Ecosyste.ms: Awesome
An open API service indexing awesome lists of open source software.
https://github.com/bourdakos1/capsule-networks
A Tensorflow implementation of Capsule Networks
https://github.com/bourdakos1/capsule-networks
Last synced: about 1 month ago
JSON representation
A Tensorflow implementation of Capsule Networks
- Host: GitHub
- URL: https://github.com/bourdakos1/capsule-networks
- Owner: bourdakos1
- License: mit
- Created: 2017-11-10T00:03:43.000Z (over 6 years ago)
- Default Branch: master
- Last Pushed: 2018-02-15T16:52:08.000Z (over 6 years ago)
- Last Synced: 2024-02-18T05:31:27.657Z (5 months ago)
- Language: Python
- Size: 11 MB
- Stars: 478
- Watchers: 43
- Forks: 159
- Open Issues: 8
-
Metadata Files:
- Readme: README.md
- License: LICENSE
Lists
- awesome-CapsNet - bourdakos1/capsule-networks
- awesome-capsule-networks - bourdakos1/capsule-networks
- my-awesome-stars - bourdakos1/capsule-networks - A Tensorflow implementation of Capsule Networks (Python)
README
# Capsule Networks
A Tensorflow implementation of Capsule Networks
For more information on Capsule Networks please read my [Medium article](https://hackernoon.com/capsule-networks-are-shaking-up-ai-heres-how-to-use-them-c233a0971952).
**[Update]** Check out my [new article](https://medium.freecodecamp.org/understanding-capsule-networks-ais-alluring-new-architecture-bdb228173ddc) with a deeper explanation on how capsules work.
This repo was largely based off of [naturomics CapsNet-Tensorflow repo](https://github.com/naturomics/CapsNet-Tensorflow) with the current differences being an added `requirements.txt` and the MNIST dataset is included. Power users may want to refer to the naturomics repo for the latest versions.
## Usage
Install the requirements and download dataset:
```bash
pip install -r requirements.txt
python download_data.py
```
Start training!
```bash
python main.py
```
## Testing Accuracy
```bash
python main.py --is_training False
```
## Visualization
Check out this [Visualization Tool](https://github.com/bourdakos1/CapsNet-Visualization) I built to play around with the DigitCaps vectors to see how it effects the recontructions:
[](https://github.com/bourdakos1/CapsNet-Visualization)