Skip to main content

A library that implements optionally monotonic lattice based models.

Project description

TensorFlow Lattice is a library that implements fast-to-evaluate and interpretable (optionally monotonic) lattice based models, which are also known as interpolated look-up tables. The library includes a collection of Estimators, which operate like any TensorFlow Estimator. It also includes Keras layers for lattices and feature calibration that can be composed into custom models.

Project details


Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distribution

tensorflow_lattice-2.0.10.tar.gz (205.7 kB view details)

Uploaded Source

Built Distribution

tensorflow_lattice-2.0.10-py2.py3-none-any.whl (236.6 kB view details)

Uploaded Python 2 Python 3

File details

Details for the file tensorflow_lattice-2.0.10.tar.gz.

File metadata

  • Download URL: tensorflow_lattice-2.0.10.tar.gz
  • Upload date:
  • Size: 205.7 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/3.7.0 importlib_metadata/4.6.4 pkginfo/1.8.2 requests/2.25.1 requests-toolbelt/0.9.1 tqdm/4.57.0 CPython/3.9.9

File hashes

Hashes for tensorflow_lattice-2.0.10.tar.gz
Algorithm Hash digest
SHA256 42d3c2f1a23762652dad3f44c9bc5935c969c85ef0e798f05b6d690c37bdd27e
MD5 a3125f383f31f5615c611df2bc9a4c9a
BLAKE2b-256 9ab2e79e4492542b3f80cdbd7b259e8930777e7ececf4d006f033b71d7657d42

See more details on using hashes here.

Provenance

File details

Details for the file tensorflow_lattice-2.0.10-py2.py3-none-any.whl.

File metadata

  • Download URL: tensorflow_lattice-2.0.10-py2.py3-none-any.whl
  • Upload date:
  • Size: 236.6 kB
  • Tags: Python 2, Python 3
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/3.7.0 importlib_metadata/4.6.4 pkginfo/1.8.2 requests/2.25.1 requests-toolbelt/0.9.1 tqdm/4.57.0 CPython/3.9.9

File hashes

Hashes for tensorflow_lattice-2.0.10-py2.py3-none-any.whl
Algorithm Hash digest
SHA256 e0c15c59475841c27ac9bce49cf71e4125401ef7db415b5886111825f6cb8e4d
MD5 b86e706ded47c22127da533108919770
BLAKE2b-256 2dd127e13026db060f9c1a00507b92a4ac0be3b89adf0896adb24b73b9ffe290

See more details on using hashes here.

Provenance

Supported by

AWS AWS Cloud computing and Security Sponsor Datadog Datadog Monitoring Fastly Fastly CDN Google Google Download Analytics Microsoft Microsoft PSF Sponsor Pingdom Pingdom Monitoring Sentry Sentry Error logging StatusPage StatusPage Status page