xc-7984 comments

Repositories
Issues
Comments

Results 2 comments of


                                            xc-7984

Partitions K

So the best K is 2?When k=2,Glow is h(x1)=x1,while yours is h(x1) = s1*x1+u1.Only changing this can make the results better than Glow on the Imagenet dataset?I amd confused about...

Partitions K

So if i replace the dynamic linear transform with a affine coupling layer and a actnorm layer,the result should be better.Glow consists of a affine coupling layer and a actnorm...