Skip to content

Simple numpy implementation of (Bayesian) Neural Network

License

Notifications You must be signed in to change notification settings

aurora1625/bayesnn

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

42 Commits
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

bayesnn

Simple numpy implementation of (Bayesian) Neural Network

Instructions

Running MNIST experiment

  • change the param.path_data in demo/mnist-sghmc.py to your dataset
  • python mnist-sghmc.py 2>log.txt
  • note: the evaluation statistics comes out from stderr, which is redirected into log.txt in last command

How to adapting to other classification experiment:

  • check mnist.py, which is specific to mnist dataset experiment
  • get a copy, change the function cfg_param and run_exp
  • basically we need a rewritten version of mnist.py and demo/mnist-sghmc.py

About

Simple numpy implementation of (Bayesian) Neural Network

Resources

License

Stars

Watchers

Forks

Packages

No packages published