tf.keras.metrics.get
Stay organized with collections Save and categorize content based on your preferences.
Retrieves a Keras metric as a function/Metric class instance.
tf.keras.metrics.get( identifier )
The identifier may be the string name of a metric function or class.
metric = metrics.get("categorical_crossentropy") type(metric) <class 'function'> metric = metrics.get("CategoricalCrossentropy") type(metric) <class '...metrics.CategoricalCrossentropy'>
You can also specify config of the metric to this function by passing dict containing class_name and config as an identifier. Also note that the class_name must map to a Metric class
identifier = {"class_name": "CategoricalCrossentropy", "config": {"from_logits": True} } metric = metrics.get(identifier) type(metric) <class '...metrics.CategoricalCrossentropy'>
Args |
|---|
identifier | A metric identifier. One of None or string name of a metric function/class or metric configuration dictionary or a metric function or a metric class instance |
Returns |
|---|
A Keras metric as a function/ Metric class instance. |
Except as otherwise noted, the content of this page is licensed under the Creative Commons Attribution 4.0 License, and code samples are licensed under the Apache 2.0 License. For details, see the Google Developers Site Policies. Java is a registered trademark of Oracle and/or its affiliates. Some content is licensed under the numpy license.
Last updated 2024-06-07 UTC.
[[["Easy to understand","easyToUnderstand","thumb-up"],["Solved my problem","solvedMyProblem","thumb-up"],["Other","otherUp","thumb-up"]],[["Missing the information I need","missingTheInformationINeed","thumb-down"],["Too complicated / too many steps","tooComplicatedTooManySteps","thumb-down"],["Out of date","outOfDate","thumb-down"],["Samples / code issue","samplesCodeIssue","thumb-down"],["Other","otherDown","thumb-down"]],["Last updated 2024-06-07 UTC."],[],[],null,["# tf.keras.metrics.get\n\n\u003cbr /\u003e\n\n|------------------------------------------------------------------------------------------------------------------|\n| [View source on GitHub](https://github.com/keras-team/keras/tree/v3.3.3/keras/src/metrics/__init__.py#L162-L206) |\n\nRetrieves a Keras metric as a `function`/`Metric` class instance. \n\n tf.keras.metrics.get(\n identifier\n )\n\nThe `identifier` may be the string name of a metric function or class. \n\n metric = metrics.get(\"categorical_crossentropy\")\n type(metric)\n \u003cclass 'function'\u003e\n metric = metrics.get(\"CategoricalCrossentropy\")\n type(metric)\n \u003cclass '...metrics.CategoricalCrossentropy'\u003e\n\nYou can also specify `config` of the metric to this function by passing dict\ncontaining `class_name` and `config` as an identifier. Also note that the\n`class_name` must map to a `Metric` class \n\n identifier = {\"class_name\": \"CategoricalCrossentropy\",\n \"config\": {\"from_logits\": True} }\n metric = metrics.get(identifier)\n type(metric)\n \u003cclass '...metrics.CategoricalCrossentropy'\u003e\n\n\u003cbr /\u003e\n\n\u003cbr /\u003e\n\n\u003cbr /\u003e\n\n| Args ---- ||\n|--------------|---------------------------------------------------------------------------------------------------------------------------------------------------------------|\n| `identifier` | A metric identifier. One of None or string name of a metric function/class or metric configuration dictionary or a metric function or a metric class instance |\n\n\u003cbr /\u003e\n\n\u003cbr /\u003e\n\n\u003cbr /\u003e\n\n\u003cbr /\u003e\n\n| Returns ------- ||\n|---|---|\n| A Keras metric as a `function`/ `Metric` class instance. ||\n\n\u003cbr /\u003e"]]
View source on GitHub