Faceswap Forum

MaxHunter

Again, I'm not sure if this helps you or not, but after doing another clean install and addressing the anaconda/git commands I'm getting different error/crash report. It will not let me train or extract and gives me a different error report as before. Sorry if this is redundant, I'm just unsure if t...

MaxHunter

Okay. I don't know if this is related to this: https://forum.faceswap.dev/viewtopic.php?t=2725 but a new error has popped up. This one is related to extraction: 06/27/2023 20:37:15 ERROR Got Exception on main handler: Traceback (most recent call last): File "C:\Users\e4978\faceswap\lib\cli\laun...

MaxHunter

Results After updating when trying to check for updates in the GUI: 06/27/2023 15:09:11 INFO Checking for updates... 06/27/2023 15:09:11 INFO Git is not installed or you are not running a cloned repo. Unable to check for updates Some tests updating manually: (base) C:\Users\e4978>conda activate face...

MaxHunter

When you used "extract from faces" to do a new alignment file it didn't filter those out?

I think it should have filtered those into a "duplicate" folder when you create a new alignment file.

MaxHunter

Good question!

MaxHunter

I think this is related to having two of the same faces in a VR clip. When I sorted faces and then created an alignment file, it of course kicked out over 8k duplicate faces. Is there a way to add those duplicates back in? Also - off extraction topic, but since I have your attention- what are the od...

MaxHunter

I just got my board back last night and decided to just start from scratch. Before I was reusing model weights. There must have been something in the model weights, a corruption perhaps, because I haven't had any problems as of yet.

Thanks for your insight.

MaxHunter

Sorry for the late reply, I burned out my Motherboard somehow so I've been on the downlow. It's crazy, it just sat and bounced around the .60s and wouldn't go down, or UP, and no picture in the preview. On the other hand the B side was fine and was masking the A side with(seemingly) little difficult...

MaxHunter

Thanks! I'll keep going then. It'll be interesting to see what happens if I load these weights when it's finished into another model.

I thought maybe this had something to do with "FC dimensions" being wrong, as I never mess with that function.

MaxHunter

Here's what I'm confused about: My A Faces' loss is stuck in the .60's while my B face continues to learn (currently in the .04's.) I'm honestly more concerned with my B face learning. Even though the A face is stuck, is the B face still learning the A face, or is it just learning it's own face with...

MaxHunter

Okay. So apparently this is affecting my A face from learning. Why? Is it a setting? Would my dimensions setting in Phaze A be the cause? My B face is learning just fine and seems to be placed on my A face in the previews, but is it learning properly if my A Face isn't learning? Hmmm....

MaxHunter

I've never seen this before. Should I be worried? The last line is what really concerns me., Exception in Tkinter callback Traceback (most recent call last): File "C:\Users\e4978\MiniConda3\envs\faceswap\lib\tkinter\__init__.py", line 1892, in __call__ return self.func(*args) File "C:...

MaxHunter

Great post and questions. I've been at this for about a year so I am far from an expert. I've had one recent model turn out terrible, and the only thing I could attest it too is "overtraining." I use a specific B model alot trying to get it down to under .02 loss, and I think you're right,...

MaxHunter

Unless you are using an SLI to combine 3090s it will not use both GPUs. Again, sorry to do this to you, but this is also not true. SLI is not required for distributed training. Yes, but if they're s on a 3090/3060 setup, they can't run a model over 12gb because of the 3060 memory limitations. So if...

MaxHunter

I have a 3080ti and a 3090. First, when you say you have (4) 3090, do you mean it's in the 4th slot, or do you mean you have 4 separate 3090s? I've been told the more GPUs the slower it'll run. Unless you are using an SLI to combine 3090s it will not use both GPUs. However, all is not lost, it's my ...

MaxHunter

For others with the same question: From Discord, Super Hans When I’ve dome that before, it’s more of a case where the new face A is “good enough” than looking for perfection. I’m sure it’ll probably be better if both sides are fully trained to perfection, but like all things it’s a balancing act bet...

MaxHunter

If I I'm reusing a B face, and I'm uninterested in swapping the A onto the B face, am I wasting my time trying to get the A face to the absolute loss minimum? Further Explanation: I use a lot of the same actors faces for my B face, and now have them down to a reasonable loss value. It occured to me ...

MaxHunter

Question about this: I can't seem to get my Masking Editor to stick either. Does re-masking through the Masking Tool/tab reset the mask after I manually edit it? The way I'm understanding everything in this post is that I'm to edit (when I use the Mask editor, not box editor) in the manual tool and ...

MaxHunter

Thanks, man. This worked.

MaxHunter

You're saying: Add the faces you want for training, and then re-extract using the alignment tool, and then edit the mask coverage?

Faceswap Forum

Search found 194 matches

Error when starting training: OSError: Unable to open file (bad object header version number)

Re: Per Discord convo. Here's the anaconda prompts.

Error updating Faceswap: Git is not installed or you are not running a cloned repo.

Re: separating re-feeds from false positives

Re: Questions regarding input & output size

Adding Duplicates

Re: An error I've never seen...

Re: An error I've never seen...

Re: An error I've never seen...

Re: An error I've never seen...

Re: An error I've never seen...

An error I've never seen...

Re: Overtraining question

Re: multigpu not working in GUI version

Re: multigpu not working in GUI version

Re: A bit of a basic question...

A bit of a basic question...

Re: Adjusted masks during manual adjustment - didn't seem to work with training - error on conversion.

Re: Masking is off when adding new faces in manual

Re: Masking is off when adding new faces in manual