UT3Weights.allclose
===================

.. py:method:: t3toolbox.uniform_tucker_tensor_train.UT3Weights.allclose(other, rtol = None, atol = None)

   .. code-block:: python

      def allclose(
              self,
              other: 'UT3Weights',

              rtol:  typ.Optional[float] = None,  # None: the ambient jax-aware default (safety.comparison_rtol)
              atol:  typ.Optional[float] = None,  # None: 0.0
      ) -> NDArray:  # bool, shape=stack_shape (0-d unstacked); reduce with .all()


   True where the MASKED edge-weight vectors are numerically equal, per stack element
   (padding is don't-care; norm-based ``atol + rtol * max`` reference). Different rank masks
   raise. Bitwise incl. padding: :py:meth:`corewise_equal`; ``==`` is intentionally not
   defined.