778 Open source projects that are alternatives of or similar to ONNX-Runtime-with-TensorRT-and-OpenVINO

Efficient ML Filter Runtimes for VapourSynth (with built-in support for waifu2x, DPIR, RealESRGANv2, and Real-CUGAN)

YOLOX is a high-performance anchor-free YOLO, exceeding yolov3~v5 with MegEngine, ONNX, TensorRT, ncnn, and OpenVINO supported. Documentation: https://yolox.readthedocs.io/

Tengine is a lite, high performance, modular inference engine for embedded device

PyTorch/TorchScript compiler for NVIDIA GPUs using TensorRT

Multiple types of NN model optimization environments. It is possible to directly access the host PC GUI and the camera to verify the operation. Intel iHD GPU (iGPU) support. NVIDIA GPU (dGPU) support.

Komputation is a neural network framework for the Java Virtual Machine written in Kotlin and CUDA C.

All-in-one AI container for rapid prototyping

A CUDA implementation of SIFT for NVidia GPUs (1.2 ms on a GTX 1060)

A community run, 5-day PyTorch Deep Learning Bootcamp

Ubuntu 18.04 How to install Nvidia driver + CUDA + CUDNN + build tensorflow for gpu step by step command line

gmonitor is a GPU monitor (Nvidia only at the moment)

Set up CUDA for machine learning (and gaming) on macOS using a NVIDIA eGPU

🏎️ Accelerate training and inference of 🤗 Transformers with easy to use hardware optimization tools

gprMax is open source software that simulates electromagnetic wave propagation using the Finite-Difference Time-Domain (FDTD) method for numerical modelling of Ground Penetrating Radar (GPR)

Go package for computer vision using OpenCV 4 and beyond.

The C++ parallel algorithms library.

Experiments with CUDA and Rust

OptiX Path Tracer

🐜 A CUDA based miner for Monero

PyTorch/TorchScript compiler for NVIDIA GPUs using TensorRT

A fast stacked hourglass network for human pose estimation on OpenVino

Data visualisation in Python based on OptiX 7.2 ray tracing framework.

This is a highly separated deployment project based on Deepstream , including the full range of Yolo and continuously expanding deployment projects such as Ocr.

Hardware-accelerated DNN model inference ROS2 packages using NVIDIA Triton/TensorRT for both Jetson and x86_64 with CUDA-capable GPU

No description or website provided.

PyTorch Project Specification.

Lane detection for the Nvidia Jetson TX2 using OpenCV4Tegra

Dockerfiles for OpenCV compiled with CUDA, opencv_contrib modules and Python 3 bindings

A fast Clojure Tensor & Deep Learning library

GitHub Action to install CUDA

ILGPU JIT Compiler for high-performance .Net GPU programs

Thin C++-flavored wrappers for the CUDA Runtime API

⚡ Open-source software for deep learning-based digital pathology

JetScan : GPU accelerated portable RGB-D reconstruction system

Cooperative primitives for CUDA C++.

OpenCL integration for Python, plus shiny features

An extensible HPC framework for CUDA, OpenCL and native CPU.

💰 USB flash drive ISO image for Ethereum, Zcash and Monero mining with NVIDIA graphics cards and Ubuntu GNU/Linux (headless)

☁️ Volumetric path tracer using cuda

The C++ Standard Library for your entire system.

cuML - RAPIDS Machine Learning Library

Achieve peak performance on x86 CPUs and NVIDIA GPUs

Modified nVidia .inf files to run drivers on all video cards, research & telemetry free drivers

Image-processing software for cryo-electron microscopy

Super simple & easy Windows 10 cryptocurrency miner made by NiceHash.

A c++ implementation of yolov5 and deepsort

⚡ boost inference speed of T5 models by 5x & reduce the model size by 3x.

How to export PyTorch models with unsupported layers to ONNX and then to Intel OpenVINO

Sample projects for TensorRT in C++

tensorrt int8 量化yolov5 onnx模型

SDK for GPU accelerated genome assembly and analysis

InsightFace REST API for easy deployment of face recognition services with TensorRT in Docker.

The purpose of this project is to apply mediapipe to more AI chips.

YOLO v3, v4, v5, v6, v7 + SORT tracking + ROS platform. Supporting: YOLO with Darknet, OpenCV(DNN), OpenVINO, TensorRT(tkDNN). SORT supports python(original) and C++. (Not Deep SORT)

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

ONNX-TensorRT: TensorRT backend for ONNX

🌲 Aimbot powered by real-time object detection with neural networks, GPU accelerated with Nvidia. Optimized for use with CS:GO.

针对pytorch模型的自动化模型结构分析和修改工具集，包含自动分析模型结构的模型压缩算法库

Rust wrapper for Microsoft's ONNX Runtime (version 1.8)

🍅🍅🍅YOLOv5-Lite: lighter, faster and easier to deploy. Evolved from yolov5 and the size of model is only 930+kb (int8) and 1.7M (fp16). It can reach 10+ FPS on the Raspberry Pi 4B when the input size is 320×320~