Computes the gradient for the tanh of `x` wrt its input.
Specifically, `grad = dy (1 - yy)`, where `y = tanh(x)`, and `dy` is the corresponding input gradient.
Constants
String | OP_NAME | The name of this op, as known by TensorFlow core engine |
Public Methods
Output<T> |
asOutput()
Returns the symbolic handle of the tensor.
|
static <T extends TType> TanhGrad<T> | |
Output<T> |
z()
|
Inherited Methods
Constants
public static final String OP_NAME
The name of this op, as known by TensorFlow core engine
Public Methods
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 TanhGrad<T> create (Scope scope, Operand<T> y, Operand<T> dy)
Factory method to create a class wrapping a new TanhGrad operation.
Parameters
scope | current scope |
---|
Returns
- a new instance of TanhGrad