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.
**Notice** There are several common situations in the reimplementation issues as below 1. Reimplement a model in the model zoo using the provided configs 2. Reimplement a model in the...
Hi. I'm trying to train ByteTrack to that track multi classes using a TAOdataset. **Describe the bug** When I run the . /tools/train.py script, I geu an error during evaluation...
OC-SORT is accepted to cvpr2023
How to perform sharding when the TAO dataset is too large?What datasets can I use to train a multi class tracker? Can only track pedestrians on the MOT dataset? How...
We saw that both mmdetection and mmcv are updated . Are you planning to update mmtracking also , if not can you share new installation code because it is showing...
**Describe the feature** Hi, when will mmtracking support mmcv==2.0.0 **Motivation** In order to use the latest MMRazor for model pruning, one has to use mmcv==2.0.0. But mmtracking does not support...
Thanks for the amazing mmtracking framework, however, I find some minor errors in the install instructions. In the instruction, the example of MOT demo is >python demo/demo_mot_vis.py \ > configs/mot/deepsort/deepsort_faster-rcnn-r50-fpn_8xb2-4e_mot17halftrain_test-mot17halfval.py...
I have built image with docker, installed requirements with pip, tried to run SOT demo: ``` # python demo/demo_sot.py configs/sot/siamese_rpn/siamese_rpn_r50_1x_lasot.py --input demo/demo.mp4 --device cpu --output output.mp4 No CUDA runtime is...
Hello, I have installed the dev-1.x branch so I can use the StrongSort tracker. Unfortunately, however, when I call demo_mot_vis.py, I get an error that Transformer cannot be imported. What...
Do you support for conversion to onnx? Do you have a script to do it? What are the steps we need to convert MOT model to onnx? Thank you in...