tf.estimator.export.ServingInputReceiver
Stay organized with collections
Save and categorize content based on your preferences.
A return type for a serving_input_receiver_fn.
tf.estimator.export.ServingInputReceiver(
features, receiver_tensors, receiver_tensors_alternatives=None
)
The expected return values are:
features: A Tensor, SparseTensor, or dict of string or int to Tensor
or SparseTensor, specifying the features to be passed to the model.
Note: if features passed is not a dict, it will be wrapped in a dict
with a single entry, using 'feature' as the key. Consequently, the model
must accept a feature dict of the form {'feature': tensor}. You may use
TensorServingInputReceiver if you want the tensor to be passed as is.
receiver_tensors: A Tensor, SparseTensor, or dict of string to Tensor
or SparseTensor, 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,
SparseTensor, or dict of string to Tensor orSparseTensor.
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.
Attributes |
|---|
features
|
|
receiver_tensors
|
|
receiver_tensors_alternatives
|
|
Except as otherwise noted, the content of this page is licensed under the Creative Commons Attribution 4.0 License, and code samples are licensed under the Apache 2.0 License. For details, see the Google Developers Site Policies. Java is a registered trademark of Oracle and/or its affiliates.
Last updated 2020-10-01 UTC.
[null,null,["Last updated 2020-10-01 UTC."],[],[],null,["# tf.estimator.export.ServingInputReceiver\n\n\u003cbr /\u003e\n\n|-----------------------------------------------------------------------------------|-------------------------------------------------------------------------------------------------------------------------------------|\n| [TensorFlow 2 version](/api_docs/python/tf/estimator/export/ServingInputReceiver) | [View source on GitHub](https://github.com/tensorflow/estimator/tree/master/tensorflow_estimator/python/estimator/export/export.py) |\n\nA return type for a serving_input_receiver_fn.\n\n#### View aliases\n\n\n**Compat aliases for migration**\n\nSee\n[Migration guide](https://www.tensorflow.org/guide/migrate) for\nmore details.\n\n[`tf.compat.v1.estimator.export.ServingInputReceiver`](/api_docs/python/tf/estimator/export/ServingInputReceiver), \\`tf.compat.v2.estimator.export.ServingInputReceiver\\`\n\n\u003cbr /\u003e\n\n tf.estimator.export.ServingInputReceiver(\n features, receiver_tensors, receiver_tensors_alternatives=None\n )\n\nThe expected return values are:\nfeatures: A `Tensor`, `SparseTensor`, or dict of string or int to `Tensor`\nor `SparseTensor`, specifying the features to be passed to the model.\nNote: if `features` passed is not a dict, it will be wrapped in a dict\nwith a single entry, using 'feature' as the key. Consequently, the model\nmust accept a feature dict of the form {'feature': tensor}. You may use\n`TensorServingInputReceiver` if you want the tensor to be passed as is.\nreceiver_tensors: A `Tensor`, `SparseTensor`, or dict of string to `Tensor`\nor `SparseTensor`, specifying input nodes where this receiver expects to\nbe fed by default. Typically, this is a single placeholder expecting\nserialized `tf.Example` protos.\nreceiver_tensors_alternatives: a dict of string to additional\ngroups of receiver tensors, each of which may be a `Tensor`,\n`SparseTensor`, or dict of string to `Tensor` or`SparseTensor`.\nThese named receiver tensor alternatives generate additional serving\nsignatures, which may be used to feed inputs at different points within\nthe input receiver subgraph. A typical usage is to allow feeding raw\nfeature `Tensor`s *downstream* of the tf.parse_example() op.\nDefaults to None.\n\n\u003cbr /\u003e\n\n\u003cbr /\u003e\n\n\u003cbr /\u003e\n\n| Attributes ---------- ||\n|---------------------------------|---------------|\n| `features` | \u003cbr /\u003e \u003cbr /\u003e |\n| `receiver_tensors` | \u003cbr /\u003e \u003cbr /\u003e |\n| `receiver_tensors_alternatives` | \u003cbr /\u003e \u003cbr /\u003e |\n\n\u003cbr /\u003e"]]
TensorFlow 2 version
View source on GitHub