tfr.keras.losses.SoftmaxLoss

View source on GitHub

Computes Softmax cross-entropy loss between y_true and y_pred.

tfr.keras.losses.SoftmaxLoss(
    reduction=tf.losses.Reduction.AUTO,
    name=None,
    lambda_weight=None,
    temperature=1.0,
    ragged=False
)

For each list of scores s in y_pred and list of labels y in y_true:

loss = - sum_i y_i * log(softmax(s_i))

Standalone usage:

y_true = [[1., 0.]]
y_pred = [[0.6, 0.8]]
loss = tfr.keras.losses.SoftmaxLoss()
loss(y_true, y_pred).numpy()
0.7981389

# Using ragged tensors
y_true = tf.ragged.constant([[1., 0.], [0., 1., 0.]])
y_pred = tf.ragged.constant([[0.6, 0.8], [0.5, 0.8, 0.4]])
loss = tfr.keras.losses.SoftmaxLoss(ragged=True)
loss(y_true, y_pred).numpy()
0.83911896

Usage with the compile() API:

model.compile(optimizer='sgd', loss=tfr.keras.losses.SoftmaxLoss())

Definition:

$$ \mathcal{L}({y}, {s}) =

• \sum_i y_i \cdot \log\left(\frac{exp(s_i)}{\sum_j exp(s_j)}\right) $$

Args
reduction	(Optional) The tf.keras.losses.Reduction to use (see tf.keras.losses.Loss).
name	(Optional) The name for the op.
lambda_weight	(Optional) A lambdaweight to apply to the loss. Can be one of tfr.keras.losses.DCGLambdaWeight, tfr.keras.losses.NDCGLambdaWeight, or, tfr.keras.losses.PrecisionLambdaWeight.
temperature	(Optional) The temperature to use for scaling the logits.
ragged	(Optional) If True, this loss will accept ragged tensors. If False, this loss will accept dense tensors.

Methods

from_config

View source

@classmethod
from_config(
    config, custom_objects=None
)

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()

Returns the config dictionary for a Loss instance.

__call__

View source

__call__(
    y_true, y_pred, sample_weight=None
)

See _RankingLoss.