zerodohero
zerodohero
> For the synthetic dataset, we have used the ground truth kernel. For real dataset, we have used a kernel estimation algorithm based on MAP framework. Also, you may refer...
> For the real images, first, accurate kernel estimation is required to get plausible result. > Second, most of the real images have JPEG compression artifacts and noise. It looks...
> > how to test by using my own dataset? > > You just need to replace the pictures in ‘Input/g20/Set5’ and delete the relevant code of 'gt' in test.py...
I have the same problem, and I can't use my own image to generate hyperresolution images, and I guarantee that gt is twice as much input as input. And I...
> Hello, If you are talking about this sentence in the conclusion section, " Also, the proposed network with a low number of parameters (i.e., with a maximum size of...
> To get the number of parameters: (5.5*1024*1024*8bytes)/32(float32) Regards, Sajad > […](#) > On Tue, May 26, 2020 at 8:45 PM zerodohero ***@***.***> wrote: Thank you, is 5.5M the parameter...
> It either clips or compresses the values accordingly. > I do not remember. > Any, I think it is not significant at all thank you very much.
> 1. Thanks for the compliments. > 2. IDK why you get these messages. Please verify your environment is exactly as specified in the requirements.txt. > 3. I didn't try...
> I am not familiar with these warnings but I suspect the environment. > 7000x7000 is larger than I experimented on - I hope it works well... It should! ok,Thank...