Least Squares Loss

From https://arxiv.org/abs/1611.04076​
Source: /losses/least_squares_loss.py​
1
a,b,c = (config.labels or [-1,1,1])
2
d_loss = 0.5*((d_real - b)**2) + 0.5*((d_fake - a)**2)
3
g_loss = 0.5*((d_s
Copied!
examples
Configurations: /losses/least_squares_loss/​
1
{
2
  "class": "function:hypergan.losses.least_squares_loss.LeastSquaresLoss"
3
}
Copied!
options
attribute
description
type
labels
[a,b,c].  Defaults to [-1,1,1]
array of floats (optional)

F Divergence Loss

Logistic Loss

Last modified 1yr ago

Copy link

Contents

examples

options