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 want to work on VisDrone dataset. Is there any code for converting VisDrone dataset (DET and VID version) to coco dataset format?
 使用官方训练的yolox-ByteTrack直接也测demo.MP4视频结果明显不对,我没有改动任何配置文件,不知道怎么回事,请帮忙看下。 另外,有一处貌似有bug: mmdet 3.0.0rc0的/usr/local/lib/python3.7/dist-packages/mmdet/models/dense_heads/base_dense_head.py第196行,rescale默认为true,但是/usr/local/lib/python3.7/dist-packages/mmdet/models/dense_heads/yolox_head.py的354行默认为false,导致程序运行终止,请帮忙排查。
Hello, I am currently attempting to integrate mmrotate into mmtracking as a detector, but I am facing some challenges. I am seeking advice or guidance on how to successfully achieve...
/home/nhl510wm/xxy/code/mmtracking/mmtrack/core/utils/misc.py:24: UserWarning: Setting OMP_NUM_THREADS environment variable for each process to be 1 in default, to avoid your system being overloaded, please further tune the variable for optimal performance in your...
An error occurred while running mmtracking on the Windows system, and the configuration file is using qdtrack_ Faster rcnn_ R101_ Fpn_ 24e_ Lvis.py, training was conducted on the lvis dataset,...
/opt/conda/lib/python3.7/site-packages/mmcv/__init__.py:21: UserWarning: On January 1, 2023, MMCV will release v2.0.0, in which it will remove components related to the training process and add a data transformation module. In addition, it...
Hi, I am working on mmtracking 1.x and trying to train a Reid model. I found that the batch size only can be set as 1 in version 1.x. In...
Add OpenXLab Badge to share official applications, community applications and ecological applications based on MMTracking in the OpenXLab platform.
When I used tools/train.py to train deepsort, the following error occurred: NotImplementedError: Please train 'detector' and 'reid' models first, then reference with SORT/DeepSORT. I have trained the checkpoint for the...