Skip to content

Latest commit

 

History

History
32 lines (25 loc) · 1.04 KB

README.md

File metadata and controls

32 lines (25 loc) · 1.04 KB
Raw

learn2com

Original Paper: Learning to Communicate: Channel Auto-encoders, Domain Specific Regularizers, and Attention

Installation

  • Clone the repo and cd into it.

    git clone https://github.com/bitsandscraps/learn2com.git
cd learn2com

  • Install the virtual evironment. I use pipenv but you may use whatever program you want.

    pipenv --three

    To use pipenv, you need to first erase the line that has tensorflow in the Pipfile, and then re-install tensorflow in any way you want.

Run the Program

pipenv run python -m learn2com.main

learn2com.main can take a handful of command-line options. Check it out using the -h option, or reading through the code.

TODO

  • The delay channel is not working properly. The network fails miserably with delay regularization.
  • The performance is not even close to what the paper is saying.
  • Plot-generation code
  • Localization networks