Introducing LiteRT: Google's high-performance runtime for on-device AI, formerly known as TensorFlow Lite. Learn more

mediapipe_model_maker.object_detector.ObjectDetectorOptions

View source on GitHub

Configurable options for building object detector.

mediapipe_model_maker.object_detector.ObjectDetectorOptions(
    supported_model: mediapipe_model_maker.object_detector.SupportedModels,
    model_options: Optional[mediapipe_model_maker.object_detector.ModelOptions] = None,
    hparams: Optional[mediapipe_model_maker.object_detector.HParams] = None
)

Attributes
`supported_model`	A model from the SupportedModels enum.
`model_options`	A set of options for configuring the selected model.
`hparams`	A set of hyperparameters used to train the object detector.

Methods

`eq`

__eq__(
    other
)

Class Variables
hparams	`None`
model_options	`None`

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 2024-05-07 UTC.

mediapipe_model_maker.object_detector.ObjectDetectorOptions

Attributes

Methods

__eq__

Class Variables

`eq`