search

NVIDIA / vid2vid

Pytorch implementation of our method for high-resolution (e.g. 2048x1024) photorealistic video-to-video translation.
Other
8.57k stars 1.2k forks source link

Error in the function _init_params in models.py and update_learning_rate in base_model.py #118

Closed bansals888 closed 5 years ago

bansals888 commented 5 years ago

Screenshot (7) There are following two problems with this function:- (1)-In the function init_params it should also get a parameter "data_loader" as when then condition ( ( (start_epoch > opt.niter_step) is encountered it will give an error. So we should also pass "data_loader" as parameter from train.py (2)- When the condition (start_epoch > opt.niter) is encountered it will call "update_learning_rate" Screenshot (9)

which is using only "optimizer_D" so it is giving an error. So there should be two update_learning_rate each for Generator and Discriminator. Can @tcwang0509 confirm it?

tcwang0509 commented 5 years ago

Sorry for the errors. It should be fixed now. Thanks!