Python v0.4.0a0+62b766a

Erase

class dragon.vm.dali.ops.Erase(
  axes=(0, 1),
  fill_value=0,
  normalized_anchor=True,
  normalized_shape=True,
  **kwargs
)[source]

Erase regions from the input.

Examples:

erase = dali.ops.Erase(
    # The axes to erase
    axes=[0, 1],
    # The value fill
    fill_value=0.,
)
y = erase(inputs['x'], anchor=(0, 0), shape=(100, 100))

__new__

static Erase.__new__(
  cls,
  axes=(0, 1),
  fill_value=0,
  normalized_anchor=True,
  normalized_shape=True,
  **kwargs
)[source]

Create an Erase operator.

Parameters:
  • axes (Sequence[int], optional) – The padding axes.
  • fill_value (Union[number, Sequence[float]], optional) – The value to fill the erased regions.
  • normalized_anchor (bool, optional, default=True) – Provided anchor is normalized or not.
  • normalized_shape (bool, optional, default=True) – Provided shape is normalized or not.
Returns:

nvidia.dali.ops.Erase – The operator.