Skip to content

A variational recurrent neural network implementation in tensorflow

Notifications You must be signed in to change notification settings

kimkilho/tensorflow-vrnn

 
 

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

25 Commits
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

tensorflow-vrnn

A variational recurrent neural network as described in:

Chung, J., Kastner, K., Dinh, L., Goel, K., Courville, A. C., & Bengio, Y. (2015). A recurrent latent variable model for sequential data. In Advances in neural information processing systems (pp. 2980-2988).

Requirements

python == 3.5 tensorflow == 1.2.1 numpy==1.13.1

main.py

  • train this model
python main.py

cell.py

  • VRNNCell structure

utils.py

  • Basic functions implementation

ops.py

  • Basic operations based on tensorflow

config.py

  • Basic configuration of model
  • Every configuration can be changed here.

VRNN Structure Global Structure

About

A variational recurrent neural network implementation in tensorflow

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Languages

  • Python 100.0%