Skip to content
/ EB_GFN Public

Code for our paper "Generative Flow Networks for Discrete Probabilistic Modeling"

License

Notifications You must be signed in to change notification settings

GFNOrg/EB_GFN

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

11 Commits
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

Energy-based GFlowNets

Code for our ICML 2022 paper Generative Flow Networks for Discrete Probabilistic Modeling by Dinghuai Zhang, Nikolay Malkin, Zhen Liu, Alexandra Volokhova, Aaron Courville, Yoshua Bengio.

Example

Synthetic tasks

python -m synthetic.train --data checkerboard --lr 1e-3 --type tblb --hid_layer 3 --hid 256 --print_every 100 --glr 1e-3 --zlr 1 --rand_coef 0 --back_ratio 0.5 --lin_k 1 --warmup_k 1e5 --with_mh 1

Discrete image modeling

python -m deepebm.ebm --model mlp-256 --lr 1e-4 --type tblb --hid_layer 3 --hid 256 --glr 1e-3 --zlr 1 --rand_coef 0 --back_ratio 0.5 --lin_k 1 --warmup_k 5e4 --with_mh 1 --print_every 100 --mc_num 5

About

Code for our paper "Generative Flow Networks for Discrete Probabilistic Modeling"

Resources

License

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Languages