DMinMax¶

Inheritance Diagram

class ashpy.keras.losses.DMinMax(from_logits=True, label_smoothing=0.0)[source]¶

Bases: tensorflow.python.keras.losses.Loss

Implementation of MinMax Discriminator loss as tf.keras.losses.Loss.

\[L_{D} = - \frac{1}{2} E [\log(D(x)) + \log (1 - D(G(z))]\]

Methods

`__init__`([from_logits, label_smoothing])	Initialize the loss.
`call`(d_real, d_fake)	Compute the MinMax Loss.

Attributes

reduction Return the reduction type of this loss.

__init__(from_logits=True, label_smoothing=0.0)[source]¶

Initialize the loss.

Return type:	`None`

call(d_real, d_fake)[source]¶

Compute the MinMax Loss.

Play the DiscriminatorMinMax game between the discriminator computed in real and the discriminator compute with fake inputs.

Parameters:	d_real (`tf.Tensor`) – Real data. d_fake (`tf.Tensor`) – Fake (generated) data.
Return type:	`Tensor`
Returns:	`tf.Tensor` – Output Tensor.

reduction¶

Return the reduction type of this loss.

Return type:	`ReductionV2`
Returns:	:py:classes:`tf.keras.losses.Reduction` – Reduction.