Custom Prediction Routine on Google AI Platform

5.0 /5

(1 Rating)

Offered byCoursera

Custom Prediction Routine on Google AI Platform
at
Coursera
Overview

Upskilling is a better roadmap to success. Enroll in this course to learn critical principles of Data Science through real-life case studies & examples

Duration	2 hours
Start from	Start Now
Total fee	Free
Mode of learning	Online
Difficulty level	Intermediate
Official Website	Explore Free Course
Credential	Certificate

Custom Prediction Routine on Google AI Platform
at
Coursera
Highlights

Earn a certificate of learning on course completion
Start instantly and learn at your own schedule.
Enroll for free
Pay only for getting a certificate of completion
This course is offered by Rhyme

Custom Prediction Routine on Google AI Platform
at
Coursera
Course details

Skills you will learn

Software Testing Data Science

More about this course

In this 2-hour long project-based course, you will learn how to deploy, and use a model on Google's AI Platform. Normally, any model trained with the TensorFlow framework is quite easy to deploy, and you can simply upload a Saved Model on Google Storage, and create an AI Platform model with it. But, in practice, we may not always use TensorFlow. Fortunately, the AI Platform allows for custom prediction routines as well and that's what we are going to focus on. Instead of converting a Keras model to a TensorFlow Saved Model, we will use the h5 ?le as is. Additionally, since we will be working with image data, we will use this opportunity to look at encoding and decoding of byte data into string for data transmission and then encoding of the received data in our custom prediction routine on the AI Platform before using it with our model.