ak.to_torch
-----------

.. py:module: ak.to_torch

Defined in `awkward.operations.ak_to_torch <https://github.com/scikit-hep/awkward/blob/36da52cfa8846355c390beb6555eac1d31c27c26/src/awkward/operations/ak_to_torch.py>`__ on `line 15 <https://github.com/scikit-hep/awkward/blob/36da52cfa8846355c390beb6555eac1d31c27c26/src/awkward/operations/ak_to_torch.py#L15>`__.

.. py:function:: ak.to_torch(array)


    :param array: Array-like data. May be a high level :py:obj:`ak.Array`,
              or low-level :py:obj:`ak.contents.ListOffsetArray`, :py:obj:`ak.contents.ListArray`,
              :py:obj:`ak.contents.RegularArray`, :py:obj:`ak.contents.NumpyArray`

Converts ``array`` (only ListOffsetArray, ListArray, RegularArray and NumpyArray data types supported)
into a PyTorch Tensor, if possible.

If ``array`` contains any other data types (RecordArray for example) the function raises a TypeError.