tf.keras.Loss

Loss base class.

Main aliases

tf.keras.losses.Loss

Compat aliases for migration

See Migration guide for more details.

tf.keras.Loss(
    name=None, reduction='sum_over_batch_size', dtype=None
)

This is the class to subclass in order to create new custom losses.

Args
`reduction`	Type of reduction to apply to the loss. In almost all cases this should be `"sum_over_batch_size"`. Supported options are `"sum"`, `"sum_over_batch_size"`, `"mean"`, `"mean_with_sample_weight"` or `None`. `"sum"` sums the loss, `"sum_over_batch_size"` and `"mean"` sum the loss and divide by the sample size, and `"mean_with_sample_weight"` sums the loss and divides by the sum of the sample weights. `"none"` and `None` perform no aggregation. Defaults to `"sum_over_batch_size"`.
`name`	Optional name for the loss instance.
`dtype`	The dtype of the loss's computations. Defaults to `None`, which means using `keras.backend.floatx()`. `keras.backend.floatx()` is a `"float32"` unless set to different value (via `keras.backend.set_floatx()`). If a `keras.DTypePolicy` is provided, then the `compute_dtype` will be utilized.

To be implemented by subclasses:

Example subclass implementation:

class MeanSquaredError(Loss):
    def call(self, y_true, y_pred):
        return ops.mean(ops.square(y_pred - y_true), axis=-1)

Attributes
`dtype`

Attributes

dtype

call(
    y_true, y_pred
)

@classmethod
from_config(
    config
)

get_config()

__call__(
    y_true, y_pred, sample_weight=None
)

Call self as a function.