# tf.keras.applications.resnet50.decode_predictions

<br />

|---|
| [![](https://www.tensorflow.org/images/GitHub-Mark-32px.png) View source on GitHub](https://github.com/keras-team/keras/tree/v2.14.0/keras/applications/resnet.py#L616-L621) |

Decodes the prediction of an ImageNet model.

#### View aliases


**Main aliases**

[`tf.keras.applications.resnet.decode_predictions`](https://www.tensorflow.org/api_docs/python/tf/keras/applications/resnet50/decode_predictions)

<br />

    tf.keras.applications.resnet50.decode_predictions(
        preds, top=5
    )

<br />

<br />

<br />

| ## Args ||
|---|---|
| `preds` | Numpy array encoding a batch of predictions. |
| `top` | Integer, how many top-guesses to return. Defaults to 5. |

<br />

<br />

<br />

<br />

| ## Returns ||
|---|---|
| A list of lists of top class prediction tuples `(class_name, class_description, score)`. One list of tuples per sample in batch input. ||

<br />

<br />

<br />

<br />

| ## Raises ||
|---|---|
| `ValueError` | In case of invalid shape of the `pred` array (must be 2D). |

<br />