mmtracking
mmtracking copied to clipboard
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.
Hi, I'm trying to use MMTrack on a custom dataset organized as COCOVideo Dataset as shown in the documentation. But when running the tools/test.py script I get an error because...
Thanks for your error report and we appreciate it a lot. **Checklist** 1. I have searched related issues but cannot get the expected help. 2. The bug has not been...
Hello everyone, I have a model which was trained by mmdetection for detecting Ship. Now i want to use that model for tracking ship in mmtracking. So, is there any...
Thanks for your error report and we appreciate it a lot. **Checklist** 1. I have searched related issues but cannot get the expected help. 2. The bug has not been...
May I know how to modify the __init__.py file to solve the compatibility issue? (mmtracking) C:\Users\guangwei\mmtracking>python demo/demo_mot_vis.py configs/mot/deepsort/sort_faster-rcnn_fpn_4e_mot17-private.py --input demo/demo.mp4 --output mot.mp4 Traceback (most recent call last): File "demo/demo_mot_vis.py", line...
Dear author: I noticed that the bytetrack in mmtracking return the yolox detected bboxes, while the original bytetrack in [https://github.com/ifzhang/ByteTrack](url) return the kalman filter predicted bboxes, so does this distinction...
Below is my tracker config I try to modify for Yolo _base_ = [ '../../_base_/models/yolo_8x8.py', '../../_base_/datasets/mot_challenge.py', '../../_base_/default_runtime.py' ] #img_scale = (800, 1440) img_scale = (416, 416) samples_per_gpu = 4 model...
Hi! I am trying to download the detector weights for MOT17 and MOT20 by using the link in /configs/mot/strongsort/README.md. However, the links for the detection, reid and AFlink weights do...