Building and Deploying Deep Learning Applications with TensorFlow

1h 46mIntermediate2017-08-02

Authors

Adam Geitgey

Developer and Machine Learning Consultant

Course details

TensorFlow is one of the most popular deep learning frameworks available. It's used for everything from cutting-edge machine learning research to building new features for the hottest start-ups in Silicon Valley. In this course, learn how to install TensorFlow and use it to build a simple deep learning model. After he shows how to get TensorFlow up and running, instructor Adam Geitgey demonstrates how to create and train a machine learning model, as well as how to leverage visualization tools to analyze and improve your model. Finally, he explains how to deploy models locally or in the cloud. When you wrap up this course, you'll be ready to start building and deploying your own models with TensorFlow.

Learning objectives
What's TensorFlow?
Hardware, software, and language requirements
Creating a TensorFlow model
Training a deep learning model with TensorFlow
Visualizing the computational graph
Adding custom visualizations to TensorBoard
Exporting models for use with Google Cloud

Skills covered

TensorFlowNeural Networks and Deep LearningGoogleArtificial Intelligence (AI)One-Off

Concepts

0. Introduction

01 - Welcome
02 - What you should know
03 - Using the exercise files

1. Setting Up TensorFlow

04 - Install TensorFlow on macOS
05 - Install TensorFlow on Windows

2. TensorFlow Overview

06 - What is TensorFlow
07 - Why is it called TensorFlow
08 - Hardware, software, and language requirements
09 - The train test evaluation flow in TensorFlow
10 - Build a simple model in TensorFlow

3. Creating a TensorFlow Model

11 - Options for loading data
12 - Load the data set
13 - Define the model structure
14 - Set up the model training loop

4. Training a Model in TensorFlow

15 - Train
16 - Log
17 - Save and load trained models

5. TensorBoard

18 - Visualize the computational graph
19 - Visualize training runs
20 - Add custom visualizations to TensorBoard

6. Using a Trained TensorFlow

21 - Export models for use in production
22 - Configure a new Google Cloud account
23 - Host your model in the cloud with Google Cloud
24 - Use a model in the cloud

Conclusion

25 - Next steps