tf.contrib.layers.softmax

View source on GitHub

Performs softmax on Nth dimension of N-dimensional logit tensor.

tf.contrib.layers.softmax(
    logits,
    scope=None
)

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).

Args:

• logits: N-dimensional Tensor with logits, where N > 1.
• scope: Optional scope for variable_scope.

Returns:

A Tensor with same shape and type as logits.