Inside TensorFlow - tf.Keras - Part 1

Inside TensorFlow - tf.Keras - Part 1

TensorFlow via YouTube Direct link

Intro

1 of 24

1 of 24

Intro

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

Never Stop Learning.

Get personalized course recommendations, track subjects and courses with reminders, and more.

Someone learning on their laptop while sitting on the floor.