The pupose of this project is to do the inference of models YOLOv3 and YOLOv3-Tiny using the the TF-TRT (TensorFlow-TensorRT) Python API with TensorFlow v1.15

Shrimp management autonomous vehicle ROS source code

DC Brushless DC Motor with Computer Vision using behavioural cloning AI, to recognise roads and autonomously run on them

📀NVIDIA DeepStream integrated GStreamer Plugin. Mask objects with cuda cores on Jetson boards. Fast and smooth since everything is done on NVMM.🏎

Run a reproducible COLMAP workflow from a YAML configuration file and log NVIDIA Jetson metrics

Configuration for the neural simulator GENN and python library PyGENN on Jetson Xavier NX

Rust GRPC server for face recognition, face detection and face alignment using TensorRT, Cuda on JetPack SDK (Jetson Nano, Jetson Xavier NX)

This repository contains the content for a proof of concept implementation of computer vision systems in industry. The project explores scalability and performance using the NVIDIA ecosystem, aiming to create an example scaffold for implementing a system accessible to non-technical users.

Experiments with ROS2 / Docker on a Jetson Xavier

Test of tensorRT on a custom net using jetson devices

A small setup to deploy a containerized python ROS2 node that runs the inference of a deep network on images by the OAK-D Lite camera on a Nvidia Jetson

Cookbook for new Robotics students

NVIDIA Jetson TX1, TX2, AGX & Nano Linux kernel driver for the IMX327 based "VEYE-MIPI-327" camera module by veye.cc

Realtime Monocular depth estimation using Logitech Camera and Jetson Xavier NX board. Used weights from the "Monodepth" algorithm for training, to test in real-time.

基于YOLOv5和NX的ROS硬件在环

ROS package to get "sensor_msgs/Imu" data from mpu6050 on Jetson Xavier NX

Python sample for referencing pre-trained SSD MobileNet V2 (TF 1.x) model with TensorRT

Personal docker setup with all the tools and packages I use