RAGAN Loss

# wasserstein type
cr = torch.mean(d_real,0)
cf = torch.mean(d_fake,0)
d_loss = -(d_real-cf) + (d_fake-cr)
g_loss = -(d_fake-cr)

examples

{
"class": "function:hypergan.losses.ragan_loss.RaganLoss",
"type": "hinge"
}

options

attribute

description

type

type

least_squares,hinge,wasserstein or standard. Defaults to standard

string (optional)

rgan

rgan does not average over batch. Defaults to false

boolean (optional)

labels

[a,b,c]. Defaults to [-1,1,1]. Only used in least_squares type

array of floats (optional)