Computes softmax activations.
For each batch `i` and class `j` we have
$$softmax[i, j] = exp(logits[i, j]) / sum_j(exp(logits[i, j]))$$
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> Softmax<T> | |
Output<T> |
softmax()
Same shape as `logits`.
|
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 Softmax<T> create (Scope scope, Operand<T> logits)
Factory method to create a class wrapping a new Softmax operation.
Parameters
scope | current scope |
---|---|
logits | 2-D with shape `[batch_size, num_classes]`. |
Returns
- a new instance of Softmax