A library for transfer learning by reusing parts of TensorFlow models.

TensorFlow Hub

TensorFlow Hub is a repository of reusable assets for machine learning with TensorFlow. In particular, it provides pre-trained SavedModels that can be reused to solve new tasks with less training time and less training data.

This GitHub repository hosts the tensorflow_hub Python library to download and reuse SavedModels in your TensorFlow program with a minimum amount of code, as well as other associated code and documentation.

Getting Started

• Introduction
• The asset types of tfhub.dev
  • SavedModels for TensorFlow 2 and the Reusable SavedModel interface.
  • Deprecated: hub.Modules for TensorFlow 1 and their Common Signatures collection.
• Using the library
  • Installation
  • Migration to TF2
  • Common issues
  • Build from source
  • Hosting a module
• Tutorials
  • TF2 Image Retraining
  • TF2 Text Classification
  • Additional TF1 and TF2 examples

Contributing

If you’d like to contribute to TensorFlow Hub, be sure to review the contribution guidelines. To contribute code to the library itself (not examples), you will probably need to build from source.

This project adheres to TensorFlow’s code of conduct. By participating, you are expected to uphold this code.

We use GitHub issues for tracking requests and bugs. Please see the TensorFlow Hub mailing list for general questions and discussion, or tag tensorflow-hub on Stack Overflow.

License

Apache License 2.0