search

ratschlab / RGAN

Recurrent (conditional) generative adversarial networks for generating real-valued time series data.
https://arxiv.org/abs/1706.02633
MIT License
639 stars 181 forks source link

Pytorch version #23

Closed dmortem closed 6 years ago

dmortem commented 6 years ago

Hi, thank you for your codes. And I wonder whether there is a pytorch version of the codes?

corcra commented 6 years ago

There is not, I'm afraid. We would gladly appreciate someone rewriting it in pytorch!

dmortem commented 6 years ago

Hi, @corcra I wonder why to optimize D_logit_real to 1 instead of D_real. D_logit_real is the output of LSTM and D_real = sigmoid(D_logit_real). https://github.com/ratschlab/RGAN/blob/master/experiment.py#L77

dmortem commented 6 years ago

My mistake, the link of the code is https://github.com/ratschlab/RGAN/blob/master/model.py#L171