tf.keras.losses.get | TensorFlow v2.16.1 (original) (raw)
tf.keras.losses.get
Retrieves a Keras loss as a function/Loss class instance.
tf.keras.losses.get(
identifier
)
The identifier may be the string name of a loss function or Loss class.
loss = losses.get("categorical_crossentropy")
type(loss)
<class 'function'>
loss = losses.get("CategoricalCrossentropy")
type(loss)
<class '...CategoricalCrossentropy'>
You can also specify config of the loss to this function by passing dict containing class_name and config as an identifier. Also note that theclass_name must map to a Loss class
identifier = {"class_name": "CategoricalCrossentropy",
"config": {"from_logits": True} }
loss = losses.get(identifier)
type(loss)
<class '...CategoricalCrossentropy'>
| Args | |
|---|---|
| identifier | A loss identifier. One of None or string name of a loss function/class or loss configuration dictionary or a loss function or a loss class instance. |
| Returns |
|---|
| A Keras loss as a function/ Loss 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.