Skip to content

A simple tensorflow implementation of CapsNet (by Dr. G. Hinton), based on my understanding. This repository is built with an aim to simplify the concept, implement and understand it.

Notifications You must be signed in to change notification settings

rohit-mehra/CapsNet-tensorflow-jupyter

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

10 Commits
 
 
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

CapsNet-tensorflow-jupyter

License Contributions welcome

A Tensorflow implementation of CapsNet, based on my understanding. This repository is built with an aim to simplify the concept, implement and understand it.

Any suggestions, or any mistake you find, I'll be happy to entertain.

Credits for this amazing comparison: https://github.com/naturomics/CapsNet-Tensorflow capsVSneuron

Requirements

  • python3
  • numpy==1.13.1
  • tensorflow==1.3.0

Usage

Clone this repository with git.

$ git clone https://github.com/rrqq/CapsNet-tensorflow-jupyter.git
$ cd CapsNet-tensorflow-jupyter-master

Run Options

  1. Use Jupyter Notebook (with visualizations)
  2. From linux terminal:
$ script -c "sudo python3 main.py" train_log.txt
  1. For Dynamic Loop implementation:
$ script -c "sudo python3 dynamic_main.py" train_log_dynamic.txt

Test Accuracy (dynamic_main.py): 99.38 % First round with default parameters as in paper. The test set was the default provided by Tensorflow.

Reference

In depth analysis.

About

A simple tensorflow implementation of CapsNet (by Dr. G. Hinton), based on my understanding. This repository is built with an aim to simplify the concept, implement and understand it.

Topics

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published