Parsing-R-CNN

PWC

PWC

PWC

(New!) Official implementation of Parsing R-CNN for Instance-Level Human Analysis (CVPR 2019)

Citing Parsing R-CNN

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

@inproceedings{yang2019cvpr,
  title = {Parsing R-CNN for Instance-Level Human Analysis},
  author = {Lu Yang and Qing Song and Zhihui Wang and Ming Jiang},
  booktitle = {Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2019}
}

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

Installation

Install Parsing R-CNN following INSTALL.md.

Dataset

You need to download the datasets and annotations following this repo's formate. As:

And following data structure to train or evaluate Parsing R-CNN models.

Results and Models

On CIHP val

Backbone LR Det AP mIoU Parsing (APp50/APvol/PCP50) DOWNLOAD
R-50-FPN 1x 65.8 52.8 57.2/51.2/55.4
R-50-FPN 3x 68.7 56.0 64.1/54.1/60.7 GoogleDrive

On MHP-v2 val

Backbone LR Det AP mIoU Parsing (APp50/APvol/PCP50) DOWNLOAD
R-50-FPN 1x 66.5 34.0 19.9/36.7/32.4
R-50-FPN 3x 69.0 36.1 27.4/40.5/38.3 GoogleDrive

On DensePose_COCO val

Backbone LR Det AP UV AP (AP/AP50/AP75/APm/APl) DOWNLOAD
R-50-FPN s1x 57.4 59.3/90.5/68.7/56.2/60.8 GoogleDrive

ImageNet pretrained weight

Visualization

coming soon.

Training

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

Evaluation

multi-gpu evaluation,

python tools/test_net.py --cfg ckpts/CIHP/e2e_rp_rcnn_R-50-FPN_3x_ms/e2e_rp_rcnn_R-50-FPN_3x_ms.yaml --gpu_id 0,1,2,3,4,5,6,7

single-gpu evaluation,

python tools/test_net.py --cfg ckpts/CIHP/e2e_rp_rcnn_R-50-FPN_3x_ms/e2e_rp_rcnn_R-50-FPN_3x_ms.yaml --gpu_id 0

License

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