How is the weight of each key point calculated

leoxiaobin / deep-high-resolution-net.pytorch

The project is an official implementation of our CVPR2019 paper "Deep High-Resolution Representation Learning for Human Pose Estimation"

https://jingdongwang2017.github.io/Projects/HRNet/PoseEstimation.html

MIT License

4.31k stars 908 forks source link

How is the weight of each key point calculated #271

Open XiaopinWang opened 2 years ago

XiaopinWang commented 2 years ago

self.joints_weight = np.array( [ 1., 1., 1., 1., 1., 1., 1., 1.2, 1.2, 1.5, 1.5, 1., 1., 1.2, 1.2, 1.5, 1.5 ], dtype=np.float32 ).reshape((self.num_joints, 1)) Can you explain to me how the weights of each key point are calculated，thanks！

anas-zafar commented 1 year ago

@XiaopinWang were you able to understand it?