search

thunil / TecoGAN

This repo contains source code and materials for the TEmporally COherent GAN SIGGRAPH project.
Apache License 2.0
5.99k stars 1.14k forks source link

Why should FNet，and SRNet be trained respectively ？because of gradient back propagation？ #110

Open hzg456 opened 3 years ago

hzg456 commented 3 years ago

Why should FNet，and SRNet be trained respectively(I mean using two Optimizers）？ because the function tfa.image.dense_image_warp cannot be used for gradient back propagation？

eewindfly commented 2 years ago

The pro is that you can fine-tine two networks separately, however, in the source code, no different hyper-parameters are applied. Therefore, I think respective training is not a must. If I am wrong, please correct me.