Zhongdao / UniTrack

[NeurIPS'21] Unified tracking framework with a single appearance model. It supports Single Object Tracking (SOT), Video Object Segmentation (VOS), Multi-Object Tracking (MOT), Multi-Object Tracking and Segmentation (MOTS), Pose Tracking, Video Instance Segmentation (VIS), and class-agnostic MOT (e.g. TAO dataset).
MIT License
334 stars 35 forks source link

Vehicles are not detected #28

Open v-diepttn147 opened 2 years ago

v-diepttn147 commented 2 years ago

Hi @Zhongdao, great work!

I ran mot_demo.py on some of my videos and there is a detecting problem, I used the default configs, newest code and here's the results I got:

00011 Pic 1: No vehicle is detected

00053 Pic 2: Not all vehicles are detected

00162 Pic 3: No vehicle is detected

Is it the detector's problem? Should I replace YOLOX with YOLOv5?

Update: I tried the YOLOX separately on the same data and it worked well, all vehicles are detected. Don't know where the problem came from.

00002

Update 2: I clone the newest version of YOLOX code into detector folder and replace the old one and it worked.