https://github.com/tensorflow/lattice

Lattice methods in TensorFlow
https://github.com/tensorflow/lattice

Last synced: 28 days ago
JSON representation

Lattice methods in TensorFlow

• Host: GitHub
• URL: https://github.com/tensorflow/lattice
• Owner: tensorflow
• License: apache-2.0
• Created: 2017-09-22T03:27:49.000Z (about 7 years ago)
• Default Branch: master
• Last Pushed: 2024-07-30T20:06:20.000Z (3 months ago)
• Last Synced: 2024-09-30T16:41:59.646Z (about 1 month ago)
• Language: Python
• Size: 1.52 MB
• Stars: 518
• Watchers: 37
• Forks: 94
• Open Issues: 10
• Metadata Files:
  • Readme: README.md
  • Contributing: CONTRIBUTING.md
  • License: LICENSE
  • Authors: AUTHORS

Awesome Lists containing this project

• awesome-tensorflow - Lattice - Implementation of Monotonic Calibrated Interpolated Look-Up Tables in TensorFlow (Libraries)
• AwesomeResponsibleAI - Tensorflow Lattice
• awesome-list - Lattice - Lattice methods in TensorFlow (Deep Learning Framework / High-Level DL APIs)
• awesome-tensorflow - Lattice - Implementation of Monotonic Calibrated Interpolated Look-Up Tables in TensorFlow (Libraries)
• fucking-awesome-tensorflow - Lattice - Implementation of Monotonic Calibrated Interpolated Look-Up Tables in TensorFlow (Libraries)

README

        

# TensorFlow Lattice

TensorFlow Lattice is a library that implements constrained and interpretable

lattice based models. It is an implementation of

[Monotonic Calibrated Interpolated Look-Up Tables](http://jmlr.org/papers/v17/15-243.html)

in [TensorFlow](https://www.tensorflow.org).

The library enables you to inject domain knowledge into

the learning process through common-sense or policy-driven shape constraints.

This is done using a collection of Keras layers that can satisfy constraints

such as monotonicity, convexity and pairwise trust:

* PWLCalibration: piecewise linear calibration of signals.

* CategoricalCalibration: mapping of categorical inputs into real values.

* Lattice: interpolated look-up table implementation.

* Linear: linear function with monotonicity and norm constraints.

The library also provides easy to setup canned estimators for common use cases:

* Calibrated Linear

* Calibrated Lattice

* Random Tiny Lattices (RTL)

* Crystals

With TF Lattice you can use domain knowledge to better extrapolate to the parts

of the input space not covered by the training dataset. This helps avoid

unexpected model behaviour when the serving distribution is different from the

training distribution.



  



You can install our prebuilt pip package using

```bash

pip install tensorflow-lattice

```