LogSoftmax

public final class LogSoftmax

Computes log softmax activations.

For each batch `i` and class `j` we have

logsoftmax[i, j] = logits[i, j] - log(sum(exp(logits[i])))

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> LogSoftmax<T>
create(Scope scope, Operand<T> logits)
Factory method to create a class wrapping a new LogSoftmax operation.
Output<T>
logsoftmax()
Same shape as `logits`.

Inherited Methods

Constants

public static final String OP_NAME

The name of this op, as known by TensorFlow core engine

Constant Value: "LogSoftmax"

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 LogSoftmax<T> create (Scope scope, Operand<T> logits)

Factory method to create a class wrapping a new LogSoftmax operation.

Parameters
scope current scope
logits 2-D with shape `[batch_size, num_classes]`.
Returns
  • a new instance of LogSoftmax

public Output<T> logsoftmax ()

Same shape as `logits`.