DLight model still blurry after 400k iterations

Converting source frames into swapped frames
Forum rules
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.
Post Reply
User avatar
iguana314
Posts: 3
Joined: Thu Sep 10, 2020 2:05 pm

DLight model still blurry after 400k iterations

Post by iguana314 »

Hi,

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?

User avatar
torzdf
Posts: 941
Joined: Fri Jul 12, 2019 12:53 am
Answers: 126
Has thanked: 26 times
Been thanked: 184 times

Re: DLight model still blurry after 400k iterations

Post by torzdf »

*Generally* still blurry is down to data issues, or a requirement to train longer.

If the image is a close-up then there is likely to always be some blurring due to upscaling.

My word is final


User avatar
sergor
Posts: 12
Joined: Wed Jan 15, 2020 7:59 pm
Has thanked: 8 times

Re: DLight model still blurry after 400k iterations

Post by sergor »

Hi,

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

Post Reply