pytorch/examples
Vedi su GitHubIs total variation loss necessary in fast_neural_style?
Open
#278 aperta il 3 gen 2018
good first issuequestion
Metriche repository
- Star
- (21.634 star)
- Metriche merge PR
- (Nessuna PR mergiata in 30 g)
Descrizione
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.