conda install pytorch==1.5.1 torchvision==0.6.1 cudatoolkit=10.2 -c pytorch

pip install -r requirements.txt

path/to/ADEChallengeData2016/
  images/
    training/
    validation/
  annotations/ 
    training/
    validation/
  dt_offset/
    training/
    validation/

path/to/PASCAL-Context/
  train/
    image/
    label/
    dt_offset/
  val/
    image/
    label/
    dt_offset/

python -m torch.distributed.launch --nproc_per_node=8 \ # specify gpu number
--master_port=29500  \
train.py  --launcher pytorch \
--config /path/to/config_file 

# single-gpu testing
python test.py --checkpoint /path/to/checkpoint \
--config /path/to/config_file \
--eval mIoU \
[--out ${RESULT_FILE}] [--show] \
--aug-test \ # for multi-scale flip aug

# multi-gpu testing (4 gpus, 1 sample per gpu)
python -m torch.distributed.launch --nproc_per_node=4 --master_port=29500 \
test.py  --launcher pytorch --eval mIoU \
--config_file /path/to/config_file \
--checkpoint /path/to/checkpoint \
--aug-test \ # for multi-scale flip aug

@article{zhu2021unified,
  title={A Unified Efficient Pyramid Transformer for Semantic Segmentation},
  author={Zhu, Fangrui and Zhu, Yi and Zhang, Li and Wu, Chongruo and Fu, Yanwei and Li, Mu},
  journal={arXiv preprint arXiv:2107.14209},
  year={2021}
}