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

can retrain? #58

Closed
gongyue666 opened this issue Aug 14, 2018 · 5 comments
Closed

can retrain? #58

gongyue666 opened this issue Aug 14, 2018 · 5 comments

Comments

@gongyue666
Copy link

Can the detector be retrained by my own dataset?
By the way there are too many nodes and .launch files, do they all needed?Seem too large for me

@tlind
Copy link
Member

tlind commented Oct 8, 2018

Which detector?
The launch files and nodes are provided for maximum flexibility and deployment of different kinds of robots. This is a relatively generic framework for person tracking from (mobile) robots, not an application tailored to a specific robot.

@CodeToPoem
Copy link

Hello,
I have a problem with the 'groups_probabilistic_small.model' in 'spencer_social_relations'. Can I see the origin datasets that used to retrain svm model?

@tlind
Copy link
Member

tlind commented Feb 24, 2019

I think I might still have an annotated CARMEN logfile of the groundtruth tracks/groups. Give me some time to dig that out from an old computer. I cannot share the visual data (camera image stream) for privacy reasons.

@tlind tlind closed this as completed Feb 24, 2019
@tlind tlind reopened this Feb 24, 2019
@CodeToPoem
Copy link

Thanks a lot. @tlind

@tlind
Copy link
Member

tlind commented Mar 5, 2019

I am responding to the SVM-related questions in #63.
Closing this issue because original author did not reply any further.

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