HyperGAN
HyperGAN
HyperGAN
HyperGAN
About
Getting started
CLI guide
Configurations
Showcase
AI Explorer for Android
Youtube, Twitter, Discord +
Examples
2D
Text
Classification
Colorizer
Next Frame (video)
Tutorials
Training a GAN
Pygame inference
Creating an image dataset
Searching for hyperparameters
Components
GAN
Generator
Discriminator
Layers
Loss
ALI Loss
F Divergence Loss
Least Squares Loss
Logistic Loss
QP Loss
RAGAN Loss
Realness Loss
Softmax Loss
Standard Loss
Wasserstein Loss
Latent
Trainer
Optimizer
Train Hook
Other GAN implementations
Powered by GitBook

Standard Loss

  • Source: /losses/standard_loss.py​

criterion = torch.nn.BCEWithLogitsLoss()
g_loss = criterion(d_fake, torch.ones_like(d_fake))
d_loss = criterion(d_real, torch.ones_like(d_real)) + criterion(d_fake, torch.zeros_like(d_fake))

examples

  • Configurations: /losses/standard_loss/​

{
"class": "class:hypergan.losses.standard_loss.StandardLoss"
}
Previous
Softmax Loss
Next
Wasserstein Loss
Last updated 8 months ago