Building Deep Learning Applications with Keras 2.0

Introduction

• Welcome
• What you should know
• Using the exercise files

1. Keras Overview

• What is Keras?
• TensorFlow and Theano backends
• Using Keras vs. TensorFlow

2. Setting Up Keras

• Installing Keras with the TensorFlow backend on macOS
• Installing Keras with the TensorFlow backend on Windows

3. Creating a Neural Network in Keras

• The train-test-evaluation flow
• Keras Sequential API
• Pre-processing training data
• Define a Keras model using the Sequential API

4. Training Models

• Training and evaluating the model
• Making predictions
• Saving and loading models

5. Pre-Trained Models in Keras

• Pre-trained models
• Recognize images with ResNet50 model

6. Monitoring a Keras model with TensorBoard

• Export Keras logs in TensorFlow format
• Visualize the computational graph
• Visualize training progress

7. Using a Trained Keras Model in Google Cloud

• Exporting Google Cloud-compatible models
• Configuring a new Google Cloud account
• Uploading a Keras model to Google Cloud
• Using a model in Google Cloud

Conclusion

• Next steps