Coder Social home page Coder Social logo

ai4ce / disconet Goto Github PK

View Code? Open in Web Editor NEW
132.0 132.0 17.0 1.42 MB

[NeurIPS2021] Learning Distilled Collaboration Graph for Multi-Agent Perception

License: MIT License

3d-object-detection 3d-scene-understanding autonomous-driving collaborative-learning communication-networks computer-vision deep-learning graph graph-learning knowledge-distillation multi-agent-learning multi-agent-perception multi-agent-system point-cloud-processing v2v v2x-communication

disconet's People

Contributors

dekunma avatar roboticsyimingli 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  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  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  avatar  avatar  avatar  avatar

Watchers

 avatar  avatar  avatar  avatar  avatar

disconet's Issues

Is there a problem with the given checpoints file?

When I want to train the Disconet model, I transferred the /checkpoints/det/upperbound/no_rsu/epoch_100.pth to the teacher model, but the error "no valid check point file in logs dir, weights not loaded" is reported when running. Is there a problem with the provided. pth file? If not, how to solve it

Question about running train_codet.py

Hi, thanks for your excellent work!
When I run command make make train_disco, I got the following error:
image
and the error is:
image
The dataset is the V2X-Sim2.0(parsed) provided by https://github.com/ai4ce/DiscoNet
image
In the V2X-Sim2.0(parsed) is:
image

My system is Ubuntu 22.04 , and python version is 3.7.16.
My cuda version is 11.2
Could you tell me what the problem is?

3D object detection

Hi, thank you for your good job!
I noticed that DiscoNet is implemented on a one-stage 3D object detection model, have you conducted it on a two-stage 3D object detection model?

How can I train the teacher model ?

If I don't want to use the pretrained teacher model, then I just have to set kd_flag to zero, right? But I ran into an error when I did like that. Or the teacher model just can't be trained?

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.