PyTorch implementation of Generating Person Images with Appearance-aware Pose Stylizer (IJCAI 2020)
PyTorch implementation of "Generating Person Images with Appearance-aware Pose Stylizer" [IJCAI 2020].
@inproceedings{huang2020generating,
title={Generating Person Images with Appearance-aware Pose Stylizer},
author={Huang, Siyu and Xiong, Haoyi and Cheng, Zhi-Qi and Wang, Qingzhong
and Zhou, Xingran and Wen, Bihan and Huan, Jun and Dou, Dejing},
booktitle={IJCAI},
year={2020}
}
git clone https://github.com/siyuhuang/PoseStylizer.git
cd PoseStylizer
dataset/market_data.zip
and the DeepFashion dataset dataset/fashion_data.zip
from Google Drive / Baidu Disk (Password: jl0s). The zip files include images /train
/test
, keypoint annotations annotation.csv
, and pose transfer pairs pairs.csv
.cd dataset
unzip market_data.zip
unzip fashion_data.zip
cd ..
python tool/generate_pose_map_market.py
python tool/generate_pose_map_fashion.py
Download our pretrained checkpoints from Google Drive / Baidu Disk (Password: jl0s).
bash test_market.sh
bash test_fashion.sh
bash train_market.sh
bash train_fashion.sh
Note: We use 8 GPUs for training by default. If you have less GPUs, change --gpu_ids
and --batchSize
accordingly. The results are competitive to the results in our paper.
Tensorflow 1.14.1 (Python3) is required.
Market-1501
python tool/getMetrics_market.py
python tool/getMetrics_fashion.py
pose_estimator.h5
under the root folder PoseStylizer
./results
folder.
python tool/crop_market.py
or
python tool/crop_fashion.py
input_folder
and output_path
in tool/compute_coordinates.py
.python2 tool/compute_coordinates.py
python tool/calPCKH_market.py
or
python tool/calPCKH_fashion.py
The code is written based on nice frameworks pytorch-CycleGAN-and-pix2pix and Pose-Transfer. The code is written by Dr. Siyu Huang.