Unable to reproduce EnlightenGAN-N about enlightengan HOT 9 CLOSED

You should upload some results then I can help debug

from enlightengan.

My apologies for taking so long to reply. Here are a few sample images I have.
The results of enhancement from my end have a lot of artifacts around light sources.

from enlightengan.

Do you use the dark dataset in BDD-100k and bright dataset from what I provided?

from enlightengan.

Yes I did for both. More specifically I used images from BDD-100k that are labeled as "night" in the labels.

Do you know what is causing this artifact, or how to move forward from here to troubleshoot the problem?

from enlightengan.

我也用bdd-100k数据集去训练，我想问您说低亮度数据集使用自己的，正常光数据集使用您提供的1016张图片，那我自己低亮度的数据个数有限制吗，对低亮度的图片还有其他要求吗？非常期待您 的回复 @yueruchen

from enlightengan.

I'm really busy over the last month. Have you solved the problems? @zhangxiaopang88 @russelltankl

from enlightengan.

@zhangxiaopang88 If you want to use your own dataset, you should confirm that 1) the dataset you prepared is not extremely dark, which is not suitable in our case due to severe noise. 2) prepare ~1000 data should be enough

from enlightengan.

@yueruchen I have not solved it yet. Currently, I'm not sure how to proceed

from enlightengan.

Could you please slightly enlarge the self_feature_preserving_loss --vgg ?
Normally we use gan loss and vgg loss to balance the brightness and naturalness. Seems that your results show that you make it too much bright, so you should increase the --vgg loss weight.

from enlightengan.