tf.keras.losses.get

View source on GitHub

Retrieves a Keras loss as a function/Loss class instance.

View aliases

Compat aliases for migration

See Migration guide for more details.

tf.compat.v1.keras.losses.get

tf.keras.losses.get(
    identifier
)

The identifier may be the string name of a loss function or Loss class.

loss = tf.keras.losses.get("categorical_crossentropy")
type(loss)
<class 'function'>
loss = tf.keras.losses.get("CategoricalCrossentropy")
type(loss)
<class '...keras.losses.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 the class_name must map to a Loss class

identifier = {"class_name": "CategoricalCrossentropy",
              "config": {"from_logits": True} }
loss = tf.keras.losses.get(identifier)
type(loss)
<class '...keras.losses.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.

Raises
ValueError	If identifier cannot be interpreted.