Machine Learning

Libraries for Machine Learning.

Newest releases

keenon DiffDART: Differentiable Physics Engine

ChunelFeng 跨平台/多语言的 相似向量/相似词/相似句 高性能检索引擎。功能强大,使用方便

jatinchowdhury18 A lightweight neural network inferencing engine written in C++. This library was designed with the intention of being used in real-time audio processing, but may be useful for other tasks as well.

quantumjot BayesianTracker (btrack) is a Python library for multi object tracking, used to reconstruct trajectories in crowded fields. Here, we use a probabilistic network of information to perform the trajectory linking. This method uses sp

tudelft Spiking Neural Networks in C++ with strong GPU acceleration through CUDA

upczww TensorRT implementation of "RepVGG: Making VGG-style ConvNets Great Again"

coin-or A C++ Algorithmic Differentiation Package: Home Page

Samsung This project ONE aims at providing a high-performance, on-device neural network (NN) inference framework that performs inference of a given NN model on processors, such as CPU, GPU, DSP or NPU.

NVIDIA The cuDNN Frontend API is a C++ header-only library that demonstrates how to use the cuDNN C backend API. The cuDNN C backend API is documented in the cuDNN developer guide.

espressif ESP-Skainet is Espressif's intelligent voice assistant, which currently supports the Wake Word Engine and Speech Commands Recognition.

bloomberg A word2vec negative sampling implementation with correct CBOW update.

petercerno High-performance backtesting engine written in C++ for evaluating trading strategies restricted to a single trading pair (e.g. BTC/USD) and finding their optimal hyper-parameters. This software gives you a full control over every

pegasusTrader CTP 高频量化交易平台 C++ Trade Platform for quant developer

jizhang-cmu Autonomous Navigation and Collision Avoidance for Ground Robots

graphcore PopTorch is a set of extensions for PyTorch enabling models to be trained, evaluated and used on the GraphCore IPU.

ethz-asl libnabo is a fast K Nearest Neighbour library for low-dimensional spaces. It provides a clean, legacy-free, scalar-type–agnostic API thanks to C++ templates. Its current CPU implementation is strongly inspired by ANN, but with mor

electech6 Detailed comments for ORB-SLAM3

vidalt Modern implementation of the hybrid genetic search (HGS) algorithm specialized to the capacitated vehicle routing problem (CVRP). This code also includes an additional neighborhood called SWAP*.

NVIDIA-AI-IOT Human pose estimation is the computer vision task of estimating the configuration (‘the pose’) of the human body by localizing certain key points on a body within a video or a photo

deepmind A learning environment written in C++ and Lua for the creation of grid worlds.

d99kris Spacy-cpp is a C++ wrapper library for the excellent NLP library spaCy.

tohtsky myFM is an implementation of Bayesian Factorization Machines based on Gibbs sampling, which I believe is a wheel worth reinventing.

NVIDIA cuCollections (cuco) is an open-source, header-only library of GPU-accelerated, concurrent data structures.

nihui The YOLOv5 object detection android example

adham-elarabawy An open-source 3D-printed quadrupedal robot. Intuitive gait generation through 12-DOF Bezier Curves. Full 6-axis body pose manipulation. Custom 3DOF Leg Inverse Kinematics Model accounting for offsets.

Mazhichaoruya Perception of Autonomous mobile robot,Using ROS,rs-lidar-16,By SLAM,Object Detection with Yolov5 Based DNN

google Makani was a project to develop a commercial-scale airborne wind turbine, culminating in a flight test of the Makani M600 off the coast of Norway. All Makani software has now been open-sourced. This repository contains the working

lxxue A Fixed Nearest Neighbors Search implemented on CUDA with similar interface as pytorch3d.ops.knn_points.

xboot A lightweight, portable pure C99 onnx inference engine for embedded devices with hardware acceleration support.

jinfagang This project is forked from torch2trt and torch2trt_dynamic, the aiming of this project is provide a way directly convert pytorch models to TensorRT engine

QuantScientist ncnnRay++ is a CMake based integration of raylib and the very popular Tencent ncnn Deep Learning library. ncnn is written in C++ designed (but not only) for edge computing devices. The project depends on the Vulkan SDK (Vulakn is

keyth72 Guitar plugin made with JUCE that uses neural network models to emulate real world hardware.

zju3dv Robust and Efficient Visual-Inertial Odometry with Multi-plane Priors