This repository contains Python implementation of the paper Making DensePose fast and light
[January 2022]Updated to latest Detectron2 and released the weights. Breaking: network quantization lost in this version, see issue.[June 2020]Initial code release
# Install Detectron2 and DensePose
git clone https://github.com/facebookresearch/detectron2.git && cd detectron2
git checkout bb96d0b01d0605761ca182d0e3fac6ead8d8df6e
pip install -e .
cd projects/DensePose
pip install -e .timm==0.4.12torch==1.10.1
# Train
python train_net.py --config-file configs/mobile_parsing_rcnn_b_s3x.yaml --num-gpus 8
# Test
python train_net.py --config-file configs/mobile_parsing_rcnn_b_s3x.yaml --eval-only MODEL.WEIGHTS model.pth
| Name | lr sched |
box AP |
segm AP |
dp. AP GPS |
dp. AP GPSm |
download |
|---|---|---|---|---|---|---|
| Mobile-Parsing-RCNN-B | s3x | 57.1 | 59.0 | 50.4 | 54.4 | model |
| Mobile-Parsing-RCNN-B-WC2M | s3x | 59.4 | 63.7 | 57.3 | 60.3 | model |
| Mobile-Parsing-RCNN-B-CSE | s3x | 60.2 | 64.3 | 59.0 | 61.2 | model |
WC2M corresponds to new training procedure and the model that performs estimation of confidence in regressed UV
coordinates as well as confidences associated with coarse and fine segmentation;
see Sanakoyeu et al., 2020 for details.
CSE corresponds to a continuous surface embeddings model for humans;
see Neverova et al., 2020 for details.
Note: weights for Mobile-Parsing-RCNN-B (s3x) are not the same as presented in the paper but with a similar performance.
See DensePose (Getting Started)
If you find our work useful in your research, please consider citing:
@inproceedings{rakhimov2021making,
title={Making DensePose fast and light},
author={Rakhimov, Ruslan and Bogomolov, Emil and Notchenko, Alexandr and Mao, Fung and Artemov, Alexey and Zorin, Denis and Burnaev, Evgeny},
booktitle={Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision},
pages={1869--1877},
year={2021}
}See the LICENSE for more details.