tensorflow-addons 0.23.0

TensorFlow Addons.

Stars: 1680, Watchers: 1680, Forks: 605, Open Issues: 88

The tensorflow/addons repo was created 5 years ago and the last code push was 2 weeks ago.
The project is very popular with an impressive 1680 github stars!

How to Install tensorflow-addons

You can install tensorflow-addons using pip

pip install tensorflow-addons

or add it to a project with poetry

poetry add tensorflow-addons

Package Details

Author

Google Inc.

License

Apache 2.0

Homepage

PyPi:

https://pypi.org/project/tensorflow-addons/

GitHub Repo:

https://github.com/tensorflow/addons

Classifiers

• Scientific/Engineering/Mathematics
• Software Development/Libraries
• Software Development/Libraries/Python Modules

Related Packages

Errors

A list of common tensorflow-addons errors.

Code Examples

Here are some tensorflow-addons code examples and snippets.

GitHub Issues

The tensorflow-addons package has 88 open issues on GitHub

• Proposed feature: Multi-Head Attention with O(sqrt(N)) memory
• Make GN and IN the same dtype behavior as BN or LN in mixed_precision
• Exclude parameters from AdamW's weight decaying
• ValueError: Dimensions must be equal, but are 100 and 19 for '{{node cond/add_1}} = AddV2[T=DT_INT32](cond/add, cond/add_1/Cast)' with input shapes: [?,100], [?,100,19].
• Cannot install tensorflow-addons with python 3.10
• Added Precision & Recall Metrics with average and threshold parameter
• Loss calculated incorrectly in networks_seq2seq_nmt.ipynb
• [WIP] Build against tf2.8rc0
• Fix backport bot
• MacOS Arm64 support for stable TF-Addons Releases
• ValueError: Dimensions must be equal, but are 75 and 8 for
• Fix under tested build on macos
• Support for macOS Monterey
• dev_container
• Triangular2/Exponential cyclical learning rates do not work when logging with Tensorboard

See more issues on GitHub