Results 3 comments of Yang Liu

> Code is not working for celeba. I am not able to obtain the results as reported in the paper. The image reconstruction and random sample generation both are of...

I reimplemented their work, the model can perfectly fit the training data, but can NOT generalize to unseen data robustly. By "not robust" I mean, 1. different seed yields very...

> So this is the reason why the currently-supported events are referred to as "discrete" events. > > "Continuous" events are a planned feature. If this is a priority for...