You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
As pointed out in Wangt-CN/DisCo#86, the accurate code is mse = np.mean((original/1.0 - compressed/1.0) ** 2) instead of mse = np.mean((original - compressed) ** 2) , because original and compressed images are uint8 in their code, and (original - compressed) * * 2 will cause numerical overflow.
If you use their evaluation code of computing PSNR, please update your results.
The text was updated successfully, but these errors were encountered:
The Disco code of computing PSNR as follows is wrong:
https://github.com/Wangt-CN/DisCo/blob/8538889c9ee9edd8dd43ffee182d1a91ce7a9828/tool/metrics/ssim_l1_lpips_psnr.py#L13.
As pointed out in Wangt-CN/DisCo#86, the accurate code is mse = np.mean((original/1.0 - compressed/1.0) ** 2) instead of mse = np.mean((original - compressed) ** 2) , because original and compressed images are uint8 in their code, and (original - compressed) * * 2 will cause numerical overflow.
If you use their evaluation code of computing PSNR, please update your results.
The text was updated successfully, but these errors were encountered: