GitHub

tfma.load_eval_result

Loads EvalResult object for use with the visualization functions.

tfma.load_eval_result(
    output_path: str,
    output_file_format: Optional[str] = 'tfrecord',
    model_name: Optional[str] = None
) -> tfma.EvalResult

Used in the notebooks

Used in the tutorials
FaceSSD Fairness Indicators Example Colab Introduction to Fairness Indicators TensorFlow Constrained Optimization Example Using CelebA Dataset Wiki Talk Comments Toxicity Prediction Fairness Indicators on TF-Hub Text Embeddings

Args
`output_path`	Output directory containing config, metrics, plots, etc.
`output_file_format`	Optional file extension to filter files by.
`model_name`	Optional model name. Required if multi-model evaluation was run.

Returns
EvalResult object for use with the visualization functions.

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 2022-12-14 UTC.

tfma.load_eval_result

Used in the notebooks

Args

Returns