T
- data type for softmax()
output@Operator(group="nn") public final class Softmax<T extends Number> extends PrimitiveOp implements Operand<T>
For each batch `i` and class `j` we have
$$softmax[i, j] = exp(logits[i, j]) / sum_j(exp(logits[i, j]))$$
operation
Modifier and Type | Method and Description |
---|---|
Output<T> |
asOutput()
Returns the symbolic handle of a tensor.
|
static <T extends Number> |
create(Scope scope,
Operand<T> logits)
Factory method to create a class wrapping a new Softmax operation.
|
Output<T> |
softmax()
Same shape as `logits`.
|
equals, hashCode, op, toString
public static <T extends Number> Softmax<T> create(Scope scope, Operand<T> logits)
scope
- current scopelogits
- 2-D with shape `[batch_size, num_classes]`.public Output<T> asOutput()
Operand
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.
asOutput
in interface Operand<T extends Number>
OperationBuilder.addInput(Output)
Copyright © 2022. All rights reserved.