@misc{mt-segmentation,
    author = {Ansheng You, Zhenhua Chai},
    title = {MT-Segmentation},
    howpublished = {\url{https://git.sankuai.com/users/youansheng/repos/mt-segmentation}},
    year = {2020}
}

This repository provides source code for most deep learning based cv problems. We'll do our best to keep this repository up-to-date. If you do find a problem about this repository, please raise an issue or submit a pull request.

• Semantic Segmentation
  • DeepLabV3: Rethinking Atrous Convolution for Semantic Image Segmentation
  • PSPNet: Pyramid Scene Parsing Network
  • DenseASPP: DenseASPP for Semantic Segmentation in Street Scenes
  • Asymmetric Non-local Neural Networks for Semantic Segmentation

Now only support Python3.x, pytorch 1.3.

pip3 install -r requirements.txt
cd lib/exts
sh make.sh

All the performances showed below fully reimplemented the papers' results.

• Cityscapes (Single Scale Whole Image Test): Base LR 0.01, Crop Size 769

• ADE20K (Single Scale Whole Image Test): Base LR 0.02, Crop Size 520

Take PSPNet as an example. ("tag" could be any string, include an empty one.)

• Training

cd scripts/cityscapes/
bash run_fs_pspnet_cityscapes_seg.sh train tag

• Resume Training

cd scripts/cityscapes/
bash run_fs_pspnet_cityscapes_seg.sh train tag

• Validate

cd scripts/cityscapes/
bash run_fs_pspnet_cityscapes_seg.sh val tag

• Testing:

cd scripts/cityscapes/
bash run_fs_pspnet_cityscapes_seg.sh test tag