tf.raw_ops.SparseSoftmaxCrossEntropyWithLogits

Computes softmax cross entropy cost and gradients to backpropagate.

tf.raw_ops.SparseSoftmaxCrossEntropyWithLogits(
    features, labels, name=None
)

Unlike SoftmaxCrossEntropyWithLogits, this operation does not accept a matrix of label probabilities, but rather a single label per row of features. This label is considered to have probability 1.0 for the given row.

Inputs are the logits, not probabilities.

Args:

  • features: A Tensor. Must be one of the following types: half, bfloat16, float32, float64. batch_size x num_classes matrix
  • labels: A Tensor. Must be one of the following types: int32, int64. batch_size vector with values in [0, num_classes). This is the label for the given minibatch entry.
  • name: A name for the operation (optional).

Returns:

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.