pytorch/examples
Is total variation loss necessary in fast_neural_style?
Aberta
#278 aberto em 3 de jan. de 2018
good first issuequestion
Métricas do repositório
- Stars
- (21.634 estrelas)
- Métricas de merge de PR
- (Métricas PR pendentes)
Description
I notice that there is no total variation loss regularization implemented in the example of fast_neural_style. But the paper declared it and their torch version use it. I'm wondering if total variation loss is necessary or not in style transfer.