Skip to content

A Tensorflow Implementation of "SegFormer: Simple and Efficient Design for Semantic Segmentation with Transformers"

Notifications You must be signed in to change notification settings

tejas1904/SegFormer-tf

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

22 Commits
 
 
 
 
 
 
 
 

Repository files navigation

#[WIP]

  • Add Model
  • Train on ADE20k dataset
  • Train on cityscapes

SegFormer-tf

This repository is about an implementation of the research paper "SegFormer: Simple and Efficient Design for Semantic Segmentation with Transformers"

SegFormer is a Transformer-based framework for semantic segmentation that unifies Transformers with lightweight multilayer perceptron (MLP) decoders.

Paper : https://arxiv.org/pdf/2105.15203

Model Architecture :

Detailed overview of MiT :

About

A Tensorflow Implementation of "SegFormer: Simple and Efficient Design for Semantic Segmentation with Transformers"

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Languages

  • Jupyter Notebook 99.8%
  • Python 0.2%