Stars
Scapy: the Python-based interactive packet manipulation program & library.
Detectron2 is a platform for object detection, segmentation and other visual recognition tasks.
Deepstream/Gstreamer custom element to access the buffer in gpu memory and map it to GpuMat. Purpose of the element is to use it for preprocessing where it has been written using basic cuda program…
Hardware-accelerated video decoding, encoding and processing on Intel graphics through VA-API. This module has been merged into the main GStreamer repo for further development.
OpenVINO™ is an open source toolkit for optimizing and deploying AI inference
A unified library of SOTA model optimization techniques like quantization, pruning, distillation, speculative decoding, etc. It compresses deep learning models for downstream deployment frameworks …
To ensure developers can get the most out of our performance-leading hardware, we built the Voyager™ SDK which facilitates the development of high-performance applications.
WasmEdge is a lightweight, high-performance, and extensible WebAssembly runtime for cloud native, edge, and decentralized applications. It powers serverless apps, embedded functions, microservices,…
High-performance Inference and Deployment Toolkit for LLMs and VLMs based on PaddlePaddle
Docker Mastery Udemy course to build, compose, deploy, and manage containers from local development to high-availability in the cloud
Official code for "FeatUp: A Model-Agnostic Frameworkfor Features at Any Resolution" ICLR 2024
an edge-real-time anchor-free object detector with decent performance
[CVPR 2025] Event Stream based Object Detection Benchmark Dataset
Effortless AI-assisted data labeling with AI support from YOLO, Segment Anything (SAM+SAM2), MobileSAM!!
Hello AI World guide to deploying deep-learning inference networks and deep vision primitives with TensorRT and NVIDIA Jetson.
Blueprint for Ingesting massive volumes of live or archived videos and extract insights for summarization and interactive Q&A
基于Nvidia Deepstream的支持多模型并行推理的流视频处理框架
An open source library for face detection in images. The face detection speed can reach 1000FPS.
Development repository for the Triton language and compiler
This AI system integrates DeepStream for face recognition. It also applies a face alignment algorithm before feature extraction, improving the system’s robustness and accuracy in recognizing faces.
Examples of Linux Inter-Processing Communication
OcelStream is a modular DeepStream-based platform for real-time video analytics using custom models like YOLO, SAM, and D-Fine. It includes C++ parsers, Python bindings, and RabbitMQ to stream fram…