Completed
Whole-model saving / serialization and reinstantiation across platforms
Class Central Classrooms beta
YouTube videos curated by Class Central.
Classroom Contents
Inside TensorFlow - tf.Keras - Part 1
Automatically move to the next video in the Classroom when playback concludes
- 1 Intro
- 2 The Keras architecture
- 3 What does a Layer do?
- 4 What does a Layer not do?
- 5 The most basic layer
- 6 A canonical lazy layer (build(), add_weight())
- 7 Nested layers
- 8 Basic usage of a layer
- 9 Defining losses on the fly and collecting them at the end
- 10 Making your layers serializable
- 11 Special call argument: training
- 12 Basic Model
- 13 A Model handles top-level functionality
- 14 Eager & graph execution for fit(), evaluate()
- 15 The Functional API is a way to create DAGs of layers
- 16 A Functional Model behaves like any other Layer/Model, but it has several methods autogenerated (call, build, get_config)
- 17 Anatomy of a Functional Model
- 18 keras history is the coordinates of the tensor in a 3D construction grid
- 19 Static input compatibility checks
- 20 Whole-model saving / serialization and reinstantiation across platforms
- 21 Automatic masking: a first example
- 22 Automatic masking: details
- 23 In-depth: what happens when you call a layer on symbolic inputs
- 24 Using dynamic layers
