CUDA

TensorComprehensionsfacebookresearch/TensorComprehensions

A domain-specific language and C++ library for automatically synthesizing high-performance machine learning kernels.

Votenetfacebookresearch/votenet

An end-to-end 3D object detection network that uses deep point set networks and Hough voting to directly detect objects in point clouds.

VkFFTDTolm/VkFFT

A high-performance GPU-accelerated Fast Fourier Transform library supporting Vulkan, CUDA, HIP, OpenCL, Level Zero, and Metal backends.

MarSmicrosoft/MarS

A financial market simulation engine powered by a generative foundation model for realistic, interactive, and controllable order generation.

GitHub repositorycharlesq34/frustum-pointnets

A deep learning pipeline for 3D object detection from RGB-D data by combining 2D detectors with PointNet-based 3D processing.

fast_gicpSMRT-AIST/fast_gicp

A collection of high-performance GICP-based point cloud registration algorithms with multi-threaded and GPU-accelerated implementations.

ThunderSVMXtra-Computing/thundersvm

A fast Support Vector Machine (SVM) library that leverages GPUs and multi-core CPUs for high-performance machine learning.

GitHub repositoryQingyongHu/RandLA-Net

An efficient neural network for semantic segmentation of large-scale 3D point clouds using random sampling.

Speech Notemkiol/dsnote

A Linux desktop app for offline note-taking, reading, and translation using speech-to-text, text-to-speech, and machine translation.

MatXNVIDIA/MatX

A modern C++20 GPU numerical computing library with Python-like syntax for near-native performance on NVIDIA GPUs.

PersonaeCeruleanacg/Personae

A repository implementing Deep Reinforcement Learning and Supervised Learning methods with a simulated financial market environment for quantitative trading.

Deeppyandersbll/deeppy

A Pythonic deep learning framework built on NumPy with optional CUDA acceleration.

Image Analogymsracver/Deep-Image-Analogy

A deep learning technique for finding semantically-meaningful dense correspondences between images to enable visual attribute transfer.

Mocha.jlpluskid/Mocha.jl

A deep learning framework for Julia inspired by Caffe, featuring modular architecture and multiple backends.

CTPNtianzhi0549/CTPN

Scene text detection using Connectionist Text Proposal Network (CTPN) for detecting text lines in natural images.

cortexoriginrose/cortex

A Clojure library for neural networks, regression, and feature learning with GPU acceleration support.

hyperposetensorlayer/hyperpose

A library for building high-performance custom human pose estimation applications with real-time inference and flexible model development.

stdgpustotko/stdgpu

A C++17 library providing efficient STL-like data structures (vector, unordered_map, etc.) for GPU programming with CUDA, OpenMP, and HIP backends.

hebelhannes-brt/hebel

A GPU-accelerated deep learning library for Python using CUDA via PyCUDA, implementing neural networks with various training methods.

hyprwhsprgoodroot/hyprwhspr

A fast, accurate, and private native speech-to-text tool for Linux, offering system-wide dictation with local or cloud backends.

Cupochneka-nat/cupoch

A CUDA-accelerated library for rapid 3D data processing in robotics, enabling GPU-powered SLAM, collision avoidance, and path planning.

GitHub repositorydrprojects/superpoint_transformer

A PyTorch framework for efficient 3D semantic and panoptic segmentation using superpoint-based transformer architectures.

DetectAndTrackfacebookresearch/DetectAndTrack

A CVPR 2018 algorithm for efficient multi-person pose estimation and tracking in videos, ranking first in the ICCV 2017 PoseTrack challenge.

RLtoolsrl-tools/rl-tools

A high-performance, portable deep reinforcement learning library for continuous control, optimized for speed across CPUs, GPUs, and microcontrollers.

Penglabmxrch/penglab

A Google Colab notebook setup for high-performance hash cracking and penetration testing tools.

BitCrackere-ago/bitcracker

An open-source GPU-accelerated password cracking tool for BitLocker-encrypted storage devices using dictionary attacks.

deepdivedeepdrive/deepdrive

An open-source simulator for experimenting with and advancing self-driving AI, accessible to anyone with a PC.

Deepnetnitishsrivastava/deepnet

GPU-accelerated Python implementation of six fundamental deep learning algorithms using CUDA libraries.

cuda-api-wrapperseyalroz/cuda-api-wrappers

Thin, unified C++ wrappers for NVIDIA's CUDA APIs (Runtime, Driver, NVRTC, NVTX) that improve safety and ease of use.

neural-style-ptProGamerGov/neural-style-pt

A PyTorch implementation of neural style transfer, combining the content of one image with the artistic style of another.

torch-rbankane/torch-rb

A Ruby deep learning library powered by LibTorch, providing a PyTorch-like API for Ruby developers.

Torch.rbankane/torch.rb

A deep learning library for Ruby that provides a native interface to LibTorch, enabling GPU-accelerated neural network development.

Objaxgoogle/objax

An object-oriented machine learning framework built on JAX, designed for simplicity and readability in research.

DNABERTjerryji1993/DNABERT

A pre-trained BERT model designed for DNA sequence analysis, enabling genome understanding tasks like classification and motif discovery.

OpenChemMariewelt/OpenChem

A deep learning toolkit for computational chemistry and drug design research with PyTorch backend.

GitHub repositoryPRBonn/OverlapNet

A Siamese neural network for LiDAR-based loop closing and localization by predicting scan overlap and relative yaw angle.