Dose not the SRREsNet use the adversarial loss?

twtygqyy / pytorch-SRResNet

pytorch implementation for Photo-Realistic Single Image Super-Resolution Using a Generative Adversarial Network arXiv:1609.04802

MIT License

477 stars 131 forks source link

Closed Ikhwansong closed 3 years ago

Ikhwansong commented 3 years ago

It seems that there is no adversarial loss for a discriminator, even the discriminator is not used.

Why?

yuinnLIU commented 3 years ago

Because SRResNet only used the generator structure in SRGAN.

Ikhwansong commented 3 years ago

Thanks