https://github.com/catalystcode/image-segmentation-using-tiramisu

Image segmenation using deep learning - Tiramisu
https://github.com/catalystcode/image-segmentation-using-tiramisu

Last synced: 6 months ago
JSON representation

Image segmenation using deep learning - Tiramisu

• Host: GitHub
• URL: https://github.com/catalystcode/image-segmentation-using-tiramisu
• Owner: CatalystCode
• License: mit
• Created: 2018-04-18T09:09:25.000Z (over 7 years ago)
• Default Branch: master
• Last Pushed: 2020-12-07T02:52:43.000Z (about 5 years ago)
• Last Synced: 2024-07-09T19:57:10.771Z (over 1 year ago)
• Language: Jupyter Notebook
• Size: 7.29 MB
• Stars: 48
• Watchers: 10
• Forks: 20
• Open Issues: 4
• Metadata Files:
  • Readme: README.md
  • License: LICENSE

Awesome Lists containing this project

README

          

# Image Segmentation

## Overview

We recently developed a solution based on deep learning, i.e. Tiramisu, to segment the forground and remove the background in images. Our goal was to enable image retreival from a target catalogue image of a fashion retailer given a query mobile snapshot.  

 

## Contents 

In this repository, you'll find:

- the code to reproduce the image segmetnation described in the accompanying [code story](https://www.microsoft.com/developerblog/2018/04/18/deep-learning-image-segmentation-for-ecommerce-catalogue-visual-search/)

- how to train your own specific image segmentation with your own data

A trained model can be found [here](https://dwrds.blob.core.windows.net/tiramisu/TiramisuSmallModel_20180225.h5).