JetsonGPIO
yolo-tensorrt
JetsonGPIO | yolo-tensorrt | |
---|---|---|
1 | 2 | |
255 | 1,166 | |
- | - | |
7.9 | 1.1 | |
6 months ago | about 1 year ago | |
C++ | C++ | |
MIT License | MIT License |
Stars - the number of stars that a project has on GitHub. Growth - month over month growth in stars.
Activity is a relative number indicating how actively a project is being developed. Recent commits have higher weight than older ones.
For example, an activity of 9.0 indicates that a project is amongst the top 10% of the most actively developed projects that we are tracking.
JetsonGPIO
yolo-tensorrt
-
Using Yolov5 with ROS
I donβt know whether that really solves you problem, but I can tell you how to integrate yolov5 in ros. With this repo: https://github.com/enazoe/yolo-tensorrt you can build a simple ros node around their samples cpp file. This can then subscribe and use ROS images by converting them to cv::Mat using the ros cv_bridge.
-
Real-time Object Detection on Jetson Nano
yep, i tried the tensorrt implementation (https://github.com/enazoe/yolo-tensorrt), on Jetson TX1, with FP16 prevision and it runs YOLOv4 at ~10FPS Had also tried v3 which ran a bit faster, but changed to v4 for the gains in accuracy.
What are some alternatives?
JETGPIO - C library to manage the GPIO header of the Nvidia Jetson boards
yolov5 - YOLOv5 π in PyTorch > ONNX > CoreML > TFLite
jetson_stats - π Simple package for monitoring and control your NVIDIA Jetson [Orin, Xavier, Nano, TX] series
yolov5-deepsort-tensorrt - A c++ implementation of yolov5 and deepsort
tensorflow-yolov4-tflite - YOLOv4, YOLOv4-tiny, YOLOv3, YOLOv3-tiny Implemented in Tensorflow 2.0, Android. Convert YOLO v4 .weights tensorflow, tensorrt and tflite
panther - π Panther is an Open Robotic AGV platform ROS based for Outdoor and Indoor enviroments.
crop - Character Recognition Of Plates using yolov5
jetson-ffmpeg - ffmpeg support on jetson nano
LibtorchTutorials - This is a code repository for pytorch c++ (or libtorch) tutorial.
automation - Lutron Radio RA2 integration with DMX 512 light fixtures, GPIO devices, and other components. Can run on Raspberry Pi Zero W. Provides optional web interface.