chainer.functions.tensordot

chainer.functions.tensordot(a, b, axes=2)[source]

Returns the tensor dot product of two arrays along specified axes.

This is equivalent to compute dot product along the specified axes which are treated as one axis by reshaping.

Parameters
  • a (Variable or N-dimensional array) – The first argument.

  • b (Variable or N-dimensional array) – The second argument.

  • axes

    • If it is an integer, then axes axes at the last of a and the first of b are used.

    • If it is a pair of sequences of integers, then these two sequences specify the list of axes for a and b. The corresponding axes are paired for sum-product.

Returns

The tensor dot product of a and b along the axes specified by axes.

Return type

Variable

Example

>>> a = np.random.rand(5, 3, 2)
>>> b = np.random.rand(3, 2, 4)
>>> c = F.tensordot(a, b, axes=2)
>>> c.shape
(5, 4)