search

sefibk / KernelGAN

Other
337 stars 77 forks source link

The settings of parameters #54

Open jiandandan001 opened 3 years ago

jiandandan001 commented 3 years ago

Hi, thank you for this nice work, and thank you for sharing the code.

I want to compare our method with the KernelGAN+ZSSR. Could you please tell me how to set paramters in the shared the code to reproce the results in the paper?

For example, the lambda_centralized and lambda_sparse are set to 1 and 5 respectively in the paper. However, there are 0 in the shared code.

lambda_sum2one = 0.5 lambda_bicubic = 5 lambda_boundaries = 0.5 lambda_centralized = 0 lambda_sparse = 0

To make a fair comparison, could you please tell me how should I change the code and parameetrs? By the way, for different testing images, are these parameetrs fixed or not ?

Thanks.

Best wishes!

sefibk commented 3 years ago

Regarding the lambdas - sorry for this not being clear enough but check out the learner.py code. These H.P. are inserted after the Bicubic constraint is satisfied.

In order to reproduce - simply follow the README - no need to change these parameters.

All the images are run with the same H.P.

jiandandan001 commented 3 years ago

OK. Thanks