page_type: reference description: APIs to train an on-device recommendation model.

<link rel="stylesheet" href="/site-assets/css/style.css"> <!-- DO NOT EDIT! Automatically generated file. --> <div itemscope itemtype="http://developers.google.com/ReferenceObject"> <meta itemprop="name" content="tflite_model_maker.recommendation" /> <meta itemprop="path" content="Stable" /> </div>

Module: tflite_model_maker.recommendation

<!-- Insert buttons and diff --> <table class="tfo-notebook-buttons tfo-api nocontent" align="left"> <td> <a target="_blank" href="https://github.com/tensorflow/examples/blob/tflmm/v0.4.2/tensorflow_examples/lite/model_maker/public/recommendation/__init__.py"> </a> </td> </table>

APIs to train an on-device recommendation model.

Demo code:

<a href="https://github.com/tensorflow/examples/blob/master/tensorflow_examples/lite/model_maker/demo/recommendation_demo.py">https://github.com/tensorflow/examples/blob/master/tensorflow_examples/lite/model_maker/demo/recommendation_demo.py</a>

Modules

spec module: APIs for recommendation specifications.

Classes

class DataLoader: Recommendation data loader.

class ModelSpec: Recommendation model spec.

class Recommendation: Recommendation task class.

Functions

create(...): Loads data and train the model for recommendation.