search

eriklindernoren / PyTorch-GAN

PyTorch implementations of Generative Adversarial Networks.
MIT License
16.41k stars 4.07k forks source link

updata the way about how to load pretrain model #50

Closed chenyang1999 closed 5 years ago

chenyang1999 commented 5 years ago

updata the way about how to load pretrain model

eriklindernoren commented 5 years ago

Thanks :)

nixczhou commented 3 years ago

hello, i have a question, do we need to save and load optimizer.state_dict for resume training?

What stated in pytorch web: _It is important to also save the optimizer’s statedict, as this contains buffers and parameters that are updated as the model trains