# tf.estimator.export.PredictOutput

<br />

|---|---|
| [![](https://www.tensorflow.org/images/tf_logo_32px.png) TensorFlow 2 version](https://www.tensorflow.org/api_docs/python/tf/estimator/export/PredictOutput) | [![](https://www.tensorflow.org/images/GitHub-Mark-32px.png) View source on GitHub](https://github.com/tensorflow/tensorflow/blob/v1.15.0/tensorflow/python/saved_model/model_utils/export_output.py#L202-L232) |

Represents the output of a generic prediction head.

Inherits From: [`ExportOutput`](https://www.tensorflow.org/versions/r1.15/api_docs/python/tf/estimator/export/ExportOutput)

#### View aliases


**Compat aliases for migration**

See
[Migration guide](https://www.tensorflow.org/guide/migrate) for
more details.

[`tf.compat.v1.estimator.export.PredictOutput`](https://www.tensorflow.org/api_docs/python/tf/estimator/export/PredictOutput), \`tf.compat.v2.estimator.export.PredictOutput\`

<br />

    tf.estimator.export.PredictOutput(
        outputs
    )

A generic prediction need not be either a classification or a regression.

Named outputs must be provided as a dict from string to `Tensor`,

<br />

<br />

<br />

| ## Args ||
|---|---|
| `outputs` | A `Tensor` or a dict of string to `Tensor` representing the predictions. |

<br />

<br />

<br />

<br />

| ## Raises ||
|---|---|
| `ValueError` | if the outputs is not dict, or any of its keys are not strings, or any of its values are not `Tensor`s. |

<br />

<br />

<br />

<br />

| ## Attributes ||
|---|---|
| `outputs` | <br /> <br /> |

<br />

## Methods

### `as_signature_def`

[View source](https://github.com/tensorflow/tensorflow/blob/v1.15.0/tensorflow/python/saved_model/model_utils/export_output.py#L230-L232)

    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.

<br />

<br />

<br />

| Args ||
|---|---|
| `receiver_tensors` | a `Tensor`, or a dict of string to `Tensor`, specifying input nodes that will be fed. |

<br />