Jinkun Cao
Jinkun Cao
@yangyichun1997 I still haven't fixed that. Waiting for some solution provided by the author or someone else.
@XindiWu Thanks Xindi! Will try that solution.
Yes. I also encountered the same problem when trying to train on Carla data... And as I'm not familiar with the codebase style you are publishing in, it's hard for...
This is possible if you read an empty file or in a wrong path name. I tried the code on my side, it looks right. Have you fixed this issue?
Thanks so much @jpoberhauser for the awesome contribution. Now, we could also use OC-SORT with customized detector by the implementation of [mmtracking](https://github.com/noahcao/mmtracking.git).
We don't estimate new boxes confidence in the stage of tracking. A common practice is to get the scores from detector, such as YOLOX we use.
Hi, Please check the code at: tools/interpolation.py and tools/gp_interpolation.py
Hi @AbinayaKumar25, I had some discussion about experiment observation in a previous [issue](https://github.com/noahcao/OC_SORT/issues/12). You can probably get some insight and a deeper explanation there. For your question: 1. OOS also...
Yes. Actually we find similar results. OC-SORT is provided as a new baseline for more advanced study. You can feel free to improve it by integrating new components. Combining OC-SORT...
Hi @HanGuangXin , You have done really a wonderful study! It is quite impressive to me. I have some experience and thoughts from the observations you provide. 1. **Why OC-SORT...