https://github.com/harveyslash/facial-similarity-with-siamese-networks-in-pytorch

Implementing Siamese networks with a contrastive loss for similarity learning
https://github.com/harveyslash/facial-similarity-with-siamese-networks-in-pytorch

deep-learning face-recognition neural-network pytorch pytorch-tutorial siamese-network

Last synced: 1 day ago
JSON representation

Implementing Siamese networks with a contrastive loss for similarity learning

• Host: GitHub
• URL: https://github.com/harveyslash/facial-similarity-with-siamese-networks-in-pytorch
• Owner: harveyslash
• License: mit
• Created: 2017-07-19T04:10:30.000Z (over 7 years ago)
• Default Branch: master
• Last Pushed: 2020-07-16T00:03:31.000Z (over 4 years ago)
• Last Synced: 2024-12-18T08:06:38.866Z (9 days ago)
• Topics: deep-learning, face-recognition, neural-network, pytorch, pytorch-tutorial, siamese-network
• Language: Jupyter Notebook
• Homepage: https://hackernoon.com/one-shot-learning-with-siamese-networks-in-pytorch-8ddaab10340e
• Size: 6.18 MB
• Stars: 978
• Watchers: 23
• Forks: 273
• Open Issues: 12
• Metadata Files:
  • Readme: README.md
  • License: LICENSE

Awesome Lists containing this project

README

        
# Facial Similarity with Siamese Networks in Pytorch

You can read the accompanying article at https://hackernoon.com/one-shot-learning-with-siamese-networks-in-pytorch-8ddaab10340e

The goal is to teach a siamese network to be able to distinguish pairs of images. 

This project uses pytorch. 

Any dataset can be used. Each class must be in its own folder. This is the same structure that PyTorch's own image folder dataset uses.

## Update: Looking for contributor (July 2020)

If you would like to be a part of this projec, please head to https://github.com/harveyslash/Facial-Similarity-with-Siamese-Networks-in-Pytorch/issues/35

### Converting pgm files (if you decide to use the AT&T dataset) to png

1. Install imagemagick 

2. Go to root directory of the images

3. Run `find -name "*pgm" | xargs -I {} convert {} {}.png`

## Installing the right version of PyTorch 

This project is updated to be compatible with pytorch 0.4.0

#### This project requires python3.6