Class ClassificationOutput
Inherits From: ExportOutput
Represents the output of a classification head.
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.
__init__
__init__(
scores=None,
classes=None
)
Constructor for ClassificationOutput
.
Args:
scores
: A floatTensor
giving scores (sometimes but not always interpretable as probabilities) for each class. May beNone
, but only ifclasses
is set. Interpretation varies-- see class doc.classes
: A stringTensor
giving predicted class labels. May beNone
, but only ifscores
is set. Interpretation varies-- see class doc.
Raises:
ValueError
: if neither classes nor scores is set, or one of them is not aTensor
with the correct dtype.
Properties
classes
scores
Methods
tf.estimator.export.ClassificationOutput.as_signature_def
as_signature_def(receiver_tensors)
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.
Args:
receiver_tensors
: aTensor
, or a dict of string toTensor
, specifying input nodes that will be fed.