nvidia-cuda

Run a <400ms latency Voice Agent on just 4GB VRAM. Fully offline, no API keys required. Optimized for GTX 1650 and edge robotics with zero-copy inference. (Apache 2.0)

Implementation of ConjugateGradients method using C and Nvidia CUDA

This system tracks artifacts in museum and triggers alarm if artifact goes missing from the frame.

Fundamentals of heterogeneous parallel programming with CUDA C/C++ at the beginner level.

PyTorch Image and Video Super-Resolution, specialized for vehicle and traffic view processing and performed by using Deep Convolutional Neural Networks

基于 Whisper 的语音转文字工具。一键转录至剪贴板，解决云端吞字与隐私忧虑。针对中文环境优化，打破网页端限制，实现与各家大模型（ChatGPT/Grok/Gemini 等）的无缝对话。Local Whisper-based voice input tool. One-click transcribe to clipboard, zero privacy leaks, no more cloud swallowing text. Optimized for Chinese, breaks web-side limits, enabling seamless voice chat with LLMs

A simple image classifier built with Keras using NVIDIA cuda libraries.

This script collects some informations about NVLink and PCI bus traffic of NVidia GPUs. Results are published as prometheus metrics via a websocket.

A YOLOv4 model that can detect 5 classes on the road and a comparison with YOLOv3.

This repository contains scripts and commands for exporting YOLO models to different formats, including TensorRT (.engine) and ONNX (.onnx). Cuda 12.6

🤖 Set up a GPU-accelerated ROS 2 development environment with FastAPI for efficient robotics navigation and simulation using Docker on Windows.

Automatic transcriber made with the Nvidia NeMo AI toolkit. Used to transcribe speech to text in real-time from any source. Requires CUDA capable GPU to run on the local machine, if setup using virtual audio cables can transcribe the audio that is being played in real-time without any other requirements.

The simplest & most comprehensible tutorial on speaker identification with NVIDIA's `Nemo`.

🥧 Development toolkit & templates. Advanced AI context engineering, production project frameworks.

my thesis works on mri image segmentation of brain tumour using deep learning models

A pre-configured instant-ngp workspace that includes helpful scripts for getting started with NeRF training.

A deepfake face detection system using transfer learning with Xception CNN. Trained on real and fake face datasets using data augmentation, mixed precision, and GPU acceleration. Accurately classifies facial images as real or fake with high confidence. Ideal for media forensics.

Home Lab POC - Local offline capable AI pipeline for voice transcription, multilingual translation and summarization

for nvidia graphic metrics on datadog

Hybridize NVIDIA vGPU Host and Guest drivers to retain the Host's CUDA capability