GroupNorm¶

class dragon.vm.torch.nn.GroupNorm(
  num_groups,
  num_channels,
  eps=1e-05,
  affine=True
)[source]¶

Apply the group normalization. [Wu & He, 2018].

The normalization is defined as:

\[y = \frac{x - \mathrm{E}[x]} {\sqrt{\mathrm{Var}[x] + \epsilon}} * \gamma + \beta \]

Examples:

m = torch.nn.GroupNorm(num_groups=2, num_channels=4)
x = torch.randn(2, 4)
y = m(x)

See also

torch.nn.functional.group_norm(…)