Search found 8 matches

by wentdot
Thu Nov 26, 2020 6:23 am
Forum: Convert Support
Topic: Update Samples does not work (no errors, but no image refresh)
Replies: 1
Views: 5096

Update Samples does not work (no errors, but no image refresh)

I think I have everything set up correctly, and I can see that the swap is applied (faces do appear). However, changing a setting and clicking to update the samples does nothing, even if I wait for a long time.

I'm on Ubuntu and using AMD/PlaidML.

Any tips would be appreciated.

Thanks in advance.

by wentdot
Mon Nov 16, 2020 1:32 pm
Forum: Training Discussion
Topic: First attempt: Weird learning graph
Replies: 3
Views: 1919

Re: First attempt: Weird learning graph

This is model corruption and is, sadly, unrecoverable. You can try to use the restore tool to restore from the last good backup, or continue training from a previous snapshot. It looks like what happened is the huge fluctuations in the loss function knocked it into some stable local minimum. Is thi...
by wentdot
Sun Nov 15, 2020 8:02 pm
Forum: Training Discussion
Topic: Understanding how variations in data impact results
Replies: 1
Views: 1488

Understanding how variations in data impact results

I am curious about how to connect specific features of my data to my results. The "rules of thumb" make sense - including a variety of different poses, expressions, lighting, etc. But supposing the data set is necessarily flawed in some way - let's say half the data set is from before the ...
by wentdot
Sat Nov 14, 2020 11:59 pm
Forum: Training Support
Topic: Session Stats no longer appearing after a few hours of training
Replies: 15
Views: 11676

Re: Log and graph weirdness

impost3r wrote: Sat Oct 31, 2020 3:00 pm

I have the same issue as the OP.

It appears to me that viewing the Analysis page is what breaks it. Once viewed, it stops updating for the current session.

This is my experience as well.

by wentdot
Sat Nov 14, 2020 5:35 pm
Forum: Training Discussion
Topic: Modifying training data for partially trained model
Replies: 3
Views: 2007

Re: Modifying training data for partially trained model

Yes, go ahead and add data. That's fine and a normal part of training. Thanks - could you comment on the best workflow for this? The first time I did it I didn't know what to do with multiple alignment files, and I ended up re-extracting from a folder of extracted images which created its own issue...
by wentdot
Thu Nov 12, 2020 7:09 pm
Forum: Training Discussion
Topic: Modifying training data for partially trained model
Replies: 3
Views: 2007

Modifying training data for partially trained model

Hi all, I am wondering if there are drawbacks to adding additional training data part way through training. Suppose after many iterations and despite low loss values your preview still looks blurry or bad, but the data you've used is of decent quality, though perhaps insufficient. If you could add n...
by wentdot
Thu Nov 12, 2020 5:37 pm
Forum: Hardware
Topic: AMD Vega 64 issues
Replies: 4
Views: 10835

Re: AMD Vega 64 issues

Thanks for your reply. It is helpful to know the card exclusion works only with tensorflow. Of course immediately after I posted that I fixed the "power" issue... turns out it was a temperature issue after all. Without changing any profile settings, I just turned the fan up before I began ...
by wentdot
Thu Nov 12, 2020 2:38 pm
Forum: Hardware
Topic: AMD Vega 64 issues
Replies: 4
Views: 10835

AMD Vega 64 issues

Hey all, So I am the rare AMD user - I have a Vega 64 and a Vega 64 FE. I have two questions: I know I can "exclude" a card, but choosing to do so has no effect - is there something else I can try? Faceswap is defaulting to my 64 when I would like it to use the FE. I am guessing I could ph...