tensorflow-addons
TensorFlow Addons.
Decision gist · record as of 2026-08-14
Yes-with-conditions. TensorFlow Addons is worth installing if you need specific experimental components that were stable in the 0.23.0 release and your TensorFlow version is compatible. However, the dormant status (no releases in 990 days) means you should verify compatibility with your current TensorFlow and Python versions before committing. Do not use this package for new projects expecting ongoing maintenance or security updates.AI-flagged interpretation of the facts on this page — verify before relying
Before you install
- Requires TensorFlow to be installed separately; wheels are pre-built for Python 3.9, 3.10, 3.11 on x86_64 Linux and macOS (Intel and ARM).
- Medium install friction due to compiled wheels for specific Python versions and platforms.
- Package is dormant—last release was 990 days ago—so expect no active maintenance or bug fixes.
License · maintenance · safety
Apache 2.0 (permissive) — Apache 2.0 permissive license allows commercial and private use with minimal restrictions, requiring only license and copyright notice retention.
last release 2023-11-28 (990 days)
0 known vulnerabilities (OSV.dev, 2026-08-14) · 1,030,500 downloads/mo, #4,472 on PyPI
Alternatives
Verify before relying
pip install tensorflow-addons==0.23.0
import tensorflow_addons as tfa
import packaging
import typeguard- Whether tensorflow-addons 0.23.0 is compatible with recent TensorFlow versions (fact sheet does not specify TensorFlow version constraint).
- Whether dormant status means the package will work with current Python and TensorFlow ecosystem or if breaking changes have accumulated.
- What specific operators, layers, metrics, losses, and optimizers are included in 0.23.0.
What it is and what it does
TensorFlow Addons is a collection of experimental machine learning components—custom layers, loss functions, metrics, and optimizers—that extend TensorFlow but are not yet part of the core library. These additions target either emerging techniques whose broad applicability is still unclear or specialized functionality used by smaller subsets of the ML community. The package acts as an incubator for ideas that may eventually graduate to core TensorFlow or remain as optional extensions.
The package depends on packaging and typeguard for runtime support. It is distributed as pre-compiled wheels for Python 3.9, 3.10, and 3.11 on Linux x86_64 and macOS (both Intel and ARM). However, the package has been dormant for nearly three years—the last release was in November 2023—meaning no active maintenance, bug fixes, or compatibility updates are expected. This makes it risky for new projects or those requiring ongoing support.
Use it for
- Experimenting with novel layer architectures or optimization algorithms not yet available in core TensorFlow.
- Implementing specialized loss functions or metrics for niche machine learning domains.
- Prototyping research ideas before deciding whether to contribute them upstream to TensorFlow.
- Using well-tested experimental components in production if they were stable at the time of the last release.
Worth the install?
AI-flagged interpretation of the facts on this page. Verify before relying on it.
Yes-with-conditions.
TensorFlow Addons is worth installing if you need specific experimental components that were stable in the 0.23.0 release and your TensorFlow version is compatible. However, the dormant status (no releases in 990 days) means you should verify compatibility with your current TensorFlow and Python versions before committing. Do not use this package for new projects expecting ongoing maintenance or security updates.
Install
tensorflow-addons on PyPI
Before you install
Medium install friction due to compiled wheels for specific Python versions and platforms. Package is dormant—last release was 990 days ago—so expect no active maintenance or bug fixes.
Requires TensorFlow to be installed separately; wheels are pre-built for Python 3.9, 3.10, 3.11 on x86_64 Linux and macOS (Intel and ARM).
License in practice
Apache 2.0 permissive license allows commercial and private use with minimal restrictions, requiring only license and copyright notice retention.
Quickstart
pip install tensorflow-addons==0.23.0
import tensorflow_addons as tfa
import packaging
import typeguardVerify before relying
- Whether tensorflow-addons 0.23.0 is compatible with recent TensorFlow versions (fact sheet does not specify TensorFlow version constraint).
