search

menyifang / ADGAN

The Implementation of paper "Controllable Person Image Synthesis with Attribute-Decomposed GAN" CVPR 2020 (Oral); Pose and Appearance Attributes Transfer;
473 stars 90 forks source link

About the perceptual loss #3

Closed mazzzystar closed 4 years ago

mazzzystar commented 4 years ago

In your paper, the perceptual loss was:

# vggsubmod refers to certain layer of VGG.
Lper = L1(gram(vggsubmod(x)), gram(vggsubmod(y))

However in your implementation: https://github.com/menyifang/ADGAN/blob/d948cb135801c83295e9427cab5d7d738436aa95/losses/L1_plus_perceptualLoss.py#L63-L72

Could you give some explanation on that ? thanks.

menyifang commented 4 years ago

In your paper, the perceptual loss was:

# vggsubmod refers to certain layer of VGG.
Lper = L1(gram(vggsubmod(x)), gram(vggsubmod(y))

However in your implementation: https://github.com/menyifang/ADGAN/blob/d948cb135801c83295e9427cab5d7d738436aa95/losses/L1_plus_perceptualLoss.py#L63-L72

Could you give some explanation on that ? thanks.

Hi @mazzzystar, thank you for your correction! Here we directly use the implement of perceptual loss from PATN and mistake it as common style loss in perceptual loss. We will correct this issue in our arxiv version.