Realtime_Multi-Person_Pose_Estimation icon indicating copy to clipboard operation
Realtime_Multi-Person_Pose_Estimation copied to clipboard

Code repo for realtime multi-person pose estimation in CVPR'17 (Oral)

Results 102 Realtime_Multi-Person_Pose_Estimation issues
Sort by recently updated
recently updated
newest added

Thank you for your amazing job! I compiled your modified caffe frame and use miniconda3 python to run setLayers.py. A KeyError got: Traceback (most recent call last): File "/home/moon/project/reference/paf/Realtime_Multi-Person_Pose_Estimation/training/setLayers.py", line...

What is the main idea of separating ppl on image to **main person** and **other persons**? I notices in all places inside the code handling of this is absolutely same....

@ZheC -could you please consider this question? I checked the code, and I could only see that both invisible, labelled( outside segment ) and visible labelled key points((isVisible = 0,1))...

what about the annotations and other implementations for MPI dataset? I cannot see any of them.. Is it true that only trained model of MPI is given? kindly clear my...

Dear Zhe Cao, I've succeeded to run, train and evaluate your model with 4 scales in Matlab (everything for research purposes). Now I'm moving to python, and I arranged the...

Thanks for your perfect projects! However,when I get the final mAP,it confused me about how the code work to compared my json result of the single person to the groundtrues...

Hi, I am a PhD student from UW working on a research project in computer vision. I successfully trained several models in COCO with less stages. However, when I tried...

someone can put the caffe-python-evalution code? Thanks. I'm confused that I can't get the mAP as high as the author

Is there any problems that the persons skipped are not be mask out?