Skip to content

rezmansouri/SateLight

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

6 Commits
 
 
 
 
 
 
 
 

Repository files navigation

SateLight 📡

Introduction

SateLight does the task of image retrieval. It uses a simple architecture trained on the DeepSat (SAT-6) dataset, with the triplet loss function.

Usage

You can clone the repository on your own environment and run the SateLight.ipynb notebook, or run it via Google Colaboratory here. The SateLight.pdf is an already run instance of the notebook for reading purposes.

Acknowledgements

  1. Cristian Lungu's Tutorial about Triplet Loss on YouTube
  2. DeepLearning.AI's Lecture on Triplet Loss in the Convolutional Neural Networks Course