-
Thanks for creating this repo and very helpful blog post.
I tried inference x2 and x4 of EDSR model and it is good.
I'm changing source code to train for x8 model. In the `upsampling` method of `mod…
-
What would the terminal command be to evaluate the WDSR models with EDSR as backbone?
I added the following to the option.py
`parser.add_argument('--r_mean', type=float, default=0.4488,
…
-
如果按照wdsr论文里的，学习率应该是10倍？
-
Dear author, thank you for the pre-trained model. I tested the method on Buddha and Moha image
in a mat format (9x9x768x768x3), using bicubic interpolation in matlab. However, I got the results: av…
-
I cannot run the QuickStart(Demo) to test the algorithm with a image in the test folder.
I put the image in the test folder(EDSR-Pytorch/test), and I run the demo.sh in the src folder
the error hap…
-
Hello, I would like to improve the model with new pictures of faces, how can I do that?
Should my dataset have a specific shape?
-------------------------------------------------- ------------------…
-
hello,nice to meet you
I want to ask that
is checkpoint a pre-train model?
and how can i train it? thanks
looking forward your reply
-
In #40, you said you are doing data normaliztion. but i have no idea where 127.5 come from.
as far as i know, data normalization is something like y = (x - μ)/σ, where μ is mean, and σ is the stan…
-
WDSR-A
x/2->2x->x/2
computation:
3x3x2/2+3x3x2/2=18
act:
2
3x3Conv:
100%
WDSR-B:
x->6x->0.8x->x
computation:
6+6x0.8+3x3x0.8=18
act:
6
3x3Conv:
40%
(I think you use the second 1x1 Co…
-
When running EDSR model with scale 3, the following error occurs, scale 2 and 4 is OK, did anyone encounter this problem?
`Traceback (most recent call last):
File "D:/EDSR-PyTorch-master/src/main.…