Running the code without YOLOv3 and SORT

fabro66 / GAST-Net-3DPoseEstimation

A Graph Attention Spatio-temporal Convolutional Networks for 3D Human Pose Estimation in Video (GAST-Net)

MIT License

312 stars 70 forks source link

Running the code without YOLOv3 and SORT #22

Closed yerzhan7orazayev closed 3 years ago

yerzhan7orazayev commented 3 years ago

Dear @fabro66,

Is it possible to run the without YOLOv3 and SORT? If so, how one can modify the code?

Thanks.

fabro66 commented 3 years ago

Hi~ If there is only one person in the video, the YOLOv3 and SORT can be removed. But it will affect the accuracy of 2D poses because HRNet is a top-down method.