TensorFlow 1 version View source on GitHub

Represents the output of a classification head.

Inherits From: ExportOutput

    scores=None, classes=None

Either classes or scores or both must be set.

The classes Tensor must provide string labels, not integer class IDs.

If only classes is set, it is interpreted as providing top-k results in descending order.

If only scores is set, it is interpreted as providing a score for every class in order of class ID.

If both classes and scores are set, they are interpreted as zipped, so each score corresponds to the class at the same index. Clients should not depend on the order of the entries.


  • scores: A float Tensor giving scores (sometimes but not always interpretable as probabilities) for each class. May be None, but only if classes is set. Interpretation varies-- see class doc.
  • classes: A string Tensor giving predicted class labels. May be None, but only if scores is set. Interpretation varies-- see class doc.


  • classes
  • scores


  • ValueError: if neither classes nor scores is set, or one of them is not a Tensor with the correct dtype.



View source


Generate a SignatureDef proto for inclusion in a MetaGraphDef.

The SignatureDef will specify outputs as described in this ExportOutput, and will use the provided receiver_tensors as inputs.


  • receiver_tensors: a Tensor, or a dict of string to Tensor, specifying input nodes that will be fed.