Python v0.3.0

Normalize

class dragon.vm.dali.ops.Normalize(
  axes=(0, 1),
  mean=None,
  stddev=None,
  scale=1.0,
  shift=0.0,
  batch=False,
  epsilon=0,
  dtype='float32',
  **kwargs
)[source]

Normalize input.

Examples:

norm = dali.ops.Normalize(
    # Batch normalization case of HWC layout
    axes=(0, 1), batch=True, epsilon=1e-5,
)
y = norm(inputs['x'])

__new__

static Normalize.__new__(
  cls,
  axes=(0, 1),
  mean=None,
  stddev=None,
  scale=1.0,
  shift=0.0,
  batch=False,
  epsilon=0,
  dtype='float32',
  **kwargs
)[source]

Create a Normalize operator.

Parameters:
  • axes (Sequence[int], optional) – The axes to normalize.
  • mean (float, optional) – The value to subtract.
  • stddev (float, optional) – The value to divide after subtraction.
  • scale (float, optional, default=1.0) – The scale factor after normalization.
  • shift (float, optional, default=0.0) – The shift factor after normalization.
  • batch (bool, optional, default=False) – Whether to compute mean and stddev across the batch.
  • epsilon (float, optional, default=0) – The value added to the computed variance.
  • dtype (str, optional, default='float32') – The output data type.
Returns:

nvidia.dali.ops.Normalize – The operator.