CodeSmith2000

I have this happen almost every time I create a new model. I've had this happen on 1060 and 3060. The model parameters are usually very strenuous on my system...

@m3diaoffline Once you create the model on CPU then try to re-open it with GPU.

You do NOT have 16gb of VRAM. My assumption is that you are saying you have 16gb of RAM. VRAM and RAM are not the same thing. RAM is on...

When you run a model on CPU it uses you RAM. When you run a model on GPU, it uses your VRAM. Batch size 4 with 4gb of VRAM is...

First off, no, you will not get NEAR the results with the CPU as you would with a 3090. Second. batch size 21 seems high, especially with "models_opt_on_gpu: True". Even...

Well, this is a bit of an obvious question. But did you provide training data? Specifically you need to have frames of your videos in the src and dst folders,...

That just looks like "Random Warp". Its a method of randomly warping the image as it trains so it is better at generalization. This is fairly expected behavior to make...

I'm not sure if you can turn off random warping for XSeg training and frankly I don't thing you should, it helps to make the mask training be able to...

Most of us don't read Russian so a translation of that error on screen would be nice, with that said, in this case the error is generic so not helpful....

This is an obvious question, but did you have auto backup turned on?