tensorflow:: ops:: BatchMatMulV2

Multiplies slices of two tensors in batches.

Summary

Multiplies all slices of Tensor x and y (each slice can be viewed as an element of a batch), and arranges the individual results in a single output tensor of the same batch size. Each of the individual slices can optionally be adjointed (to adjoint a matrix means to transpose and conjugate it) before multiplication by setting the adj_x or adj_y flag to True , which are by default False .

The input tensors x and y are 2-D or higher with shape [..., r_x, c_x] and [..., r_y, c_y] .

The output tensor is 2-D or higher with shape [..., r_o, c_o] , where:

r_o = c_x if adj_x else r_x
c_o = r_y if adj_y else c_y

It is computed as:

output[..., :, :] = matrix(x[..., :, :]) * matrix(y[..., :, :])

NOTE : BatchMatMulV2 supports broadcasting in the batch dimensions. More about broadcasting here .

Args:

• scope: A Scope object
• x: 2-D or higher with shape [..., r_x, c_x] .
• y: 2-D or higher with shape [..., r_y, c_y] .

Optional attributes (see Attrs ):

• adj_x: If True , adjoint the slices of x . Defaults to False .
• adj_y: If True , adjoint the slices of y . Defaults to False .

Returns:

• Output : 3-D or higher with shape [..., r_o, c_o]

Public attributes

Operation operation

::tensorflow::Output output

Public functions

 BatchMatMulV2(
  const ::tensorflow::Scope & scope,
  ::tensorflow::Input x,
  ::tensorflow::Input y
)

 BatchMatMulV2(
  const ::tensorflow::Scope & scope,
  ::tensorflow::Input x,
  ::tensorflow::Input y,
  const BatchMatMulV2::Attrs & attrs
)

::tensorflow::Node * node() const 

 operator::tensorflow::Input() const 

 operator::tensorflow::Output() const 

Public static functions

Attrs AdjX(
  bool x
)

Attrs AdjY(
  bool x
)