chiixy

Results 3 comments of chiixy

why In stage 3, train the GAN loss to nan and the tensor of the network output image to nan？

I have the same NAN pix loss and perceptual loss when i train my 1024 resolution model and need to connect 512 size feat in stage3. I found first time...

why In stage 3, train the GAN loss to nan and the tensor of the network output image to nan？

> > I have the same NAN pix loss and perceptual loss when i train my 1024 resolution model and need to connect 512 size feat in stage3. > >...

problem about face_ratio

I have the same confusion about this face_ratio, and i think maybe author make a mistake in this place? I remove these face_ratio and multiplies face_ratio at 248, 253 line...