uceclz0/setr-pytorch

Rethinking Semantic Segmentation from a Sequence-to-Sequence Perspective with Transformers

Segmentation Transformer

Implementation of Segmentation Transformer in PyTorch, a new model to achieve SOTA in semantic segmentation while using transformer style encoders.

Features

• SETR
  • SETR-Naive
  • SETR-PUP
  • SETR-MLA
• SETR-Hybrid

To Do:

• Training Scripts

Installation

Create the environment:

conda env create -f environment.yml