T3Weights.allclose
==================

.. py:method:: t3toolbox.tucker_tensor_train.T3Weights.allclose(other, rtol = None, atol = None)

   .. code-block:: python

      def allclose(
              self,
              other: 'T3Weights',

              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 edge-weight vectors are numerically equal, per stack element:
   ``||self - other|| <= atol + rtol * max(||self||, ||other||)`` over the concatenated edge
   vectors (the weights ARE the mathematical object). Structural mismatches raise. Bitwise:
   :py:meth:`corewise_equal`; ``==`` is intentionally not defined -- say which you mean.