JegernOUTT / Swin-Transformer-Semantic-Segmentation

This is an official implementation for "Swin Transformer: Hierarchical Vision Transformer using Shifted Windows" on Semantic Segmentation.

Home Page:https://arxiv.org/abs/2103.14030

Geek Repo:Geek Repo

Github PK Tool:Github PK Tool

Swin Transformer for Semantic Segmentaion

This repo contains the supported code and configuration files to reproduce semantic segmentaion results of Swin Transformer. It is based on mmsegmentaion.

Updates

04/12/2021 Initial commits

Results and Models

ADE20K

Backbone Method Crop Size Lr Schd mIoU mIoU (ms+flip) #params FLOPs config log model
Swin-T UPerNet 512x512 160K 44.51 45.81 60M 945G config github/baidu github/baidu
Swin-S UperNet 512x512 160K 47.64 49.47 81M 1038G config github/baidu github/baidu
Swin-B UperNet 512x512 160K 48.13 49.72 121M 1188G config github/baidu github/baidu

Notes:

Usage

Installation

Please refer to get_started.md for installation and dataset preparation.

Inference

# single-gpu testing
python tools/test.py <CONFIG_FILE> <SEG_CHECKPOINT_FILE> --eval mIoU

# multi-gpu testing
tools/dist_test.sh <CONFIG_FILE> <SEG_CHECKPOINT_FILE> <GPU_NUM> --eval mIoU

# multi-gpu, multi-scale testing
tools/dist_test.sh <CONFIG_FILE> <SEG_CHECKPOINT_FILE> <GPU_NUM> --aug-test --eval mIoU

Training

To train with pre-trained models, run:

# single-gpu training
python tools/train.py <CONFIG_FILE> --options model.pretrained=<PRETRAIN_MODEL> [model.backbone.use_checkpoint=True] [other optional arguments]

# multi-gpu training
tools/dist_train.sh <CONFIG_FILE> <GPU_NUM> --options model.pretrained=<PRETRAIN_MODEL> [model.backbone.use_checkpoint=True] [other optional arguments] 

For example, to train an UPerNet model with a Swin-T backbone and 8 gpus, run:

tools/dist_train.sh configs/swin/upernet_swin_tiny_patch4_window7_512x512_160k_ade20k.py 8 --options model.pretrained=<PRETRAIN_MODEL> 

Notes:

  • use_checkpoint is used to save GPU memory. Please refer to this page for more details.
  • The default learning rate and training schedule is for 8 GPUs and 2 imgs/gpu.

Citing Swin Transformer

@article{liu2021Swin,
  title={Swin Transformer: Hierarchical Vision Transformer using Shifted Windows},
  author={Liu, Ze and Lin, Yutong and Cao, Yue and Hu, Han and Wei, Yixuan and Zhang, Zheng and Lin, Stephen and Guo, Baining},
  journal={arXiv preprint arXiv:2103.14030},
  year={2021}
}

Other Links

Image Classification: See Swin Transformer for Image Classification.

Object Detection: See Swin Transformer for Object Detection.

About

This is an official implementation for "Swin Transformer: Hierarchical Vision Transformer using Shifted Windows" on Semantic Segmentation.

https://arxiv.org/abs/2103.14030

License:Apache License 2.0


Languages

Language:Python 99.7%Language:Shell 0.2%Language:Dockerfile 0.1%