Code Monkey home page Code Monkey logo

Comments (1)

alsuhr-c avatar alsuhr-c commented on July 24, 2024

I believe that we did the second thing: concatenate the one-hot representations of the objects, then put through some fully connected layers with biases (code: https://github.com/alsuhr-c/nlvr-baselines/blob/master/img_ft_rnn.py#L150). Also, note that we padded the boxes with zero-vectors for objects the box did not have (up to 8 objects). It would be a good idea to embed each item individually, which we did not report results on.

We did try a model where we embedded objects independently with the same embedding matrix, and averaged them, then averaged the embeddings of each box (I'm not sure on the details of this model). This was done to model the order independence of the objects and of the boxes. The performance for this model was roughly the same as the image features + RNN model that we reported, but I don't have exact numbers at the moment.

from nlvr.

Related Issues (9)

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.