-
Thanks for your work！
1.Is the compute_patch_contextual_loss in loss.py corresponds to the CoBiRGB in your paper?
2.Is the CoBiRGB a kind of Pixel level loss like L1 in EDSR and RDN but compute the …
-
I use "python3 main.py --model EDSR --data_test Demo --scale 2 --test_only --save_results" to test given image of a bird, but the result is as the follow image, i don't understand why
![0853x4_x2_sr]…
-
Thank you for the code you provided. I am new at SR. I have a question when reading the code.why do we do MeanShift processing? What is the significance？
class MeanShift(nn.Module):
def __in…
-
Hi, the performance of EDSR is impressive, and I am new to super-resolution.
Here, I have two simple questions:
1. README declares that:
> We measured PSNR using DIV2K 0801 ~ 0900 ...
But the…
-
Hi, Jiahui,
When I run wdsr_a, there is a error:
Making model...
Traceback (most recent call last):
File "D:/project/pytorch/SR/EDSR-m/src/main.py", line 27, in
main()
File "D:/projec…
-
and can this algorithm remove noise from image??
thank you
-
Hi krasserm,
I am training the argan model with slight change, instead of using gradient.tape() inside train loop, I am using tf.keras "train_on_batch" .
I am also doing one sided label smoothin…
-
Hi, thanks for you great work. I find nEpochs is set as 10000 in the opts.lua, does it mean that we need 10000 epochs to get the results in the paper ?
-
Hi, thanks for the code. I notice that your model is developed by WDSR, would you please provide the comparision results with WDSR and EDSR? Thanks.
https://github.com/JiahuiYu/wdsr_ntire2018/blob/…
-