TensorFlow入门

课程概况

We introduce low-level TensorFlow and work our way through the necessary concepts and APIs so as to be able to write distributed machine learning models. Given a TensorFlow model, we explain how to scale out the training of that model and offer high-performance predictions using Cloud Machine Learning Engine.

Course Objectives:
Create machine learning models in TensorFlow
Use the TensorFlow libraries to solve numerical problems
Troubleshoot and debug common TensorFlow code pitfalls
Use tf.estimator to create, train, and evaluate an ML model
Train, deploy, and productionalize ML models at scale with Cloud ML Engine

课程大纲

Introduction

The tool we will use to write machine learning programs is TensorFlow and so in this course, we will introduce you to TensorFlow. In the first course, you learned how to formulate business problems as machine learning problems and in the second course, you learned how machine works in practice and how to create datasets that you can use for machine learning. Now that you have the data in place, you are ready to get started writing machine learning programs.

Core TensorFlow

We will introduce you to the core components of TensorFlow and you will get hands-on practice building machine learning programs. You will compare and write lazy evaluation and imperative programs, work with graphs, sessions, variables, as finally debug TensorFlow programs.

Estimator API

In this module we will walk you through the Estimator API.

Scaling TensorFlow models

I’m here to talk about how you would go about taking your TensorFlow model and training it on GCP’s managed infrastructure for machine learning model training and deployed.

Summary

Here we summarize the TensorFlow topics we covered so far in this course. We'll revisit core TensorFlow code, the Estimator API, and end with scaling your machine learning models with Cloud Machine Learning Engine.