tf.compat.v1.data.get_output_shapes | TensorFlow v2.16.1 (original) (raw)
tf.compat.v1.data.get_output_shapes
Stay organized with collections Save and categorize content based on your preferences.
Returns the output shapes for elements of the input dataset / iterator.
tf.compat.v1.data.get_output_shapes(
dataset_or_iterator
)
Migrate to TF2
This is a legacy API for inspecting the type signature of dataset elements. In TF 2, you should use the tf.data.Dataset.element_spec attribute instead.
Description
Args | |
---|---|
dataset_or_iterator | A tf.data.Dataset or tf.data.Iterator. |
Returns |
---|
A (nested) structure of tf.TensorShape objects matching the structure of the dataset / iterator elements and specifying the shape of the individual components. |
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 2024-04-26 UTC.