Coder Social home page Coder Social logo

Comments (3)

AlexMa011 avatar AlexMa011 commented on August 16, 2024 1

Glad you get decent results. I did compare the results given the bounding box of the object on 500 validation images. The results are better than 2017 polygon-rnn, but worse than 2018 poygon-rnn++.

from pytorch-polygon-rnn.

AlexMa011 avatar AlexMa011 commented on August 16, 2024

How about the result on training set? Like, the accuracy? The training dataset of small cropped images contains about 48k images. In my experience, the training loss can be down to nearly zero.

from pytorch-polygon-rnn.

makman7 avatar makman7 commented on August 16, 2024

Accuracy is 0.05 and loss 5.8 at step 5.44k.
I checked the performance on different epochs now it has decent results :) but still. Did you compared the repo stats with paper?

from pytorch-polygon-rnn.

Related Issues (13)

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.