Giter Site home page Giter Site logo

ppengtang / dpl Goto Github PK

View Code? Open in Web Editor NEW
32.0 3.0 11.0 1.31 MB

Codes for our paper "Deep Patch Learning for Weakly Supervised Object Classification and Discovery".

License: MIT License

MATLAB 7.19% Shell 2.29% Makefile 0.08% Python 90.44%
computer-vision weakly-supervised-learning object-classification object-detection

dpl's People

Contributors

ppengtang avatar

Stargazers

avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar

Watchers

avatar avatar avatar

Forkers

yuancoder222 haopo2005 lihua213 giserh rongchangzhao hustvl aisi746467512 weak-supervision gcv9htd cynthiacoding sunidhisachan

dpl's Issues

How to deal with the data alignment between annotation and predictions

Hi,
I'm new of caffe. And I think data annotation is very common among all the detection training applications.
I'd like to know how to deal with the data alignment between annotation and predictions during forward computation in the loss function such as smoothL1LossLayer function?
Concretely, suppose there are n*n output cells and each cell can predict m bboxs from pervious conv layer, then if there are p annotations per image.
How to make the annotataion dimensions map the predictions?

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.