 3
Views: 84

Re: Error code viewing graph whilst training.

Unfortunately that's just a message saying that Tensorflow is not OK. There's not really much I can do with it :(

by torzdf
Sat Jul 16, 2022 9:40 am
Forum: Training Discussion
Topic: Obscure close - Fish Eye Training are there any Z axis training models
Replies: 4
Views: 106

Re: Obscure close - Fish Eye Training are there any Z axis training models

The short answer is no. Images should all have a similar field of view, or you will run into the issues that you see. Ultimately, nothing is aligned in the 3D space in Faceswap. We do use some rough 3D modelling for different training types (i.e. legacy/face/head), but again, it makes assumptions th...
by torzdf
Thu Jul 14, 2022 2:47 pm
Forum: Training Support
Topic: why am I getting a mixed_float16 error?
Replies: 4
Views: 97

Re: why am I getting a mixed_float16 error?

I don't really know what to add to what the message says. You have a GTX 1080 with compute capability of 6.1 Tensorcore support was not added until GPUs with at least compute capability of 7.0 (RTX 2xxx series) You don't run with mixed precision enabled, so it doesn't impact you. It is collecting mi...
by torzdf
Thu Jul 14, 2022 12:07 pm
Forum: Training Support
Topic: why am I getting a mixed_float16 error?
Replies: 4
Views: 97

Re: why am I getting a mixed_float16 error?

The line, literally 1 line prior to your paste says:

Code: Select all

INFO     Storing Mixed Precision compatible layers. Please ignore any following warnings about using mixed precision.
by torzdf
Thu Jul 14, 2022 1:13 am
Forum: Training Support
Topic: Out of Memory after 6 Hours of Steady Training
Replies: 13
Views: 190

Re: Out of Memory after 6 Hours of Steady Training

Well, that sucks.

Not really sure what else to suggest, as this is not a repeated complaint.

You can try enabling "Allow Growth" under training settings, but I think it's a long shot that it will solve your issue.

by torzdf
Wed Jul 13, 2022 6:27 pm
Forum: Training Support
Topic: Out of Memory after 6 Hours of Steady Training
Replies: 13
Views: 190

Re: Out of Memory after 6 Hours of Steady Training

Glad you got there in the end :)

The type of mask used should make no difference.

Please do let me know if rolling back solves your issue, so I can keep track of the problem.

by torzdf
Wed Jul 13, 2022 3:58 pm
Forum: Training Support
Topic: Out of Memory after 6 Hours of Steady Training
Replies: 13
Views: 190

Re: Out of Memory after 6 Hours of Steady Training

Ok, downgrading Tensorflow looks like it forced a downgrade of typing extensions.

You should be able to fix the issue in exactly the same way as you did before, but instead of pip install tensorflow do:

Code: Select all

pip install typing-extensions">=4.0.0"
by torzdf
Wed Jul 13, 2022 3:51 pm
Forum: Training Support
Topic: Out of Memory after 6 Hours of Steady Training
Replies: 13
Views: 190

Re: Out of Memory after 6 Hours of Steady Training

That's actually an unrelated bug...

Looking at your installed packages, it looks like you have downgraded successfully.

If you give me 10 mins, I can probably fix that issue.

by torzdf
Wed Jul 13, 2022 7:34 am
Forum: Convert Support
Topic: mismatch frame rate (output & original)
Replies: 5
Views: 109

Re: mismatch frame rate (output & original)

I'm not entirely sure what you mean. If you mean that the wrong face is being swapped on (i.e. the face being swapped on is from a previous/next frame) then this is not something I've heard of before, and would suggest an issue with your video file. The process basically goes through the video frame...
by torzdf
Wed Jul 13, 2022 7:31 am
Forum: General Discussion
Topic: updates
Replies: 2
Views: 83

Re: updates

No, I don't keep a changelog, as Faceswap is constantly updated.

You can view changes to code in the commit log. I try to name commits in a useful manner:
https://github.com/deepfakes/faceswap/commits/master

by torzdf
Wed Jul 13, 2022 7:29 am
Forum: Training Support
Topic: Out of Memory after 6 Hours of Steady Training
Replies: 13
Views: 190

Re: Out of Memory after 6 Hours of Steady Training

If you're asking how to do it, it probably won't be a good idea to do it. However, I will detail the steps to downgrade Tensorflow here. Please note, after this, you are on your own. If it goes wrong, then I am unlikely to help with troubleshooting the issue as it is not a great use of my time (if i...
by torzdf
Wed Jul 13, 2022 7:20 am
Forum: Training Support
Topic: CLI documents
Replies: 1
Views: 34

Re: CLI documents

For cli, not so much. The guides also work for the cli (for the most part anyway. Some tools like preview/manual etc are obviously GUI only). python faceswap py -h will give you command line parameters Hitting the Generate button in the GUI will generate the underlying command line arguments that wi...
by torzdf
Tue Jul 12, 2022 5:43 pm
Forum: Convert Support
Topic: mismatch frame rate (output & original)
Replies: 5
Views: 109

Re: mismatch frame rate (output & original)

Duplicate frames usually happen because, at some point (probably before you even received it), the video has been converted from one frame rate to another. It is very common.

Read more here:
https://helpcenter.extremereach.com/hc/ ... ate-Frames

by torzdf
Tue Jul 12, 2022 9:19 am
Forum: Training Support
Topic: Out of Memory after 6 Hours of Steady Training
Replies: 13
Views: 190

Re: Out of Memory after 6 Hours of Steady Training

This looks to be a regression in Tensorflow which appears to impact some users and not others. In theory, this shouldn't be able to happen, as TF allocates all of the VRAM it requires at the start, so it should not run out of VRAM several hours in to a training session. I have seen this happen once ...
by torzdf
Mon Jul 11, 2022 7:52 am
Forum: Extract Support
Topic: UnicodeDecodeError: 'cp949' codec can't decode byte
Replies: 1
Views: 79

Re: get crashed my brand new computer

This is usually because of special characters in the metadata of the video file. Find a video editing tool that you can use to strip the metadata. (Something like mp3tag should work ok for mp4 files). Alternatively, if you can provide the video file, I can try to put something in which will work aro...
by torzdf
Mon Jul 11, 2022 7:44 am
Forum: Training Discussion
Topic: Is my CPU a bottleneck?
Replies: 6
Views: 130

Re: Is my CPU a bottleneck?

Honestly, I couldn't really advise one way or another. I'm not sure how accurately Windows graph represents utilization for AI tasks. I develop Faceswap on a Xeon processor with a considerably lower clock speed than yours, but with considerably more cores. If you are just looking to upgrade because ...