Skip to content

PyTorch Lightning based training of Semantic Segmentation models

Notifications You must be signed in to change notification settings

akshaykulkarni07/pl-sem-seg

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

13 Commits
 
 
 
 
 
 
 
 

Repository files navigation

Semantic Segmentation using PyTorch Lightning

Repository for implementation and training of semantic segmentation models using PyTorch Lightning. This repo was contributed as a full example in the official PyTorch Lightning repository. However there have been further changes (majorly w.r.t. coding practices) to that example since my initial pull requests were merged. Thus, this repo is no longer being maintained.

Dataset Used

The KITTI semantic segmentation dataset is used in this. So, it needs to be downloaded from above link. It is used for it's small size (200 semantically annotated images and 200 test images). Data preprocessing and loading is as per this dataset. This dataset claims to be same in format to Cityscapes (a much larger dataset of road scenes), so same code can be used with some modifications (not done in this yet, due to memory limitations).

Models Implemented