nvidia.dali.experimental.dynamic.flip#
- nvidia.dali.experimental.dynamic.flip(
- input,
- /,
- *,
- batch_size=None,
- device=None,
- depthwise=None,
- horizontal=None,
- vertical=None,
Flips the images in selected dimensions (horizontal, vertical, and depthwise).
This operator allows sequence inputs and supports volumetric data.
- Supported backends
‘cpu’
‘gpu’
- Parameters:
input¶ (Tensor/Batch ('FDHWC', 'FHWC', 'DHWC', 'HWC', 'FCDHW', 'FCHW', 'CDHW', 'CHW')) – Input to the operator.
- Keyword Arguments:
depthwise¶ (int or Tensor/Batch of int, optional, default = 0) – Flip the depthwise dimension.
horizontal¶ (int or Tensor/Batch of int, optional, default = 1) – Flip the horizontal dimension.
vertical¶ (int or Tensor/Batch of int, optional, default = 0) – Flip the vertical dimension.
batch_size¶ (int, optional) – The batch size to broadcast input tensors to. Ignored for batch inputs.
device¶ (device-like, optional) – The device to use for the operation. Must not conflict with the device of the inputs.
See also