Multiplies slices of two tensors in batches.
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: `train.BatchMatMul` supports broadcasting in the batch dimensions. More about broadcasting [here](http://docs.scipy.org/doc/numpy/user/basics.broadcasting.html).
Nested Classes
class | BatchMatMul.Options | Optional attributes for BatchMatMul
|
Constants
String | OP_NAME | The name of this op, as known by TensorFlow core engine |
Public Methods
static BatchMatMul.Options |
adjX(Boolean adjX)
|
static BatchMatMul.Options |
adjY(Boolean adjY)
|
Output<T> |
asOutput()
Returns the symbolic handle of the tensor.
|
static <T extends TType> BatchMatMul<T> |
create(Scope scope, Operand<T> x, Operand<T> y, Options... options)
Factory method to create a class wrapping a new BatchMatMul operation.
|
Output<T> |
output()
3-D or higher with shape `[..., r_o, c_o]`
|
Inherited Methods
Constants
public static final String OP_NAME
The name of this op, as known by TensorFlow core engine
Public Methods
public static BatchMatMul.Options adjX (Boolean adjX)
Parameters
adjX | If `True`, adjoint the slices of `x`. Defaults to `False`. |
---|
public static BatchMatMul.Options adjY (Boolean adjY)
Parameters
adjY | If `True`, adjoint the slices of `y`. Defaults to `False`. |
---|
public Output<T> asOutput ()
Returns the symbolic handle of the tensor.
Inputs to TensorFlow operations are outputs of another TensorFlow operation. This method is used to obtain a symbolic handle that represents the computation of the input.
public static BatchMatMul<T> create (Scope scope, Operand<T> x, Operand<T> y, Options... options)
Factory method to create a class wrapping a new BatchMatMul operation.
Parameters
scope | current scope |
---|---|
x | 2-D or higher with shape `[..., r_x, c_x]`. |
y | 2-D or higher with shape `[..., r_y, c_y]`. |
options | carries optional attributes values |
Returns
- a new instance of BatchMatMul