Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Excuse me, have you trained mars dataset by yourself? #2

Open
chrenlily opened this issue Jan 3, 2020 · 6 comments
Open

Excuse me, have you trained mars dataset by yourself? #2

chrenlily opened this issue Jan 3, 2020 · 6 comments

Comments

@chrenlily
Copy link

How do you train other types of Mars dataset?

@xiaoxiong74
Copy link
Owner

How do you train other types of Mars dataset?

I didn't train other types of Mars dataset, I just reused the original deep_sort model(just trained for person)

@chrenlily
Copy link
Author

So you don't have the deep appearance descriptor of bicycle?

@xiaoxiong74
Copy link
Owner

So you don't have the deep appearance descriptor of bicycle?

@chrenlily yes, when tracking other objects, kalman filtering is considered more in deep_sort model.

@chrenlily
Copy link
Author

ok! When you track a bicycle, just think about detection and kalman filtering.

@chrenlily
Copy link
Author

can I ask your another question? Why is the total number of bicycles and pedestrians less than the number on the box?

@zzc-ai
Copy link

zzc-ai commented Jan 5, 2021

您如何训练其他类型的火星数据集?

我没有训练其他类型的火星数据集,我只是重用了原始的deep_sort模型(仅针对人员进行训练)

您的代码是什么环境运行的呢,我是win一直报错,如果看到的话希望得到您的指导

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

No branches or pull requests

3 participants