Talking about Personal Stuffs:
- 🔭 I'm a graduate student
- 🌱 I’m currently learning C++
- 😄 Fun fact: I love photography and hiking
Other Projects:
Languages and Tools:
Cascade-RCNN+DeepSort MOTDT Trackor++
Talking about Personal Stuffs:
Other Projects:
Languages and Tools:
Can you provide the end to end model performance such as FPS?
Hi, I read FairMOT tracker codes, it's more like deepsort rather than MOTDT you mentioned in readme.
对于跟踪模块,目前来说还有更好的解决方案,比如使用MOTDT,此算法在DeepSort的基础上加入了轨迹评分的机制,目前像FairMOT、JDE使用的跟踪模块都是MOTDT,从精度和速度上此算法表现都是不错的。
Please correct me if I'm wrong. Thank you very much.
my_deep_sort_mgn.py这个文件中,第190行,如果检测模型没检测到目标框,即bbox_result为空,有没有可能出现这种情况,出现了咋整?
请问你这里把Trackor改为只用私有的检测,而不用公共的检测是吗?原来代码里的predict_boxes这个函数已经没有了好像,谢谢.
would you please suggested to fix this issue?
"deepsort = build_tracker('/root/PycharmProjects/mmdet/mgn_sort/deep/checkpoint/model.pt', use_cuda=True)"
the codes are in the my_deep_sort_mgn.py . i want to get the 'model.pt' to run the project.
安装环境的过程中发现以下问题:
ResolvePackageNotFound:
请问一下这套方案在MOT数据集,例如MOT15 MOT17 MOT20中的性能如何,是否获得了比FairMOT等one-stage的方法更好的性能,另外这套方案大概的计算时间(Hz)是多少?
非常感谢!
作者您好,在使用MGN提取行人特征时,我的场景下,提取的2048d的行人特征区分度很小,例如不同id,计算2048维的cosine距离差距只有0.01左右(范围0~1.0),虽然排序下来,同id会排在前面,但区分度很差。请问这样问题是否有解决方法。
P.S : 我的场景主要是跨镜匹配,并非用于mot,但使用了该项目同样的MGN特征提取网络
我想使用MOTDT代码,执行python eval_mot.py时候,提示这个错误,请问怎么解决
A declarative, efficient, and flexible JavaScript library for building user interfaces.
🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
An Open Source Machine Learning Framework for Everyone
The Web framework for perfectionists with deadlines.
A PHP framework for web artisans
Bring data to life with SVG, Canvas and HTML. 📊📈🎉
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
Some thing interesting about web. New door for the world.
A server is a program made to process requests and deliver data to clients.
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
Some thing interesting about visualization, use data art
Some thing interesting about game, make everyone happy.
We are working to build community through open source technology. NB: members must have two-factor auth.
Open source projects and samples from Microsoft.
Google ❤️ Open Source for everyone.
Alibaba Open Source for everyone
Data-Driven Documents codes.
China tencent open source team.