microchila

算法中 r_tracked_stracks 这个变量少了lost部分的u_track的轨迹，导致未匹配上的丢失轨迹直接删掉： ` r_tracked_stracks = [strack_pool[i] for i in u_track if strack_pool[i].state == TrackState.Tracked]`，所以每一次更新导致之前丢失的轨迹要么跟新的框匹配要么直接删除掉

MOT20

3

### Search before asking - [X] I have searched the Yolo Tracking [issues](https://github.com/mikel-brostrom/yolo_tracking/issues) and found no similar bug report. ### Question Can I ask if evaluating MOT20 only requires changing...

what is α？

1

### Search before asking - [X] I have searched the Yolo Tracking [issues](https://github.com/mikel-brostrom/yolo_tracking/issues) and found no similar bug report. ### Question What is the meaning of the abscissa α of...

new YOLO

2

### Search before asking - [X] I have searched the Yolov8 Tracking [issues](https://github.com/mikel-brostrom/yolo_tracking/issues) and found no similar enhancement requests. ### Description Will it be compatible with newer versions of the...

more reid

4

### Search before asking - [X] I have searched the Yolo Tracking [issues](https://github.com/mikel-brostrom/yolo_tracking/issues) and found no similar bug report. ### Question Is it possible to use some other reid model?...

[Task]: How to perform data enhancement in custom datasets

2

### What is the motivation for this task? data enhancement in custom datasets ### Describe the solution you'd like Some effective data enhancement methods such as UDA can be performed...

MOTA IS 50.1%

1

将MOT17的训练视频验证一边精度才50.1% 怎么回事

Shouldn't the cost matrix for making allocations be non-negative, and why is there a negative sign in front of the IOU in the code?