This respository includes a PyTorch implementation of PGECNet.
python 3.6
PyTorch 0.4.1
InPlace-ABN have a native CUDA implementation, which must be compiled with the following commands:
cd modules
sh build.sh
python build.py
Note the CUDA kernels need to update accoding to your own gpu.
Plesae download LIP dataset
pretrained model(MM:ydtv)
imagenet pretrained resnett101(MM:ydtv)
bash job_evaluate_val.sh
bash job_train_ge_multi.sh
This project is created based on the CE2P.
If this code is helpful for your research, please cite the following paper:
@article{PGEC2019,
title={Human Parsing with Pyramidical Gather-Excite Context},
author={Sanyi Zhang, Guo-jun Qi, Xiaochun Cao, Zhanjie Song, Jie Zhou},
journal={IEEE Transactions on Circuits and Systems for Video Technology(TCSVT)},
year={2021},
volume={31},
number={3},
pages={1016-1030}
}