Computes softmax cross entropy cost and gradients to backpropagate.

    features, labels, name=None

Inputs are the logits, not probabilities.


  • features: A Tensor. Must be one of the following types: half, bfloat16, float32, float64. batch_size x num_classes matrix
  • labels: A Tensor. Must have the same type as features. batch_size x num_classes matrix The caller must ensure that each batch of labels represents a valid probability distribution.
  • name: A name for the operation (optional).


A tuple of Tensor objects (loss, backprop).

  • loss: A Tensor. Has the same type as features.
  • backprop: A Tensor. Has the same type as features.