group_norm

dragon.vm.torch.nn.functional.group_norm(
  input,
  weight,
  bias,
  groups=32,
  eps=1e-05
)[source]

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

The normalization is defined as:

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

dragon.vm.torch.Tensor – The output tensor.