README.md

SegFormer: Simple and Efficient Design for Semantic Segmentation with Transformers

Figure 1: Performance of SegFormer-B0 to SegFormer-B5.

Project page | Paper | Demo (Youtube) | Demo (Bilibili) | Intro Video

SegFormer: Simple and Efficient Design for Semantic Segmentation with Transformers.
Enze Xie, Wenhai Wang, Zhiding Yu, Anima Anandkumar, Jose M. Alvarez, and Ping Luo.
NeurIPS 2021.

This repository contains the official Pytorch implementation of training & evaluation code and the pretrained models for SegFormer.

SegFormer is a simple, efficient and powerful semantic segmentation method, as shown in Figure 1.

We use MMSegmentation v0.13.0 as the codebase.

🔥🔥 SegFormer is on MMSegmentation. 🔥🔥

Installation

For install and data preparation, please refer to the guidelines in MMSegmentation v0.13.0.

Other requirements: pip install timm==0.3.2

An example (works for me): CUDA 10.1 and pytorch 1.7.1

pip install torchvision==0.8.2
pip install timm==0.3.2
pip install mmcv-full==1.2.7
pip install opencv-python==4.5.1.48
cd SegFormer && pip install -e . --user

Evaluation

Download trained weights. ( google drive | onedrive )

Example: evaluate SegFormer-B1 on ADE20K:

# Single-gpu testing
python tools/test.py local_configs/segformer/B1/segformer.b1.512x512.ade.160k.py /path/to/checkpoint_file

# Multi-gpu testing
./tools/dist_test.sh local_configs/segformer/B1/segformer.b1.512x512.ade.160k.py /path/to/checkpoint_file <GPU_NUM>

# Multi-gpu, multi-scale testing
tools/dist_test.sh local_configs/segformer/B1/segformer.b1.512x512.ade.160k.py /path/to/checkpoint_file <GPU_NUM> --aug-test

Training

Download weights ( google drive | onedrive ) pretrained on ImageNet-1K, and put them in a folder pretrained/.

Example: train SegFormer-B1 on ADE20K:

# Single-gpu training
python tools/train.py local_configs/segformer/B1/segformer.b1.512x512.ade.160k.py 

# Multi-gpu training
./tools/dist_train.sh local_configs/segformer/B1/segformer.b1.512x512.ade.160k.py <GPU_NUM>

Visualize

Here is a demo script to test a single image. More details refer to MMSegmentation's Doc.

python demo/image_demo.py ${IMAGE_FILE} ${CONFIG_FILE} ${CHECKPOINT_FILE} [--device ${DEVICE_NAME}] [--palette-thr ${PALETTE}]

Example: visualize SegFormer-B1 on CityScapes:

python demo/image_demo.py demo/demo.png local_configs/segformer/B1/segformer.b1.512x512.ade.160k.py \
/path/to/checkpoint_file --device cuda:0 --palette cityscapes

License

Please check the LICENSE file. SegFormer may be used non-commercially, meaning for research or evaluation purposes only. For business inquiries, please visit our website and submit the form: NVIDIA Research Licensing.

Citation

@inproceedings{xie2021segformer,
  title={SegFormer: Simple and Efficient Design for Semantic Segmentation with Transformers},
  author={Xie, Enze and Wang, Wenhai and Yu, Zhiding and Anandkumar, Anima and Alvarez, Jose M and Luo, Ping},
  booktitle={Neural Information Processing Systems (NeurIPS)},
  year={2021}
}