tf.estimator.export.ServingInputReceiver

Class ServingInputReceiver

Defined in tensorflow/python/estimator/export/export.py.

A return type for a serving_input_receiver_fn.

The expected return values are: features: A Tensor, SparseTensor, or dict of string to Tensor or SparseTensor, specifying the features to be passed to the model. receiver_tensors: a Tensor, or a dict of string to Tensor, specifying input nodes where this receiver expects to be fed by default. Typically, this is a single placeholder expecting serialized tf.Example protos. receiver_tensors_alternatives: a dict of string to additional groups of receiver tensors, each of which may be a Tensor or a dict of string to Tensor. These named receiver tensor alternatives generate additional serving signatures, which may be used to feed inputs at different points within the input receiver subgraph. A typical usage is to allow feeding raw feature Tensors downstream of the tf.parse_example() op. Defaults to None.

Properties

features

Alias for field number 0

receiver_tensors

Alias for field number 1

receiver_tensors_alternatives

Alias for field number 2

Methods

__new__

@staticmethod
__new__(
    cls,
    features,
    receiver_tensors,
    receiver_tensors_alternatives=None
)

Create new instance of ServingInputReceiver(features, receiver_tensors, receiver_tensors_alternatives)