batch_norm

dragon.vm.torch.nn.functional.batch_norm(
  input,
  running_mean,
  running_var,
  weight,
  bias,
  training=False,
  momentum=0.1,
  eps=1e-05
)[source]

Apply the batch normalization to input. [Ioffe & Szegedy, 2015].

Parameters:
Returns:

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