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

MNIST Generator #27

Open hi-bingo opened 5 years ago

hi-bingo commented 5 years ago

I clone the code and download the mnist in csv, run python experiment.py --settings_file mnistfull. Almost all images generated in experiments/plot are digit as '1' after 250 epoches which seems like mode collapse . Is it a common phenomenon？ Or how to avoid it?