DLeastSquare

Inheritance Diagram

---

class ashpy.keras.losses.DLeastSquare

Bases: tensorflow.python.keras.losses.Loss

Discriminator Least Square Loss as tf.keras.losses.Loss.

Methods

__init__()	Least square Loss for Discriminator.
call(d_real, d_fake)	Compute the Least Square Loss.

Attributes

reduction

Return the reduction type for this loss.

__init__()

Least square Loss for Discriminator.

Reference: Least Squares Generative Adversarial Networks [1] .

Basically the Mean Squared Error between the discriminator output when evaluated in fake samples and 0 and the discriminator output when evaluated in real samples and 1: For the unconditioned case this is:

\[L_{D} = \frac{1}{2} E[(D(x) - 1)^2 + (0 - D(G(z))^2]\]

where x are real samples and z is the latent vector.

For the conditioned case this is:

\[L_{D} = \frac{1}{2} E[(D(x, c) - 1)^2 + (0 - D(G(c), c)^2]\]

where c is the condition and x are real samples.

[1]	Least Squares Generative Adversarial Networks https://arxiv.org/abs/1611.04076

Return type:None

call(d_real, d_fake)

Compute the Least Square Loss.

Parameters:

• d_real (tf.Tensor) – Discriminator evaluated in real samples.
• d_fake (tf.Tensor) – Discriminator evaluated in fake samples.

Return type:

Tensor

Returns:

tf.Tensor – Loss.

reduction

Return the reduction type for this loss.

Return type:ReductionV2 Returns:tf.keras.losses.Reduction – Reduction.