hongsukchoi / 3DCrowdNet_RELEASE

Official Pytorch implementation of "Learning to Estimate Robust 3D Human Mesh from In-the-Wild Crowded Scenes", CVPR 2022
MIT License
155 stars 15 forks source link

How can i have my own 2d_pose_results.json, for my own images ? #30

Open mlandi96 opened 1 year ago

mlandi96 commented 1 year ago

hi every one

I want to run the demo.py on my own images and I don't know how to get the appropriate json file

thanks

hongsukchoi commented 1 year ago

Please check the format of 2d_pose_result.json in our demo data. The data is generated by https://github.com/HRNet/HigherHRNet-Human-Pose-Estimation