TensorFlow 2.0 RC is available

tf.keras.losses.LogCosh

Class `LogCosh`

Computes the logarithm of the hyperbolic cosine of the prediction error.

Aliases:

• Class `tf.compat.v1.keras.losses.LogCosh`
• Class `tf.compat.v2.keras.losses.LogCosh`
• Class `tf.compat.v2.losses.LogCosh`

`logcosh = log((exp(x) + exp(-x))/2)`, where x is the error (y_pred - y_true)

Usage:

``````l = tf.keras.losses.LogCosh()
loss = l([0., 1., 1.], [1., 0., 1.])
print('Loss: ', loss.numpy())  # Loss: 0.289
``````

Usage with tf.keras API:

``````model = tf.keras.Model(inputs, outputs)
model.compile('sgd', loss=tf.keras.losses.LogCosh())
``````

`__init__`

View source

``````__init__(
reduction=losses_utils.ReductionV2.AUTO,
name='logcosh'
)
``````

Methods

`__call__`

View source

``````__call__(
y_true,
y_pred,
sample_weight=None
)
``````

Invokes the `Loss` instance.

Args:

• `y_true`: Ground truth values.
• `y_pred`: The predicted values.
• `sample_weight`: Optional `Tensor` whose rank is either 0, or the same rank as `y_true`, or is broadcastable to `y_true`. `sample_weight` acts as a coefficient for the loss. If a scalar is provided, then the loss is simply scaled by the given value. If `sample_weight` is a tensor of size `[batch_size]`, then the total loss for each sample of the batch is rescaled by the corresponding element in the `sample_weight` vector. If the shape of `sample_weight` matches the shape of `y_pred`, then the loss of each measurable element of `y_pred` is scaled by the corresponding value of `sample_weight`.

Returns:

Weighted loss float `Tensor`. If `reduction` is `NONE`, this has the same shape as `y_true`; otherwise, it is scalar.

Raises:

• `ValueError`: If the shape of `sample_weight` is invalid.

`from_config`

View source

``````from_config(
cls,
config
)
``````

Instantiates a `Loss` from its config (output of `get_config()`).

Args:

• `config`: Output of `get_config()`.

Returns:

A `Loss` instance.

`get_config`

View source

``````get_config()
``````