- Whether dormant status means the package will work with current Python and TensorFlow ecosystem or if breaking changes have accumulated.
- What specific operators, layers, metrics, losses, and optimizers are included in 0.23.0.
Package facts
| License | Apache 2.0 permissive |
| Python support | Not specified |
| Install friction | Medium. Platform-specific wheel |
| Runtime dependencies | 2 packagespackagingtypeguard |
| Maintenance | Dormant 990 days since the last release |
| First released | |
| Downloads | 1,030,500 / month, #4,472 on PyPI 30-day window, as of 2026-08-14 |
| Known vulnerabilities | None known OSV.dev, checked 2026-08-14 |
| Classifiers | Development Status :: 4 - BetaIntended Audience :: DevelopersIntended Audience :: EducationIntended Audience :: Science/ResearchLicense :: OSI Approved :: Apache Software LicenseProgramming Language :: Python :: 3Programming Language :: Python :: 3.10Programming Language :: Python :: 3.11Programming Language :: Python :: 3.9Topic :: Scientific/Engineering :: MathematicsTopic :: Software Development :: LibrariesTopic :: Software Development :: Libraries :: Python Modules |
Evidence: tensorflow_addons-0.23.0-cp310-cp310-macosx_10_14_x86_64.whl; tensorflow_addons-0.23.0-cp310-cp310-macosx_11_0_arm64.whl; tensorflow_addons-0.23.0-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl; tensorflow_addons-0.23.0-cp311-cp311-macosx_10_14_x86_64.whl; tensorflow_addons-0.23.0-cp311-cp311-macosx_11_0_arm64.whl; tensorflow_addons-0.23.0-cp311-cp311-manylinux_2_17_x86_64.manylinux2014_x86_64.whl; tensorflow_addons-0.23.0-cp39-cp39-macosx_10_14_x86_64.whl; tensorflow_addons-0.23.0-cp39-cp39-macosx_11_0_arm64.whl; tensorflow_addons-0.23.0-cp39-cp39-manylinux_2_17_x86_64.manylinux2014_x86_64.whl
Tags
Let your AI agent find packages like this
Example. Real query, live index.
You found this page by searching. An agent finds it by wishing: SkillFed indexes 14,416 PyPI packages by what they can do, searchable in plain language.
wish › “tensorflow extensions”
- tensorflow-addonsTensorFlow Addons provides experimental operators, layers, metrics,…
- tensorflow-ioExtends TensorFlow with support for file systems and data formats not…
- types-tensorflowProvides type hints for TensorFlow 2.18.0, enabling static type…
Give your agent the search over MCP, or paste the wish link into any chat.
More Libraries packages
urllib3 is an HTTP client library that provides thread-safe connection pooling, SSL/TLS verification, multipart file uploads, request retries, compression support, and proxy handling for Python applications.
Requests is a Python HTTP library that simplifies sending HTTP/1.1 requests with automatic handling of headers, authentication, cookies, and response parsing.
Pluggy provides a plugin system that lets you define hook specifications and register implementations to be called in sequence, enabling extensible Python applications without tight coupling.
Install it if you're building an extensible application or framework.
Provides parsing, arithmetic, and recurrence rule computation for dates and times, with timezone support and iCalendar RFC compliance.
Install it if you need to parse flexible date strings, compute relative dates, handle timezones, or work with recurrence rules—it's the de facto choice for these tasks.
Six provides utility functions to write Python code that runs on both Python 2.7 and Python 3.3+, smoothing over language differences between the two versions.
pytest is a testing framework that lets you write test functions using plain assert statements and automatically discovers and runs them, with detailed failure reporting.
See also tf-keras-nightly · tf-keras · tf-slim · Keras-Preprocessing · keras-nightly · tensorflow-metadata · keras · tensorflow-probability · tensorflow-graphics · tfp-nightly