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

mediapipe_model_maker.image_classifier.ModelOptions

Configurable options for image classifier model.

mediapipe_model_maker.image_classifier.ModelOptions(
    dropout_rate: float = 0.2, alpha: float = 0.75
)

Attributes
`dropout_rate`	The fraction of the input units to drop, used in dropout layer.
`alpha`	Float, larger than zero, controls the width of the network, Only used in `mobilenet_v2_keras_spec` model spec.

Methods

__eq__(
    other
)

Class Variables
alpha	`0.75`
dropout_rate	`0.2`

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.