:py:mod:`rannet.utils`
======================

.. py:module:: rannet.utils


Module Contents
---------------


Functions
~~~~~~~~~

.. autoapisummary::

   rannet.utils.triangular_causal_mask
   rannet.utils.prefix_causal_mask
   rannet.utils.standard_normalize
   rannet.utils.mean



.. py:function:: triangular_causal_mask(seq_len: Union[int, langml.tensor_typing.Tensors]) -> langml.tensor_typing.Tensors

   Generate triangular causal mask
   :param seq_len: sequence len

   .. rubric:: Examples

   for seq_len = 3, the mask is:
   array([[1., 0., 0.],
           [1., 1., 0.],
           [1., 1., 1.]], dtype=float32)


.. py:function:: prefix_causal_mask(segment: langml.tensor_typing.Tensors) -> langml.tensor_typing.Tensors

   Generate prefix causal mask
   :param segment: segment ids

   .. rubric:: Examples

   for segment [[0, 0, 0, 1, 1]], the mask is;
   array([[[1., 1., 1., 0., 0.],
           [1., 1., 1., 0., 0.],
           [1., 1., 1., 0., 0.],
           [1., 1., 1., 1., 0.],
           [1., 1., 1., 1., 1.]]], dtype=float32)


.. py:function:: standard_normalize(x: langml.tensor_typing.Tensors, epsilon: float = 1e-07) -> langml.tensor_typing.Tensors


.. py:function:: mean(x: langml.tensor_typing.Tensors, mask: Optional[langml.tensor_typing.Tensors] = None, axis: float = -1, keepdims: bool = False) -> langml.tensor_typing.Tensors