Closed Carrotor116 closed 4 years ago
Hi, Thanks for the detailed description. Yes, it is the code for computing the PSNR of tonemapped predictions. The released model is a slightly improved version. Feel free to mention both numbers for comparison.
Hi, Thanks for the detailed description. Yes, it is the code for computing the PSNR of tonemapped predictions. The released model is a slightly improved version. Feel free to mention both numbers for comparison.
Thanks for your reply. So your work is real well :)
Hi, thanks for your work. I have a problem about the PNSR in your work. the code about psnr is following one in mode.py
I understand it is calculation of
PNSR_T
. While I tested the pretrained model in Kalantari's dataset and got a averagePSNR_T
(41.9977) which is different of thePSNR_T
in your paper (40.81 for unet ver. and 41.65 for resnet ver.). I wonder if this is normal or the code of calculatePSNR_T
is something other?The detail of my testing in following:
First I cloned the projection and downloaded the pretrained model and Kalantari's dataset (from the link in readme.md) Then I have the test dataset and pretrained model
I made a test by the command
the log is following: