TensorFlow Hub - AshokBhat/ml GitHub Wiki

About

• TensorFlow Hub is a library of reusable parts of machine learning models
  • Objectives - publication, discovery, and consumption
• A module is a self-contained piece of a TensorFlow graph, along with its weights and assets, that can be reused across different tasks in a process known as transfer learning
• Transfer learning can:
  • Train a model with a smaller dataset,
  • Improve generalization, and
  • Speed up training.

FAQ

• What is TF Hub?
• How do you use TF Hub?

See also

• TensorFlow
• Transfer Learning