Skip to content

Latest commit

 

History

History
20 lines (17 loc) · 697 Bytes

README.md

File metadata and controls

20 lines (17 loc) · 697 Bytes

DeepLab V3+ PyTorch

DeepLab V3+ is a state-of-the-art model for semantic segmentation.

This repository contains a PyTorch implementation of DeepLab V3+ trained for full driving scene segmentation tasks.

Pending Tasks

  • Base DeepLab model
    • DeepLab decoder module
    • Xception feature extractor backbone
    • Dataloaders, train script, metrics
    • Data augmentation pipeline
  • Upload pretrained weights and results
  • Planned extensions
    • Mixed precision training
    • Faster, MobileNet-v2 backbone
    • Pretraining all backbones on ImageNet
    • Dataloader for City-scapes
    • Dataloader for Baidu apollo dataset
    • Setup inference mode