8000 GitHub - eric-mitchell/dart: Deep Autoregressive Tensor Trains
[go: up one dir, main page]
More Web Proxy on the site http://driver.im/
Skip to content

eric-mitchell/dart

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

24 Commits
 
 
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

DART: Deep Autoregressive Tensor Trains

Getting started

The code requires Python version >=3.6. Package dependencies are listed in requirements.txt. Install with pip install -r requirements.txt.

Training

Available arguments are listed in src/args.py. Example training commands are:

python -m run --distribution binary --name binary_nolatents --device cuda:0 --log_path log

python -m run --distribution gaussian --name gaussian_nolatents --device cuda:0 --log_path log

python -m run --distribution gaussian --name gaussian_latents4 --device cuda:0 --log_path log --alpha_dim 4

About

Deep Autoregressive Tensor Trains

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Languages

0