Git Product home page Git Product logo

ros2_tvm's Introduction

about

  • this repo test the object detection and segmentation models with tvm in ROS2

dependencies

  • ubuntu 20.04, ROS2 galactic
  • tvm
  • pytorch

how to run

  • the object detection model is DETR
    • I tried many models from mxnet, tensorflow, and pytorch, DETR from pytorch is the only one what works correctly in tvm rust
    • the script to generate the tvm graph is in scripts/test_detection_pytorch.py
  • the image segmentation model is unet
    • the script to generate the tvm graph is in scripts/test_seg.py
  1. generate the models for tvm using the python scripts are in the scripts folder
  2. cargo run
  3. run the ROS2 kitti dataset publisher

performance

  • for cpu version tigerlake
    • object detection takes about 478.95 ms per image, which is 2.06 Hz
    • segmentation takes about 356.32 ms per image, which is 2.81 Hz

demo

  • object detection img img

  • image segmentation img img

reference

ros2_tvm's People

Contributors

shanmo avatar

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.