DLight model still blurry after 400k iterations
Read the FAQs and search the forum before posting a new topic.
Please mark any answers that fixed your problems so others can find the solutions.
DLight model still blurry after 400k iterations
The issue is pretty much as the title says. The picture is still completely burry. I ran the model for a week at we're at 395k iterations which seems enough. The mask type I'm using is VGG-obstructed.
I have about 1200 pictures from video A and B. Is it just a lack of data (though I thought the blurriness would go away after so many iterations...)
Any suggestions?
Re: DLight model still blurry after 400k iterations
If the image is a close-up then there is likely to always be some blurring due to upscaling.
My word is final
Re: DLight model still blurry after 400k iterations
Like you I trained still image-sets with the Dhl128 model. On 250K I made the first conversion - It was.. well not good!
I then did the following:
From training A -> B, I switched training B -> A. Focus on the two different sides has vastly improved conversion which was done at 350K and 450K iterations.
Matt (@torzdf) may agree here that if you pay attention to the numbers (example 0.11000, drops to 0.9000 then goes to 0.15000) it tells you that the model is still very much engaged in the training process and still "learning".
So my suggestion is when you have trained A->B 400K iterations, switch to B->A it also helps strengthen foundation of the model causing the results to become less corrupt in final images.
It also helps to tweak conversion settings (using gaussian, normalized etc.) to find the optimal result. But using still images is truly a long process and takes A LOT more training then if doing movie sequences.
I my experience (limited) that is.
Keep at it. Will share my results when reaching the 1.000.000 mark.
/sergor
Re: DLight model still blurry after 400k iterations
sergor wrote: ↑Tue Sep 29, 2020 11:25 amI then did the following:
From training A -> B, I switched training B -> A. Focus on the two different sides has vastly improved conversion which was done at 350K and 450K iterations.
So my suggestion is when you have trained A->B 400K iterations, switch to B->A it also helps strengthen foundation of the model causing the results to become less corrupt in final images.
/sergor
Is there a trick to do the A>B to B>A swap? Is there a checkbox anywhere, or do you change/swap the directories and alignment files in the training tab?
- bryanlyon
- Site Admin
- Posts: 546
- Joined: Fri Jul 12, 2019 12:49 am
- Location: San Francisco
- Has thanked: 3 times
- Been thanked: 136 times
- Contact:
Re: DLight model still blurry after 400k iterations
Do not do that. It is the exact opposite of what you should do for a quality swap. (Keep A and B separate)
Re: DLight model still blurry after 400k iterations
My experience with DLight gives good A quality, and totally washed out B quality. Dunno if that helps you. 192 SAE and Villain give me the best results.
- bryanlyon
- Site Admin
- Posts: 546
- Joined: Fri Jul 12, 2019 12:49 am
- Location: San Francisco
- Has thanked: 3 times
- Been thanked: 136 times
- Contact:
Re: DLight model still blurry after 400k iterations
DLight is an "unbalanced" model. It's meant specifically for B's face swapped onto A. It will only work well in that direction.