Upgrade to Pro — share decks privately, control downloads, hide ads and more …

Machine Learning Model Serving with Backend.AI

Jeongkyu Shin
November 29, 2018

Machine Learning Model Serving with Backend.AI

머신러닝 모델을 서비스 단에서 서빙하는 것은 손이 많이 갑니다.
서비스 과정을 편리하게 하기 위하여 TensorFlow serving 등 서빙 과정을 돕는 다양한 도구들이 공개되고 개발되고 있습니다만, 여전히 서빙 과정은 귀찮고 불편합니다. 이 세션에서는 Backend.AI 와 TensorFlow serving을 이용하여 간단하게 TensorFlow 모델을 서빙하는 법에 대해 다루어 봅니다.
Backend.AI 서빙 모드를 소개하고, 여러 TF serving 모델 등을 Backend.AI 로 서비스하는 과정을 통해 실제로 사용하는 법을 알아봅니다.

Serving the machine learning model at the service level is a lot of work. A variety of tools are being developed and released to facilitate the process of serving. TensorFlow serving is the greatest one for serving now, but the docker image baking-based serving process is not easy, not flexible and controllable enough. In this session, I will discuss how to simplify the serving process of TensorFlow models by using Backend.AI and TensorFlow serving.

I will introduce the Backend.AI serving mode (on the trunk but will be official since 1.6). After that, I will demonstrate how to use the Backend.AI serving mode that conveniently provides various TensorFlow models with TensorFlow serving on the fly.

Jeongkyu Shin

November 29, 2018

More Decks by Jeongkyu Shin

Other Decks in Technology