tf.keras.applications.convnext.decode_predictions

Decodes the prediction of an ImageNet model.

Compat aliases for migration

`tf.compat.v1.keras.applications.convnext.decode_predictions`

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

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

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

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

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. Some content is licensed under the numpy license.

Last updated 2023-10-06 UTC.

Args