enter image description here

I'm predicting the used 9 pictures to predict the last picture
so (40,40,9) -> unet -> (40,40,1)

but as you see the predict picture
enter image description here

It's not just a mask(0or 1) its float
so which loss function should I define to achieve the best Unet result? and why?


Your Answer

By clicking “Post Your Answer”, you agree to our terms of service, privacy policy and cookie policy

Browse other questions tagged or ask your own question.