GHingeLoss

Inheritance Diagram

---

class ashpy.keras.losses.GHingeLoss

Bases: tensorflow.python.keras.losses.Loss

Generator Hinge Loss as Keras Metric.

See Geometric GAN [1] for more details. The Generator Hinge loss is the hinge version of the adversarial loss. The Hinge loss is defined as:

\[L_{\text{hinge}} = \max(0, 1 - t y)\]

where y is the Discriminator output and t is the target class (+1 or -1 in the case of binary classification). The target class of the generated images is +1.

For the case of GANs

\[L_{G_{\text{hinge}}} = - \mathbb{E}_{(x \sim p_x, y \sim p_data} [ \min(0, -1+D(G(x),y)) ]\]

This can be simply approximated as:

\[L_{G_{\text{hinge}}} = - \mathbb{E}_{(x \sim p_x, y \sim p_data} [ D(G(x),y) ]\]

[1]	Geometric GAN https://arxiv.org/abs/1705.02894

Methods

__init__()	Initialize the Loss.
call(d_real, d_fake)	Compute the hinge loss.

Attributes

reduction

Return the current reduction for this type of loss.

__init__()

Initialize the Loss.

Return type:None

call(d_real, d_fake)

Compute the hinge loss.

Return type:Tensor

reduction

Return the current reduction for this type of loss.

Return type:ReductionV2