tf.compat.v1.saved_model.regression_signature_def

Creates regression signature from given examples and predictions.

View aliases

Compat aliases for migration

tf.compat.v1.saved_model.signature_def_utils.regression_signature_def

tf.compat.v1.saved_model.regression_signature_def(
    examples, predictions
)

This function produces signatures intended for use with the TensorFlow Serving Regress API (tensorflow_serving/apis/prediction_service.proto), and so constrains the input and output types to those allowed by TensorFlow Serving.

Args
`examples`	A string `Tensor`, expected to accept serialized tf.Examples.
`predictions`	A float `Tensor`.

Returns
A regression-flavored signature_def.

Raises
`ValueError`	If examples is `None`.

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.

tf.compat.v1.saved_model.regression_signature_def

View aliases

Args

Returns

Raises