L2 Loss.
Computes half the L2 norm of a tensor without the `sqrt`:
output = sum(t ** 2) / 2
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 TNumber> L2Loss<T> | |
Output<T> |
output()
0-D.
|
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 L2Loss<T> create (Scope scope, Operand<T> t)
Factory method to create a class wrapping a new L2Loss operation.
Parameters
scope | current scope |
---|---|
t | Typically 2-D, but may have any dimensions. |
Returns
- a new instance of L2Loss