nvidia.dali.experimental.dynamic.bb_flip#

nvidia.dali.experimental.dynamic.bb_flip(
input,
/,
*,
batch_size=None,
device=None,
horizontal=None,
ltrb=None,
vertical=None,
)#

Flips bounding boxes horizontally or vertically (mirror).

The bounding box coordinates for the input are in the [x, y, width, height] - xywh or [left, top, right, bottom] - ltrb format. All coordinates are in the image coordinate system, that is 0.0-1.0

Supported backends

  • ‘cpu’

  • ‘gpu’

Parameters:

input (Tensor/Batch) – Input to the operator.

Keyword Arguments:

  • horizontal (int or Tensor/Batch of int, optional, default = 1) – Flip horizontal dimension.

  • ltrb (bool, optional, default = False) – True for ltrb or False for xywh.

  • vertical (int or Tensor/Batch of int, optional, default = 0) – Flip 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.

On this page