Gradient Penalty

https://arxiv.org/pdf/1704.00028.pdf

lambdarelu(gradients(target,components)2flex)2lambda * relu(||gradients(target, components)||_2 - flex) ^2

examples

{                                                                                       
  "class": "function:hypergan.train_hooks.gradient_penalty_train_hook.GradientPenaltyTra
  "lambda": 1.00,                                                                       
  "flex": 1.0,                                                                          
  "components": ["discriminator"],                                                       
  "target": "discriminator"
}

options

attribute

description

type

target

Used in gradients(target, components)

defaults to discriminator

string (optional)

lambda

Loss multiple

defaults to 1.0

float

components

Used in gradients(target, components)

defaults to all components

array of strings

flex

Can also be a list for separate X/G flex.

example: [0.0, 10.0]

array of float

loss

Side loss is added to: g_loss or d_loss

defaults to g_loss

string

Last updated