GeneratorLSGAN

Inheritance Diagram

---

class ashpy.losses.gan.GeneratorLSGAN

Bases: ashpy.losses.gan.GeneratorAdversarialLoss

Least Square GAN Loss for generator.

Reference: https://arxiv.org/abs/1611.04076

Note

Basically the Mean Squared Error between the discriminator output when evaluated in fake and 1.

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

Methods

__init__()

Initialize the Least Square Loss for the Generator.

Attributes

fn	Return the Keras loss function to execute.
global_batch_size	Global batch size comprises the batch size for each cpu.
weight	Return the loss weight.

__init__()

Initialize the Least Square Loss for the Generator.

Return type:None