Skip to content

Pytorch code used for modeling families of nondifferentiable computational graphs

Notifications You must be signed in to change notification settings

briantimar/dag-gen

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

dag-gen

Code for generating DAGs. The RNN models for DAGs are based on the GraphRNN paper.

Running tests

In the terminal:

./test

to do

  • Allow for scaling of edges during forward pass
  • Speed up the DAG forward pass
    • First, benchmark it
    • maybe do topological sort after graph construction? Then each layer can be updated in parallel.

About

Pytorch code used for modeling families of nondifferentiable computational graphs

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published