adalkiran/distributed-inference

A project to demonstrate an approach to designing cross-language and distributed pipeline in deep learning/machine learning domain, using WebRTC and Redis Streams.

37
/ 100
Emerging

This project helps operations engineers set up a distributed deep learning system to analyze live video streams. It takes incoming video from a webcam, processes it through a YOLOX object detection model, and outputs detected objects with their locations. It's designed for system administrators and operations engineers who need to deploy real-time AI processing across multiple servers or data centers.

No commits in the last 6 months.

Use this if you need to deploy a real-time object detection system that can scale across multiple machines, handling live video streams and integrating different programming languages.

Not ideal if you are looking for a simple, single-machine solution or do not need cross-language microservices and distributed deployment without Kubernetes.

live-video-analysis distributed-systems object-detection real-time-AI operations-engineering
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 9 / 25
Maturity 16 / 25
Community 12 / 25

How are scores calculated?

Stars

86

Forks

9

Language

Go

License

Apache-2.0

Last pushed

Sep 18, 2024

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/adalkiran/distributed-inference"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.