CUDA

scirscool-japan/scirs

A comprehensive scientific computing and AI/ML library in pure Rust, offering SciPy-compatible APIs with 10-100x performance gains.

Calibnetepiception/CalibNet

A self-supervised deep learning model for extrinsic calibration between LiDAR and camera sensors using 3D spatial transformer networks.

CAPTCHA-breakinglllcho/CAPTCHA-breaking

A Python-based CAPTCHA breaking solution using Keras and OpenCV, developed for a data science competition.

DBNetdriving-behavior/DBNet

A large-scale driving behavior dataset with LiDAR point clouds, dashboard videos, and sensor data for autonomous driving research.

captcha.irctcarunpatala/captcha.irctc

A deep learning model that reads IRCTC captchas with 98% accuracy, demonstrating their vulnerability to automated booking.

cunntorch/cunn

CUDA backend implementation for Torch's neural network package, enabling GPU acceleration for deep learning models.

ClojureCUDAuncomplicate/clojurecuda

A Clojure library for GPU-accelerated computing using NVIDIA CUDA, enabling high-performance parallel processing.

Usiigacioist/usiigaci

A semi-automated pipeline for instance-aware cell segmentation, tracking, and migration analysis in phase contrast microscopy using Mask R-CNN.

KFusion: Implementation of KinectFusionGerhardR/kfusion

A CUDA-based implementation of KinectFusion for real-time dense surface reconstruction and tracking using a Kinect camera.

shainetNeuraLegion/shainet

A pure Crystal machine learning library for building and training neural networks with CPU/GPU support and PyTorch compatibility.

Dockerfacenatanielruiz/dockerface

A Docker container for face detection using Faster R-CNN deep learning, processing videos and images with bounding box outputs.

DAGANnebulaV/DAGAN

A deep learning model using generative adversarial networks for fast compressed sensing MRI reconstruction.

MotionNetpxiangwu/MotionNet

A deep learning model for joint perception and motion prediction in autonomous driving using bird's eye view maps.

stochastic-rsrust-dd/stochastic-rs

A high-performance Rust library for simulating stochastic processes, with applications in quantitative finance, statistical modeling, and synthetic data generation.

N2D2CEA-LIST/N2D2

An open-source CAD framework for designing, simulating, and deploying deep neural networks on embedded platforms.

docker-hashcatdizcza/docker-hashcat

Dockerized hashcat with multiple backends (CUDA, OpenCL, POCL) for GPU-accelerated password recovery and hash cracking.

DH3DJuanDuGit/DH3D

A deep learning approach that unifies global place recognition and local 6DoF pose refinement for robust relocalization in large-scale 3D point clouds.

MxNet.Sharptech-quantum/MxNet.Sharp

.NET Standard bindings for Apache MXNet, providing C# developers with NumPy-compatible APIs for machine learning model development, training, and deployment.

neural-dreamProGamerGov/neural-dream

A PyTorch implementation of the DeepDream algorithm for generating psychedelic, dream-like images from neural network activations.

Merlinhshindo/Merlin.jl

A fast, flexible, and compact deep learning framework for Julia that runs on CPU and CUDA GPU.

SPOCmathiasbourgoin/SPOC

A PPX-based DSL for writing GPU kernels in OCaml syntax that compiles to multiple backends (CUDA, OpenCL, Vulkan, Metal).

DComputelibmir/dcompute

A set of libraries enabling native execution of D code on GPUs and other accelerators via OpenCL and CUDA runtimes.

mmWave-localization-learninggante/mmWave-localization-learning

A machine learning algorithm for accurate, energy-efficient outdoor positioning using 5G mmWave beamformed fingerprints.

GeneCompassxCompass-AI/GeneCompass

A knowledge-informed cross-species foundation model pre-trained on over 120 million human and mouse single-cell transcriptomes to decipher universal gene regulatory mechanisms.

ANNetGPGPUANNetGPGPU/ANNetGPGPU

A GPU-accelerated (CUDA) C++ template library for building and training artificial neural networks, including self-organizing maps and back-propagation networks.

CellPLMOmicsML/CellPLM

A pre-trained language model for single-cell RNA sequencing data that encodes cell-cell relations and accelerates inference for downstream tasks.

CUBNVlabs/cub

A library of reusable CUDA C++ software components for parallel algorithms like sorting, prefix scan, reduction, and histogram.

DockerDLmatifali/dockerdl

A pre-configured Docker image with deep learning frameworks, data science tools, and GPU support for rapid environment setup.

SMAPjries/SMAP

A modular MATLAB-based platform for analyzing super-resolution microscopy (SMLM) data with GPU-accelerated fitting.

RootPainterAbe404/root_painter

A GUI-based tool for training deep neural networks to segment biological images using corrective annotation.

RustTensorramsyana/RustTensor

A learning-focused, high-performance tensor computation library built from scratch in Rust with automatic differentiation and CPU/CUDA backends.

im2imzsdonghao/Unsup-Im2Im

An implementation of unsupervised image-to-image translation using Generative Adversarial Networks (GANs).