/torchcv-seg

Semantic Segmentation ported from TorchCV

Primary LanguagePythonApache License 2.0Apache-2.0

TorchCV-Seg: Open Source for Semantic Segmentation.

@misc{CV2018,
  author =       {Donny You (youansheng@gmail.com)},
  howpublished = {\url{https://github.com/youansheng/torchcv-seg}},
  year =         {2018}
}

This repository provides source code for some deep learning based semantic segmentation. We'll do our best to keep this repository up to date. If you do find a problem about this repository, please raise it as an issue. We will fix it immediately.

Implemented Papers

  • Semantic Segmentation
    • PSPNet: Pyramid Scene Parsing Network
    • DeepLabV3: Rethinking Atrous Convolution for Semantic Image Segmentation
    • DenseASPP: DenseASPP for Semantic Segmentation in Street Scenes

Performances with torchcv-seg

  • CityScapes (Single Scale Whole Image Test): Base LR 0.01, Crop Size 769
Checkpoints Backbone Train Test mIOU BS Iters Scripts
PSPNet 3x3-Res101 train val 78.20 8 4W PSPNet
DeepLabV3 3x3-Res101 train val 79.13 8 4W DeepLabV3
  • ADE20K (Single Scale Whole Image Test): Base LR 0.02, Crop Size 520
Checkpoints Backbone Train Test mIOU PixelACC BatchSize Iters Scripts
PSPNet 3x3-Res50 train val 41.52 80.09 16 15W PSPNet
DeepLabv3 3x3-Res50 train val 42.16 80.36 16 15W DeepLabV3
PSPNet 3x3-Res101 train val 43.60 81.30 16 15W PSPNet
DeepLabv3 3x3-Res101 train val 44.13 81.42 16 15W DeepLabV3