search

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
3.52k stars 591 forks source link

how to output prediction bbox #477

Open StarBlue98 opened 2 years ago

StarBlue98 commented 2 years ago

I use my own dataset to train configs/vid/temporal_roi_align/selsa_troialign_faster_rcnn_r101_dc5_7e_imagenetvid.py After training , I want to output the prediction bbox. I am confused about how to read the results.pkl correctly and how to convert it to json. Also, what is the meaning of each array in pkl file? how to know this array is related to what image? Could you please give me some advice?

JingweiZhang12 commented 2 years ago

The results.pkl store the detection results in the dict format. About its content , you can refer to here You can use cPickle to load the '*.pkl' file.

kuangxiaoye commented 2 years ago

The results.pkl store the detection results in the dict format. About its content , you can refer to here You can use cPickle to load the '*.pkl' file.

How to export a .pkl for match mmaction2 annotation/.pkl ？