LogSoftmax

tensorflow C++ API

tensorflow::ops::LogSoftmax

Computes log softmax activations.

Summary

For each batchiand classjwe have

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

Arguments:

• scope: A Scopeobject
• logits: 2-D with shape[batch_size, num_classes].

Returns:

• Output: Same shape aslogits.

LogSoftmax block

Source link : https://github.com/EXPNUNI/enuSpaceTensorflow/blob/master/enuSpaceTensorflow/tf_nn.cpp

Argument:

• Scope scope : A Scope object (A scope is generated automatically each page. A scope is not connected.)
• Input logits: connect Input node.

Return:

• Output output: Output object of LRN class object.

Result:

• std::vector(Tensor) result_output : Returned object of executed result by calling session.

Using Method