Google I/O returns May 18-20! Reserve space and build your schedule Register now


View source on GitHub

Computes log softmax activations.

For each batch i and class j we have

logsoftmax = logits - log(reduce_sum(exp(logits), axis))

logits A non-empty Tensor. Must be one of the following types: half, float32, float64.
axis The dimension softmax would be performed on. The default is -1 which indicates the last dimension.
name A name for the operation (optional).

A Tensor. Has the same type as logits. Same shape as logits.

InvalidArgumentError if logits is empty or axis is beyond the last dimension of logits.