search

leonid-pishchulin / poseval

Evaluation of multi-person pose estimation and tracking
Other
210 stars 49 forks source link

evaluation error #8

Closed DongJT1996 closed 6 years ago

DongJT1996 commented 6 years ago

Hi, I just want to try the function evaluation.py to get the result. So i use the the annotations of train and val set, e.g. 000001_bonn_relpath_5sec_trainsub.mat to get the json file using mat2json.m function. Then I use the json file as prediction and groundtruth, and use the following command to test:

python evaluate.py --groundTruth=/mnt/data/dataset/posetrack/posetrack_data/annotations/myval/ --predictions=/mnt/data/dataset/posetrack/posetrack_data/annotations/predictions/ --evalPoseEstimation

however, there is an error as following: image Do you have any ideas? thank you!

leonid-pishchulin commented 6 years ago

please try to pull from the mainline and see if error got fixed. I pushed an update yesterday that might have fixed your issue as well.

ktr-hubrt commented 6 years ago

this error still exists，which comes from data preparation (for every point required json does not score 1 ,however when testing ,the code require every point's score

leonid-pishchulin commented 6 years ago

evaluation of per-frame multi-person pose estimation requires detection score. I update the readme.