About your NIQE result about enlightengan HOT 11 CLOSED

This experiment was conducted so long ago and I need some time to check the detail.
But you could compare the results with a recent work https://arxiv.org/abs/1905.04161. We got nearly the same results which means the experiments setting is also the same.

from enlightengan.

@yueruchen Thanks for your patient reply. I have 2 more questions.

1. Is your network capable of dealing with images with arbitrary size ?
2. In your code, what is the difference between 'self.fake_patch' and 'self.fake_patch_1' ? Why not combine them ?

from enlightengan.

1. Yes, it is fully convolutional.
2. In the original setting we only random crop 1 patch in a large image. Later we choose to select multiple patches so add another self.fake_patch_1, it is a historical problem, sorry.

from enlightengan.

I see. Thank you

from enlightengan.

So, if I wanna use the pretrained model to test my own image, I have to feed the image along with its corresponding gray image (self regularization). Am I right ?

from enlightengan.

No, it will synthesize the gray image automatically.

from enlightengan.

I have tested your provided model on all subsets. The NIQE score on VV subset differs greatly from what you have reported in Table 1 (4.799 vs 2.581). Is it normal ?

from enlightengan.

I just tested it again and got same results, please check your own problem, probably about 1) NIQE implementation (I use the official version). 2) do not change the resolution of test data.

from enlightengan.

I also used the official code of NIQE.
When I tested on VV subset, some images raised the error of insufficient GPU memory. So, did you use at least 2 gpu cards during testing process ?

from enlightengan.

@UtopiaHu I used V100 which has 32gb memory. If you want to reproduce our results you need to try a large memory gpu. Or you cloud try to retrain the network with a smaller model (decrese channel number)

from enlightengan.

I see, thanks

from enlightengan.