Build a Machine Learning Workflow with Keras TensorFlow 2.0

This course focuses on Keras as part of the TensorFlow 2.0 ecosystem, including sequential APIs to build relatively straightforward models of stacked layers, functional APIs for more complex models, and model subclassing and custom layers. 
Course info
Level
Intermediate
Updated
Jun 2, 2020
Duration
3h 15m
Table of contents
Course Overview
Understanding Keras Models and Layers
Building Regression and Classification Models
Building Image Classification Models
Building Unsupervised Machine Learning Models
Implementing Custom Layers and Models
Description
Course info
Level
Intermediate
Updated
Jun 2, 2020
Duration
3h 15m
Description

Keras shot to popularity some years ago, but in response to the rise of other deep learning frameworks such as PyTorch, Keras has transformed itself into a tightly-connected part of the TensorFlow 2.0 ecosystem.

In this course, Build a Machine Learning Workflow with Keras Tensorflow 2.0, you will see how to harness the combination of the Keras APIs and the underlying power of TensorFlow 2.0

First, you will learn how different APIs in Keras lend themselves to different use cases, like sequential models consisting of stacked layers, high-level APIs contained in tf.keras, and the first-class support for TensorFlow-specific functionality.

Next, you will discover how more complex types of models can be constructed using the functional API which is designed to create callable models - a change from the usual, object-oriented paradigm underlying most deep learning models.

Finally, you will explore how model subclassing is implemented in Keras - which is a great way of implementing the forward pass of a model imperatively, how custom layers work - which offer a high level of flexibility and can be used to define layers that hold state, and best practices that will help you get the most out of your custom layers.

When you are finished with this course, you will have the skills and knowledge to choose between the many different model-building strategies available in Keras, and to use the appropriate strategy to build a robust model that leverages the underlying power of TensorFlow 2.0.

About the author
About the author

A problem solver at heart, Janani has a Masters degree from Stanford and worked for 7+ years at Google. She was one of the original engineers on Google Docs and holds 4 patents for its real-time collaborative editing framework.

More from the author
More courses by Janani Ravi
Section Introduction Transcripts
Section Introduction Transcripts

Course Overview
Hi. My name is Janani Ravi, and welcome to this course, Build a Machine Learning Workflow with Keras TensorFlow 2.0. A little about myself. I have a master's in electrical engineering from Stanford and have worked at companies such as Microsoft, Google, and Flipkart. At Google, I was of the first engineers working on real‑time collaborative editing in Google Docs, and I hold four patents for its underlying technologies. I currently work on my own startup, Loonycorn, a studio for high‑quality video content. In response to the rise of other deep learning frameworks such as PyTorch, Keras has transformed itself into a tightly connected part of the TensorFlow 2.0 ecosystem, even as it serves its original purpose of being a high‑level, easy‑to‑use API. in this course, first you will learn how different APIs in Keras lend themselves to different use cases. Sequential models consisting of layers stacked on top of one another are simple and have long been supported by Keras. Next, you will discover how more complex types of models can be constructed using the functional API. This API is designed to create callable models, which are a change from the usual object‑oriented paradigms underlying most deep learning models. Finally, we'll explore how custom layers work and how model subclassing is implemented in Keras. Model subclassing is a great way of implementing the forward pass of a model imperatively, and is particularly useful when used with eager execution. Custom layers also offer a higher level of flexibility than sequential or functional APIs and can be used to define layers that hold state, including both trainable and non‑trainable weights. You'll also learn best practices that will help you get the most of your custom layers. When you're finished with this course, you will have the skills and knowledge to choose between the many different model building strategies available in Keras.