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
I'm working with two images, transformed to tensors in the shape of (1x3x500x500). I'm following the code examples for each metric from its web-page, but I do get nan for uqi, also for different "image"-pairs. Is there something else I might have missed? Or is there a pool of test files, that work like expected?
A few other metrics work with the same tensors; preds, target.
ergas 50.0
lpips 0.1482967
ms_ssim 0.97375298
psnr 29.01943779
ssim 0.8981939
reacted with thumbs up emoji reacted with thumbs down emoji reacted with laugh emoji reacted with hooray emoji reacted with confused emoji reacted with heart emoji reacted with rocket emoji reacted with eyes emoji
-
I'm working with two images, transformed to tensors in the shape of (1x3x500x500). I'm following the code examples for each metric from its web-page, but I do get nan for uqi, also for different "image"-pairs. Is there something else I might have missed? Or is there a pool of test files, that work like expected?
A few other metrics work with the same tensors; preds, target.
ergas 50.0
lpips 0.1482967
ms_ssim 0.97375298
psnr 29.01943779
ssim 0.8981939
uqi nan
uqi = UniversalImageQualityIndex()
uqi = uqi(preds, target)
Any advice or help is much appreciated. Regards, Rainer
Beta Was this translation helpful? Give feedback.
All reactions