nvidia.dali.experimental.dynamic.expand_dims

nvidia.dali.experimental.dynamic.expand_dims(data, /, *, batch_size=None, device=None, axes, new_axis_names=None)

Insert new dimension(s) with extent 1 to the data shape.

The new dimensions are inserted at the positions specified by axes.

If new_axis_names is provided, the new dimension names will be inserted in the data layout, at the positions specified by axes. If new_axis_names is not provided, the output data layout will be empty.”

This operator allows sequence inputs and supports volumetric data.

Supported backends

• ‘cpu’

• ‘gpu’

Parameters:

data (Tensor/Batch) – Data to be expanded

Keyword Arguments:

• axes (int or list of int or Tensor/Batch of int) – Indices at which the new dimensions are inserted.

• new_axis_names (layout str, optional, default = ‘’) –

  Names of the new dimensions in the data layout.

  The length of new_axis_names must match the length of axes. If argument isn’t be provided, the layout will be cleared.