Serving Tensorflow Models with a REST API

4.2
14 個評分
提供方
Coursera Project Network
1,615 人已註冊
在此指導項目中,您將:

Create and save Tensorflow models as servable objects

Integrate custom functions into servables

Serve TF servables using conforming to REST

Clock2 hours
Intermediate中級
Cloud無需下載
Video分屏視頻
Comment Dots英語(English)
Laptop僅限桌面

In this project-based course, you will learn step-by-step procedures for serving Tensorflow models with a RESTful API. We will learn to save a Tensorflow object as a servable, deploy servables in Docker containers, as well as how to test our API endpoints and optimize our API response time. I would encourage learners to experiment with the tools and methods discussed in this course. The learner is highly encouraged to experiment beyond the scope of the course. Note: This course works best for learners who are based in the North America region. We’re currently working on providing the same experience in other regions.

您要培養的技能

Web ApplicationPython ProgrammingTensorflowRepresentational State Transfer (REST)model optimization

分步進行學習

在與您的工作區一起在分屏中播放的視頻中,您的授課教師將指導您完成每個步驟:

  1. Define basic terminology

  2. Saving our model in the SavedModel format

  3. Serving the Model: Server Side

  4. Serving the Model: Client Requests

  5. Using Docker for serving

指導項目工作原理

您的工作空間就是瀏覽器中的雲桌面,無需下載

在分屏視頻中,您的授課教師會為您提供分步指導

常見問題

常見問題

還有其他問題嗎?請訪問 學生幫助中心