PyTorchDiscriminator.gradient_penalty¶
- PyTorchDiscriminator.gradient_penalty(x, lambda_=5.0, k=0.01, c=1.0)[sorgente]¶
Compute gradient penalty for discriminator optimization
- Parametri:
x (numpy.ndarray) – Generated data sample.
lambda (float) – Gradient penalty coefficient 1.
k (float) – Gradient penalty coefficient 2.
c (float) – Gradient penalty coefficient 3.
- Ritorna:
Gradient penalty.
- Tipo di ritorno:
torch.Tensor