TensorFlow - Custom Models, Layers, and Loss Functions with TensorFlow

Overview

On this accelerated TensorFlow Custom Models, Layers, and Loss Functions with TensorFlow course, you’ll gain knowledge on how to use and customise the TensorFlow API for your business' needs. You’ll learn to compare functional and sequential APIs, discover new models you can build with the Functional API, and build a model that produces multiple outputs including a Siamese network.

In just 2 days, you’ll learn to build custom loss functions (including the contrastive loss function used in a Siamese network) in order to measure how well a model is doing and help your neural network learn from training data. You’ll also learn to build knowledge on:

• Existing standard layers to create custom layers for your models, customise a network layer with a lambda layer, understand the differences between them, learn what makes up a custom layer, and explore activation functions.
• Existing models to add custom functionality, learn how to define your own custom class instead of using the Functional or Sequential APIs, build models that can be inherited from the TensorFlow Model class, and build a residual network (ResNet) through defining a custom model class

At the end of this course, you’ll sit the Custom Models, Layers, and Loss Functions with TensorFlow exam and achieve your certification. Through Firebrand’s Lecture | Lab | Review methodology, you’ll get access to courseware, learn from certified instructors, and train in a distraction-free environment.

Audience

This course is ideal if you are a Software Engineer or ML Engineer, interested in building your skills by learning advanced TensorFlow features to build powerful models.