Enable everyone to develop, optimize and deploy AI models natively on everyone's devices.

World's Leading Open Source JPEG 2000 Codec

YOLOv5 in PyTorch > ONNX > CoreML > TFLite

try to implement halcon shape based matching, refer to machine vision algorithms and applications, page 317 3.11.5, written by halcon engineers

A README template for anyone to copy and use.

Tensors and Dynamic neural networks in Python with strong GPU acceleration

YOLOv4 - Neural Networks for Object Detection (Windows and Linux version of Darknet )

Clone of COCO API - Dataset @ http://cocodataset.org/ - with changes to support Windows build and python3

Open MMLab Detection Toolbox and Benchmark

Open Source Computer Vision Library

Run YoloV3 with the newest TensorRT6.0 at 37 fps on NVIIDIA 1060.

a simple, efficient, easy-to-use nvidia TensorRT wrapper for cnn,sopport c++ and python

Seamless operability between C++11 and Python

ONNX-TensorRT: TensorRT backend for ONNX

Protocol Buffers - Google's data interchange format

Open Neural Network Exchange

TensorRT is a C++ library for high performance inference on NVIDIA GPUs and deep learning accelerators.

Googletest - Google Testing and Mocking Framework

A microbenchmark support library

ONNX Runtime: cross-platform, high performance scoring engine for ML models

CUB is a flexible library of cooperative threadblock primitives and other utilities for CUDA kernel programming.

This repository provides a sample to run yolov3 on int8 mode in tensorRT

If you stop typing for more than five seconds, all progress will be lost.

A PyTorch implementation of the YOLO v3 object detection algorithm