Hysia: Serving DNN-Based Video-to-Retail Applications in Cloud

TL;DR

Hysia is a cloud-based platform that simplifies development and deployment of video-to-retail applications using DNNs, optimized GPU computation, and easy model integration for multimedia practitioners and researchers.

Contribution

The paper introduces Hysia, a comprehensive cloud platform that integrates state-of-the-art multimedia libraries, optimizes GPU usage, and facilitates rapid prototyping and deployment of V2R applications.

Findings

Hysia enables efficient large-scale multimedia V2R applications.

It seamlessly integrates NVIDIA SDK, Facebook faiss, and gRPC.

Hysia is open source and available on DockerHub.

Abstract

Combining \underline{v}ideo streaming and online \underline{r}etailing (V2R) has been a growing trend recently. In this paper, we provide practitioners and researchers in multimedia with a cloud-based platform named Hysia for easy development and deployment of V2R applications. The system consists of: 1) a back-end infrastructure providing optimized V2R related services including data engine, model repository, model serving and content matching; and 2) an application layer which enables rapid V2R application prototyping. Hysia addresses industry and academic needs in large-scale multimedia by: 1) seamlessly integrating state-of-the-art libraries including NVIDIA video SDK, Facebook faiss, and gRPC; 2) efficiently utilizing GPU computation; and 3) allowing developers to bind new models easily to meet the rapidly changing deep learning (DL) techniques. On top of that, we implement an orchestrator for further optimizing DL model serving performance. Hysia has been released as an open source project on GitHub, and attracted considerable attention. We have published Hysia to DockerHub as an official image for seamless integration and deployment in current cloud environments.