ErlingLie
ErlingLie
Did you find any solution to this? I also try to train with a custom dataset. I tried both with CFG.use_darknet_cfg = True and False. No matter what I do...
I just abandoned this repo all together and used the original darknet yolov4 instead. Got it to work much quicker and better.
You should re initialize the static counter in the KalmanBoxTracker class. Although you reinitialize the sort object, the counter remains unchanged.
@Mechazo11 You need to reset the count on [this line](https://github.com/abewley/sort/blob/bce9f0d1fc8fb5f45bf7084130248561a3d42f31/sort.py#L98) If you for instance initialize multiple trackers in a for-loop, it can be done like this: ``` for i in...
@jingtongli I would modify the KalmanBoxTracker in the Sort code to take in id as argument instead of using a static variable. For this to work I made some small...
@jingtongli Glad to help!
Hey, I think making the changes as I outlined in my long code snippet above will fix this issue. As to why some numbers are skipped I believe this is...
Hm, then I am not sure if I understand your problem correctly. The general issue is that the tracker keeps one static ID-counter for all SORT objects created during the...
When I scrape each person separately I get a result like your image over there with all fields as empty lists. Any ideas how to fix this?
Did you find any solution to this?