centerpose
centerpose copied to clipboard
Push the Extreme of the pose estimation
The repo is based on CenterNet, which aimed for push the boundary of human pose estimation
multi person pose estimation using center point detection:
Main results
Keypoint detection on COCO validation 2017
Backbone | AP | FPS | TensorRT Speed | GFLOPs | Download |
---|---|---|---|---|---|
DLA-34 | 62.7 | 23 | - | - | model |
Resnet-50 | 54.5 | 28 | 33 | - | model |
MobilenetV3 | 46.0 | 30 | - | - | model |
ShuffleNetV2 | 43.9 | 25 | - | - | model |
HRNet_W32 | 63.8 | 16 | - | - | model |
HardNet | 46.0 | 30 | - | - | model |
Darknet53 | 34.2 | 30 | - | - | model |
EfficientDet | 38.2 | 30 | - | - | model |
Installation
git submodule init&git submodule update Please refer to INSTALL.md for installation instructions.
Use CenterNet
We support demo for image/ image folder, video, and webcam.
First, download the model DLA-34 from the Model zoo and put them in anywhere.
Run:
cd tools; python demo.py --cfg ../experiments/dla_34_512x512.yaml --TESTMODEL /your/model/path/dla34_best.pth --DEMOFILE ../images/33823288584_1d21cf0a26_k.jpg --DEBUG 1
The result for the example images should look like:
Evaluation
cd tools; python evaluate.py --cfg ../experiments/dla_34_512x512.yaml --TESTMODEL /your/model/path/dla34_best.pth --DEMOFILE --DEBUG 0
Training
After installation, follow the instructions in DATA.md to setup the datasets.
We provide config files for all the experiments in the experiments folder.
cd ./tools python -m torch.distributed.launch --nproc_per_node 4 train.py --cfg ../experiments/*yalm
Demo
the demo files located in the demo
directory, which is would be a very robust human detection+tracking+face reid system.
License
MIT License (refer to the LICENSE file for details).
Citation
If you find this project useful for your research, please use the following BibTeX entry.
@inproceedings{zhou2019objects,
title={Objects as Points},
author={Zhou, Xingyi and Wang, Dequan and Kr{\"a}henb{\"u}hl, Philipp},
booktitle={arXiv preprint arXiv:1904.07850},
year={2019}
}