Git Product home page Git Product logo

Comments (2)

bowenc0221 avatar bowenc0221 commented on July 19, 2024

Thank you for your interest in our work. Evaluating box AP is already supported in this code, please follow my comment to generate boxes from masks:

result.pred_boxes = Boxes(torch.zeros(mask_pred.size(0), 4))
# Uncomment the following to get boxes from masks (this is slow)
# result.pred_boxes = BitMasks(mask_pred > 0).get_bounding_boxes()

Unfortunately, the box AP is worse than Mask R-CNN, because the generated boxes are very sensitive to outliers: imaging the model predicts a single pixel that is very far from the mask, it won't affect mask AP much but it is catastrophic to box AP.

from mask2former.

VGrondin avatar VGrondin commented on July 19, 2024

Got it, thanks for the information.

from mask2former.

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.