open-mmlab / mmtracking

OpenMMLab Video Perception Toolbox. It supports Video Object Detection (VID), Multiple Object Tracking (MOT), Single Object Tracking (SOT), Video Instance Segmentation (VIS) with a unified framework.
https://mmtracking.readthedocs.io/en/latest/
Apache License 2.0
3.55k stars 598 forks source link

MOT test result #875

Open SoftSisterRui opened 1 year ago

SoftSisterRui commented 1 year ago

Hi, I have used bytetrack to train a multi-target tracking model. However, when testing, the generated .pkl file only has 6 entries for "track_bboxes", how can I get the frame ID, track ID, top left coordinate of the bounding box, top y coordinate, width, height. confidence score for the detection?

luke110 commented 8 months ago

Hello, for this pkl file, how did you convert the 6 entries of "track_bboxes". I don’t know how to operate the pkl file obtained by this test. Can you give me some suggestions?

Y0unger commented 6 days ago

Hello, I also have this problem, may I ask you how to solve this pkl file?