Giter Site home page Giter Site logo

opendrivelab / hdgt Goto Github PK

View Code? Open in Web Editor NEW
92.0 92.0 9.0 1.24 MB

[IEEE T-PAMI 2023] Unified heterogeneous transformer-based graph neural network for motion prediction

Home Page: https://ieeexplore.ieee.org/document/10192373

Python 100.00%
autonomous-driving motion-prediction waymo-challenge

hdgt's People

Contributors

faikit avatar hli2020 avatar jiaxiaosong1002 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

Watchers

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

hdgt's Issues

Module found error "metricss_soft_map"

Traceback (most recent call last):
File "train.py", line 23, in
from metricss_soft_map import soft_map
ModuleNotFoundError: No module named 'metricss_soft_map'

How to install the module named "metricss_soft_map", I cannot install it with pip and conda, could I delete the module since I found no referene of this module in code?

Loss function details

Hi,

Thanks for the great work! I noticed that in the paper, you set the classification loss weight to be 0.1, is there a reason behind this? Where can I find more information/experiments related to the hyper-parameter tuning of this weight?

Best,

Arielle

Question about INTERACTION leaderboard

@jiaxiaosong1002 Hello, I would like to know if the data for HDGT on the INTERACTION leaderboard single-agent track is based on ’all‘ types of scenarios or only on ’regular‘ types. Up to the end of 2023, all methods only included data for ’all‘ types. However, I found that when I only submit ’regular‘ data, it still generates data for ’all‘ types.

INTERACTION

hi~
it's a great work! I want to run this code with the INTERACTION dataset, how do I operate on it? Can you provide a little processing code? Very much looking forward to your reply!

An error while running train.py

Hi~
Thank you for sharing your code. This work has been very inspiring to me. So, I want to reproduce this code. But i have met some problems when i running train.py. It throws an error 'ModuleNotFoundError: No module named 'metricss_soft_map''. I'm wondering what might be the reason for this. Looking forward to your reply!

Source code

I would like know when will the source code released?

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.