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.
What you'll learn
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.
Table of contents
- Demo: Exploring and Processing the Insurance Dataset 9m
- Demo: Training a Simple Sequential Model 8m
- Demo: Configuring Training Behavior Using Callbacks 6m
- Demo: Saving Model Architecture and Weights 4m
- Demo: Loading Saved Models 4m
- Demo: Exploring and Processing the Spine Dataset 5m
- Demo: Build and Train Model Using the Functional API 7m
- Demo: Checkpointing Models Using Callbacks 3m
- Demo: Monitoring Models Using TensorBoard 6m
- Drawbacks of Dense Neural Networks 3m
- Introducing Convolutional Neural Networks 4m
- Convolution 4m
- Convolutional Layers 6m
- Pooling Layers 4m
- CNN Architecture 3m
- Demo: Loading and Preprocessing the Cifar10 Dataset 7m
- Demo: Designing the Convolutional Neural Network 3m
- Demo: Training and Prediction Using a CNN 4m
- Demo: Using Image Transformations and Dropout 5m
- Customizing Layers and Models 1m
- Model Subclassing and Custom Layers 5m
- Demo: Creating a Custom Layer 7m
- Demo: Deferring Weight Creation in a Layer 2m
- Demo: Accumulating Losses with Custom Layers 6m
- Demo: Serializing Layers and the Training Parameter 3m
- Demo: Building Custom Models 3m
- Demo: Building and Training a Regression Model Using Custom Layers 5m
- Demo: Building and Training a Custom Model with Custom Layers 4m
- Summary and Further Study 2m