View source on GitHub
|
A structure that holds the output of a tff.learning.models.VariableModel.
tff.learning.models.BatchOutput(
loss=None, predictions=None, num_examples=None
)
Used in the notebooks
| Used in the tutorials |
|---|
tff.learning.models.BatchOutput
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 2024-09-20 UTC.
[null,null,["Last updated 2024-09-20 UTC."],[],[],null,["# tff.learning.models.BatchOutput\n\n\u003cbr /\u003e\n\n|-------------------------------------------------------------------------------------------------------------------------------------------------------------|\n| [View source on GitHub](https://github.com/tensorflow/federated/blob/v0.87.0 Version 2.0, January 2004 Licensed under the Apache License, Version 2.0 (the) |\n\nA structure that holds the output of a [`tff.learning.models.VariableModel`](../../../tff/learning/models/VariableModel). \n\n tff.learning.models.BatchOutput(\n loss=None, predictions=None, num_examples=None\n )\n\n### Used in the notebooks\n\n| Used in the tutorials |\n|---------------------------------------------------------------------------------------------------------------------------------------------|\n| - [Federated Learning for Image Classification](https://www.tensorflow.org/federated/tutorials/federated_learning_for_image_classification) |\n\n| **Note:** All fields are optional (may be None).\n\n\u003cbr /\u003e\n\n\u003cbr /\u003e\n\n\u003cbr /\u003e\n\n| Attributes ---------- ||\n|----------------|----------------------------------------------------------------------------------------------------------------------------------|\n| `loss` | The scalar mean loss on the examples in the batch. If the model has multiple losses, it is the sum of all the individual losses. |\n| `predictions` | Tensor of predictions on the examples. The first dimension must be the same size (the size of the batch). |\n| `num_examples` | Number of examples seen in the batch. |\n\n\u003cbr /\u003e"]]