Welcome to our training guide for inference and deep vision runtime library for NVIDIA DIGITS and Jetson Xavier/TX1/TX2. This repo uses NVIDIA TensorRT for efficiently deploying neural networks onto the embedded platform, improving performance and power efficiency using graph optimizations, kernel fusion, and half-precision FP16 on the Jetson.
deep-learning inference computer-vision embedded image-recognition object-detection segmentation jetson jetson-tx1 jetson-tx2Autonomous visual navigation components for drones and ground vehicles using deep learning. Refer to wiki for more information on how to get started. This project contains deep neural networks, computer vision and control code, hardware instructions and other artifacts that allow users to build a drone or a ground vehicle which can autonomously navigate through highly unstructured environments like forest trails, sidewalks, etc. Our TrailNet DNN for visual navigation is running on NVIDIA's Jetson embedded platform. Our arXiv paper describes TrailNet and other runtime modules in detail.
ai computer-vision deep-learning robotics artificial-intelligence drones jetsonThis repository contains scripts and documentation to use TensorFlow image classification and object detection models on NVIDIA Jetson. The models are sourced from the TensorFlow models repository and optimized using TensorRT. Flash your Jetson TX2 with JetPack 3.2 (including TensorRT).
neural-network tensorflow models realtime inference optimize nvidia image-classification object-detection train tx1 jetson tensorrt tx2OpenDataCam is an open source tool to quantify the world. It quantifies and tracks moving objects with live video analysis. It is designed to be an accessible, affordable and open-source solution to better understand interactions in urban environments. OpenDataCam never records any photo or video data. The system only saves surveyed meta-data, in particular the path an object moved or number of counted objects at a certain point. The novelty of OpenDataCam is, that everything happens on location, while no visual data is saved or sent to online cloud processing.
iot dataviz computer-vision camera yolo darknet jetson smart-city jetson-tx2 jetson-xavier jetson-nanojetson-stats is a package for monitoring and control your NVIDIA Jetson [Xavier NX, Nano, AGX Xavier, TX1, TX2] Works with all NVIDIA Jetson ecosystem. Read the Wiki for more detailed information or read the package documentation.
pypi nvidia tegra jetson-tx1 cpu-monitoring jetson jetson-tx2 gpu-monitoring memory-monitoring tegrastats nvidia-jetson jetson-xavier jtop jetson-nano jetson-stats nvpmodel jetson-clocks jetson-release jetson-config jetson-xavier-nxPaddlePaddle End-to-End Development Toolkit(『飞桨』深度学习全流程开发工具)
deep-neural-networks deployment detection neural-networks classification segmentation resnet deeplearning unet industry jetson mobilenet yolov3Pre-trained models for human pose estimation capable of running in real time on Jetson Nano. This makes it easy to detect features like left_eye, left_elbow, right_ankle, etc. Training scripts to train on any keypoint task data in MSCOCO format. This means you can experiment with training trt_pose for keypoint detection tasks other than human pose.
real-time pytorch human-pose-estimation pretrained-models jetson live-demo tensorrt human-pose jetson-xavier jetson-nano torch2trtCupoch is a library that implements rapid 3D data processing for robotics using CUDA. The goal of this library is to implement fast 3D data computation in robot systems. For example, it has applications in SLAM, collision avoidance, path planning and tracking. This repository is based on Open3D.
robotics gpu voxel cuda pathfinding point-cloud collision-detection ros registration gpgpu distance-transform odometry jetson pybind11 visual-odometry occupancy-grid-map triangle-meshThe idea of this project is automatically update and setup your NVIDIA Jetson [Nano, Xavier, TX2i, TX2, TX1, TK1] embedded board without wait a lot of time. The Bibbibi Boddibi Boo script recognize if the script run on the NVIDIA Jetson or remotely and request the address and the password to connect on your board.
opencv kernel deep-learning agx ros nvidia jetson-tx1 zed xavier jetson jetson-tk1 jetson-tx2 nvidia-jetson jetson-easy jetson-performance jetson-nanoTensorFlow for Nvidia Jetson TX1/TX2. This script will download lastest build tensorflow in this repository.
tensorflow nvidia-jetson tensorflow-nvjetson jetsonA lightweight and extensible type ahead library. Browserify compatible. Found an issue? Have a feature request? Open a Github Issue and/or fork this repo.
typeahead type ahead type-ahead a head auto complete autocomplete typ typing completing micro microjs marcojetson marco jetson lightweight extensible objects strings list collections mithril mithriljs compatibleHuman pose estimation is the computer vision task of estimating the configuration (‘the pose’) of the human body by localizing certain key points on a body within a video or a photo. The following application serves as a reference to deploy custom pose estimation models with DeepStream 5.0 using the TRTPose project as an example. A detailed deep-dive NVIDIA Developer blog is available here.
real-time computer-vision tesla deepstream human-pose-estimation jetson tensorrtRepository for the Formula 1 Epoch, or F1Epoch, Team. The F1Epoch RACECAR Robots, Epoch and RaceX, are deployable in a wide variety of situations that can affect an office environment, from a fire to an earthquake to a furious storm. Meant to replace a fire marshal, these robots will make multiple head count assessments of the building. In essence, it will try to count humans who are still and based on sensors and a timestamp, send a report of the location of the person spotted.
artificial-intelligence self-driving-car rc-car jetsonROS2 nodes for DeepStream applications. This work is based on sample applications from the DeepStream Python Apps project. The packages have been tested on NVIDIA Jetson AGX Xavier with Ubuntu 18.04, ROS Eloquent, DeepStream SDK 5.0 (or later) and TensorRT. The project accesses some files in the DeepStream 5.0 root location (/opt/nvidia/deepstream/deepstream/samples/).
eloquent real-time deep-learning robotics deepstream jetson ros2The basic usage consists of creating diagnostics_msgs and services for control fan mode/speed, setting up jetson_clocks, and power mode. This will change fan speed to 100; you can see Jetson Fan being turned on.
eloquent robotics jetson ros2This repository contains ROS2 packages for carrying out real time classification and detection for images using PyTorch. It also contains packages which use TensorRT to perform faster inference via torch2trt.
real-time deep-learning robotics pytorch object-detection jetson ros2 tensorrt ssd-mobilenet classification-model resnet-18 ai-iotIn this repository, we build ros2 wrapper for trt_pose for real-time pose estimation on NVIDIA Jetson.
robotics human-pose-estimation jetson ros2 tensorrtThe Turtlebot3 hardware is all open source, and you can find the STL files for the base plates of the burger and waffle on their wiki. You can 3D print extra base plates and modify your Turtlebot3 however you would like. Below is an example of a 3 level mod of the TB3 Burger. It comes with 8 base plates, and I 3D printed another one to create a 3 level mod with 3 plates on each level. This mod is more stable than the 4 level robot, and also allows for more room to add additional sensors.
kernel turtlebot jetson delivery-botSteno is an intelligent video-conferencing system that allows you to make worry-free calls by using 16 microphones and a 360° camera. The system uses artificial intelligence as well as other technologies to offer an enhanced experience both visually and audibly. Steno films and records each person individually, then sends everything to the video-conferencing system. It's like if everyone had a webcam! Steno films you dynamically, which means that if you move around the table, it will be able track your voice and position, and make sure all your words and movements are sent to the end users.
c-plus-plus localization camera video-recording speech-to-text microphones stenography videoconference jetson human-detection odas yolov3 dewarping-library
We have large collection of open source products. Follow the tags from
Tag Cloud >>
Open source products are scattered around the web. Please provide information
about the open source projects you own / you use.
Add Projects.