tf.contrib.layers.softmax( logits, scope=None )
Performs softmax on Nth dimension of N-dimensional logit tensor.
For two-dimensional logits this reduces to tf.nn.softmax. The N-th dimension needs to have a specified number of elements (number of classes).
Tensorwith logits, where N > 1.
scope: Optional scope for variable_scope.
Tensor with same shape and type as logits.