Faceswap Forum

Wikipedia has a good visual guide:

https://en.wikipedia.org/wiki/Compariso ... algorithms

The short answer is "probably not but maybe". One thing that we do with our training process is we don't save out the optimizer weights. The Optimizer is a part of the model, but to save it's weights can triple the size of the model. Because of that, each time we start the model the weight...

We welcome PRs, as like I said, the mechanics are easy but this is unlikely to be done by us since we don't know how we'd set up the options.

Hmmm, can't be sure, but it looks like a storage access problem. ml.p3.2xlarge doesn't have local storage and it's synchronized to the network. Not sure why the hangup is happening though. Try a much higher save interval, not a lower one. That sets how many iterations between saving out your models.

Yes, this is possible, and the mechanics of it are quite easy. The hard part is the heuristics. When you roll back, how much you roll back, how much you lower LR and all of that are completely unknowable and so we leave it as an exercise to the user.

Biases exist intrinsically in dense (Fully connected) layers but are generally not included in convolutional layers because convolutions work in a different way and don't really need them. HOWEVER, "weights" are generally taken to mean all variables used in the model. For example, convolut...

No, you don't need to combine multiple extracts for one alignment file. The alignment file is only needed for the convert step, and since each time you extract a video it creates a matching alignment file you don't need to combine them at all anymore.

Check the file at 'C:\Users\chris\Desktop\NIKBIT\spiderman0 (40).png' first. That filename doesn't look like an extracted file to me. If that's not it, I'd suggest starting first with the Tools -> Alignments -> Rename to make sure they're all named with the original name and check if they all match....

I tried raising the learning rate and it appears to destroy the model and progress. I'm assuming that is because it is now broadening the learning landscape and "resetting." But again I'm going to let it run for fun as an experiment. Either way it turns out it's going to teach me a good l...

Identity leakage is a subtle thing. It is easier to see in some contexts over others but it's there when you re-use a decoder. If you're training with FFHQ or similar dataset, the recommended method is to train a model with those, then copy the encoder over using the "Load Weights" when cr...

I am not blasting you. Just pointing out Dunning Kruger effect. The simple matter is that I don't have to train to 100 billion to know that FaceSwap can never become an "instant swapper" for the same reason that I know that a car cannot fly if you give it high enough octane fuel. It's not ...

Perfect loss is mathematically impossible. It's not just an infeasible thing, it's complete nonsense. Like claiming that some invention creates more power than it takes in -- It's simply impossible. That said, what you're doing is even worse in many ways. Effectively you're massively overtraining yo...

I've never seen this. Are you sure that only images from that fsa are in the folder?

On a single GPU your link speed is unlikely to be a major bottleneck.

No. Or more accurately mostly no. The model will train at the same speed if the data is good. That's not the whole story though. If you have a very few images then you'll "overtrain" before the model reaches it's maximum quality. That may show you what looks like high quality faces but it'...

Check if your GPU is overclocked (factory overclocks too) and remove them. Often overclocking leads to slight instability that you wont notice in a video game but can be catastrophic to machine learning. If that still doesn't fix it, try power cycling your device. Turn it off. Unplug it, and leave i...

Nobody has all the answers regarding NaNs. If you're running into them a lot with a given dataset, then you may want to try lowering the LR, reducing the Batch size, making sure not to use any multipliers, turning off mixed precision, and maybe even changing the loss function. Any or all of these ca...

Things outside the mask are just noise. Don't worry about them at all.

It's not provided explicitly to the model. It learns to find it by itself from the data.

Aside, have any of you guys played with one of these?: https://www.nvidia.com/en-us/design-visualization/rtx-a6000/ ...The 48GB VRAM is tempting. I would LOVE to play with 48gb cards, sadly Open Source doesn't pay well enough to justify such large purchases (and nobody has volunteered to let us use...

Faceswap Forum

Search found 790 matches

Re: Bicubic vs. Nearest Neighbor

Re: Nan Question I haven't seen yet

Re: Thoughts on Auto-Training

Re: Training freezes after 1100 iterations

Re: Thoughts on Auto-Training

Re: Where are the biases?

Re: Is it a good idea to extract from your faces folder to consolidate the alignments file?

Re: Cleaning Alignments - Error

Re: Experiments in pretraining

Re: Perfect 0.0 Loss value achieved !

Re: Perfect 0.0 Loss value achieved !

Re: Perfect 0.0 Loss value achieved !

Re: Cleaning Alignments - Error

Re: PCIe 2.0 and 4.0

Re: Let me see if I have this right regarding training time...

Re: okay this totally threw me...

Re: Avoiding NaN Errors

Re: [Discussion] Notes on Loss functions

Re: Where does the eye direction get stored for the training/conversion?

Re: Potential VRAM Saving techniques