andreas128 / SRFlow

Official SRFlow training code: Super-Resolution using Normalizing Flow in PyTorch
Other
831 stars 111 forks source link

Will you use all of the z during your training/testing process? #42

Open TiankaiHang opened 3 years ago

TiankaiHang commented 3 years ago

As the subject. image Will you use zL, z{L-1}, ..., z_1, all of them, to do the training or the inference?

A more detailed question? How do you calculate -log(p(z)), does it equal to \sum_{i=1}^L (log(p(z_i)))?

Thanks.