Low PSNR when evaluate the reproduction model and pretrained model about meta-sr-pytorch HOT 16 OPEN

I found that there may be some bugs in the latest version of the code. I tried to switch the code to the previous version(2e1a266) and got a PSNR value similar to that in the paper.

from meta-sr-pytorch.

Thanks a lot, @hanlinwu! I will try it soon and update here if it works well.

from meta-sr-pytorch.

Here is the update. By rolling back to the commit as @hanlinwu pointed out, I successfully achieved around 41dB PSNR on the Set5 validation set. However, when I test the pre-trained model on B100 (which I created myself by Octave rather than Matlab), the PSNR is even lower (around 27dB).

I found that I could not actually reproduce the input image by running the dataset generation script in MATLAB using Octave. @XuecaiHu Would you mind if you could share the B100 dataset that you use for the training or sharing the Matlab version that you run? Thanks a lot!

from meta-sr-pytorch.

Did you solve this problem?@hcwang95

from meta-sr-pytorch.

@reddandelion217 No, I've tried one another training dataset and still cannot reproduce the performance in the paper. Not sure where is the problem.

from meta-sr-pytorch.

@hcwang95 After analyzing the file history, I think the problem comes from the code below in file trainer.py, because there is no reason to do this:
i = 1
h, w,_ = pos_mat.size()
while(pos_mat[i][0][0]<= 1e-6 and i<h):
i = i+1

    j = 1
    #pdb.set_trace()
    h, w,_ = pos_mat.size()
    while(pos_mat[0][j][1]<= 1e-6 and j<w):
        j = j+1

    pos_mat_small = pos_mat[0:i,0:j,:]

and the code below in file metardn.py:
local_weight = self.repeat_weight(local_weight,scale_int,x.size(2),x.size(3))

from meta-sr-pytorch.

@hcwang95 Hello, have you solved the reproduction problem?
I have a similar problem with you. I used the script ./generate_LR_metasr_X1_X4_idealboy.m to prepare the B100 dataset. Then I used the downloaded model_1000.pt to evaluate the PSNR and SSIM results.
What I got at scales 1.1 ~ 2.0 is as follows:

The PSNR results I got are much lower than that from the paper. @XuecaiHu Could you please help solve the problem? Thank you!

from meta-sr-pytorch.

@hcwang95 Can you provide some details about how you solve the low-PSNR problem? I meet the same problem with you. I feel confused about @hanlinwu 's comment -- on the preview version

from meta-sr-pytorch.

@supercaoO can you check the output of the h_project_coord and w_project_coord？

from meta-sr-pytorch.

and show me the results @supercaoO

from meta-sr-pytorch.

@XuecaiHu Thanks for your reply. I have emailed you ([email protected]) the results.

from meta-sr-pytorch.

@liangheng96 Hello. After cloning the repository, maybe you can try git reset --hard 2e1a266832ab3a2dd855c98c34387c47a4ebec01 to switch it to the previous version of the repository. I think that is what @hanlinwu means.

from meta-sr-pytorch.

@supercaoO Thank you! I know what @hanlinwu means by now. Now I swith to the previous version, and then I can get the similar results to the paper. Thank you very much!

from meta-sr-pytorch.

I think @reddandelion217 's comment is right. I delete these codes and then get the right PSNR.

@hcwang95 After analyzing the file history, I think the problem comes from the code below in file trainer.py, because there is no reason to do this:
i = 1
h, w,_ = pos_mat.size()
while(pos_mat[i][0][0]<= 1e-6 and i<h):
i = i+1

    j = 1
    #pdb.set_trace()
    h, w,_ = pos_mat.size()
    while(pos_mat[0][j][1]<= 1e-6 and j<w):
        j = j+1

    pos_mat_small = pos_mat[0:i,0:j,:]

and the code below in file metardn.py:
local_weight = self.repeat_weight(local_weight,scale_int,x.size(2),x.size(3))

from meta-sr-pytorch.

Hi, do you see any errors in meta.py, saying 'ValueError: only one element tensors can be converted to Python scalars'? Thanks!@hcwang95

from meta-sr-pytorch.

Any updates on this?

from meta-sr-pytorch.