Official implementation of Renovating Parsing R-CNN for Accurate Multiple Human Parsing (ECCV2020)

In this repository, we release the RP R-CNN code in Pytorch.

• RP R-CNN architecture:

• RP R-CNN output:

If you use RP R-CNN, please use the following BibTeX entry.

@inproceedings{yang2020eccv,
  title = {Renovating Parsing R-CNN for Accurate Multiple Human Parsing},
  author = {Lu Yang and Qing Song and Zhihui Wang and Mengjie Hu and Chun Liu and Xueshi Xin and Wenhe Jia and Songcen Xu},
  booktitle = {Proceedings of European Conference on Computer Vision (ECCV)},
  year = {2020}
}

• 8 x TITAN RTX GPU
• pytorch1.4
• python3.6.8

Install RP R-CNN following INSTALL.md.

On CIHP

On MHP-v2

• 'baseline' denotes our implementation Parsing R-CNN.
• '+tta' denotes using test-time augmentation, including: soft-nms + bbox voting + h-flipping + multi-scale

ImageNet pretrained weight

• R-50
• X-101-32x8d

To train a model with 8 GPUs run:

python -m torch.distributed.launch --nproc_per_node=8 tools/train_net.py --cfg cfgs/CIHP/e2e_rp_rcnn_R-50-FPN_3x_ms.yaml

python tools/test_net.py --cfg ckpts/CIHP/e2e_rp_rcnn_R-50-FPN_6x_ms/e2e_rp_rcnn_R-50-FPN_6x_ms.yaml --gpu_id 0,1,2,3,4,5,6,7

python tools/test_net.py --cfg ckpts/CIHP/e2e_rp_rcnn_R-50-FPN_6x_ms/e2e_rp_rcnn_R-50-FPN_6x_ms.yaml --gpu_id 0

RP-R-CNN is released under the MIT license.