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.

  • 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.

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

Return type:



>>> 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)