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.
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.
Stars
86
Forks
9
Language
Go
License
Apache-2.0
Category
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.
Higher-rated alternatives
deepspeedai/DeepSpeed
DeepSpeed is a deep learning optimization library that makes distributed training and inference...
helmholtz-analytics/heat
Distributed tensors and Machine Learning framework with GPU and MPI acceleration in Python
hpcaitech/ColossalAI
Making large AI models cheaper, faster and more accessible
horovod/horovod
Distributed training framework for TensorFlow, Keras, PyTorch, and Apache MXNet.
bsc-wdc/dislib
The Distributed Computing library for python implemented using PyCOMPSs programming model for HPC.