dusty-nv/jetson-inference
A deep learning inference library and tutorial for deploying vision models (imageNet, detectNet, segNet, poseNet, actionNet) on NVIDIA Jetson devices using TensorRT optimization.
Velocity · 7d
+2.5
★ / day
Trend
→steady
star history
This project provides a guide and DNN library for running optimized deep learning inference on NVIDIA Jetson embedded devices. It uses TensorRT to accelerate inference on GPU hardware and PyTorch for model training. The library exposes vision primitives including image classification, object detection, semantic segmentation, pose estimation, and action recognition, with examples for camera streaming, WebRTC webapps, and ROS/ROS2 integration.