GithubHelp home page GithubHelp logo

Comments (7)

aguscas avatar aguscas commented on May 27, 2024 1

I think everything else is exactly the same

from norfair.

joaqo avatar joaqo commented on May 27, 2024

Thanks! @aguscas you may have some insight on this.

from norfair.

aguscas avatar aguscas commented on May 27, 2024

Hello there! We are not using the confidence score of the detections during the evaluations. If you set that score to be anything greater or equal to -1, the evaluation will return the same results. If you set it to something less than -1, that specific prediction will be ignored during the evaluation. What I mean is that, it doesn't really matter to which number you set that confidence value, as long as it is greater or equal to -1

from norfair.

fcakyon avatar fcakyon commented on May 27, 2024

@aguscas thanks for your response!

In this comment you mentioned that when score is 0, that detection will be ignored during evaluation: #42 (comment).

That got me a bit confused. Are detections with score of 0 ignored or only detections with -1 are being ignored?

from norfair.

aguscas avatar aguscas commented on May 27, 2024

If you set to 0 the confidence in your ground truth files, then that object will be ignored. So there are 2 confidence values, one thing is the confidence value in your trackers (which we set to -1), and another thing is the confidence value in the ground truth labels (which is set to 1 when you want to take that object into account in the evaluation, or 0 otherwise).

from norfair.

fcakyon avatar fcakyon commented on May 27, 2024

@aguscas thanks a lot, that clears all things up!

One last question. Are there any more differences between tracker output and ground truth or is this all i need to know while arranging ground truths and tracker outputs?

from norfair.

dekked avatar dekked commented on May 27, 2024

Thanks @aguscas for the help, we definitely need to do a better job at documenting some parts of this :)

from norfair.

Related Issues (20)

Recommend Projects

  • React photo React

    A declarative, efficient, and flexible JavaScript library for building user interfaces.

  • Vue.js photo Vue.js

    🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.

  • Typescript photo Typescript

    TypeScript is a superset of JavaScript that compiles to clean JavaScript output.

  • TensorFlow photo TensorFlow

    An Open Source Machine Learning Framework for Everyone

  • Django photo Django

    The Web framework for perfectionists with deadlines.

  • D3 photo D3

    Bring data to life with SVG, Canvas and HTML. 📊📈🎉

Recommend Topics

  • javascript

    JavaScript (JS) is a lightweight interpreted programming language with first-class functions.

  • web

    Some thing interesting about web. New door for the world.

  • server

    A server is a program made to process requests and deliver data to clients.

  • Machine learning

    Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.

  • Game

    Some thing interesting about game, make everyone happy.

Recommend Org

  • Facebook photo Facebook

    We are working to build community through open source technology. NB: members must have two-factor auth.

  • Microsoft photo Microsoft

    Open source projects and samples from Microsoft.

  • Google photo Google

    Google ❤️ Open Source for everyone.

  • D3 photo D3

    Data-Driven Documents codes.