search

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
338 stars 34 forks source link

Inference Statistics #2

Closed vjsrinivas closed 3 years ago

vjsrinivas commented 3 years ago

Hello,

I know this project was just released and some things are still being put up, but do you have any information on the inference speeds for UniTrack with ResNet18 and ResNet50 base appearance models?

Zhongdao commented 3 years ago

Hi @vjsrinivas, Here're my results on the inference speed, all run on a single NVIDIA Titan Xp GPU. With ResNet18 as the appearance model, UniTrack runs at ~35 FPS for SOT, ~2 FPS for VOS, and ~10 FPS for MOT/MOTS/PoseTrack. With ResNet50 as the appearance model, UniTrack runs at ~15 FPS for SOT, ~1.5 FPS for VOS, and ~3 FPS for MOT/MOTS/PoseTrack.

vjsrinivas commented 3 years ago

Thank you!