search

Prinsphield / ELEGANT

ELEGANT: Exchanging Latent Encodings with GAN for Transferring Multiple Face Attributes
https://arxiv.org/abs/1803.10562
MIT License
262 stars 42 forks source link

Loss function inconsistent with the article #11

Closed CharlesNord closed 5 years ago

CharlesNord commented 5 years ago

https://github.com/Prinsphield/ELEGANT/blob/6a36225a958ceee95419d7f0a098dae5c749b7f7/ELEGANT.py#L203 In your code , the loss function of discriminator is not the same as in the paper. The weight of losses from two discriminators are not equal, is this setting important and could lead to a better performance?

Prinsphield commented 5 years ago

For simplicity, the paper neglects the coefficient in each loss term. Because the overall design is towards the right way, so it will work finally.

Actually, I have not tried other coefficients. It may lead to better performance. You may adjust the coefficient accordingly when the total number of attributes or the training attributes get changed in order to obtain better performance.

CharlesNord commented 5 years ago

For simplicity, the paper neglects the coefficient in each loss term. Because the overall design is towards the right way, so it will work finally.

Actually, I have not tried other coefficients. It may lead to better performance. You may adjust the coefficient accordingly when the total number of attributes or the training attributes get changed in order to obtain better performance.

I get it, thank you very much for your reply