dusty-nv/jetson-utils

Stars
693
Rank 65,262 (Top 2 %)
Language
C++
License
MIT License
Created almost 7 years ago
Updated 5 months ago

dusty-nv/jetson-utils

dusty-nv

There are no reviews yet. Be the first to send feedback to the community and the maintainers!

C++/CUDA/Python multimedia utilities for NVIDIA Jetson

jetson-utils

C++/CUDA/Python multimedia utilities for NVIDIA Jetson:


`/`	Filesystem, CSV/JSON/XML parsing, command-line
`camera/`	GStreamer-based camera capture (V4L2, MIPI CSI)
`codec/`	GStreamer-based hardware video encoder/decoder
`cuda/`	CUDA image processing functions
`display/`	OpenGL window & rendering
`image/`	Image loading & saving
`input/`	Human Interface Devices (HID) from `/dev/input`
`network/`	Sockets, IPv4/IPv6, WebRTC/RTSP server
`python/`	Python bindings and examples
`threads/`	Multithreading, locks, and events
`video/`	Video streaming interfaces

Documentation

Documentation for jetson-utils can be found here:

Building from Source

jetson-utils is typically built as a submodule of jetson-inference, but it can also be compiled/installed standalone:

git clone https://github.com/dusty-nv/jetson-utils
mkdir build
cd build
cmake ../
make -j$(nproc)
sudo make install
sudo ldconfig

If you're missing dependencies, run the jetson-inference/CMakePreBuild.sh script.

jetson-inference

Hello AI World guide to deploying deep-learning inference networks and deep vision primitives with TensorRT and NVIDIA Jetson.

jetson-containers

Machine Learning Containers for NVIDIA Jetson and JetPack-L4T

jetson-reinforcement

Deep reinforcement learning GPU libraries for NVIDIA Jetson TX1/TX2 with PyTorch, OpenAI Gym, and Gazebo robotics simulator.

ros_deep_learning

Deep learning inference nodes for ROS / ROS2 with support for NVIDIA Jetson and TensorRT

jetbot_ros

ROS nodes and Gazebo model for NVIDIA JetBot with Jetson Nano

jetson-voice

ASR/NLP/TTS deep learning inference library for NVIDIA Jetson using PyTorch and TensorRT

NanoLLM

Optimized local inference for LLMs with HuggingFace-like APIs for quantization, vision/language models, multimodal agents, speech, vector DB, and RAG.

jetson-scripts

Configuration scripts and install guides for NVIDIA Jetson platform

turbo2

Tegra Unmanned Retrieval Bot gen2, with NVIDIA Jetson and deep reinforcement learning

jetson-presentations

PDF slides about NVIDIA's Jetson embedded platform and deep learning.

camera-capture

GUI tool for collecting & labeling data from live camera feed

pytorch-segmentation

Training of semantic segmentation networks with PyTorch

rovernet

Deep reinforcement learning-driven robotic controller and navigation library using Torch.

super-resolution

PyTorch super resolution model with RGB support and ONNX exporter

pytorch-classification

Training of image classification models with PyTorch

pytorch-detection

Training of object detection networks with PyTorch

pytorch-odometry

Training of visual odometry estimation networks using PyTorch

NanoDB

Zero-copy multimodal vector DB with CUDA and CLIP/SigLIP

clip_trt

CLIP and SigLIP models optimized with TensorRT with a Transformers-like API

gtc-llm-lab

Jetson AI Lab - LLM Inference

pytorch-timeseries

ros2_pololu

ROS2 nodes for Pololu Maestro, Jrk, and Simple Motor Controller