mediapipe_model_maker.gesture_recognizer.ModelOptions
Stay organized with collections
Save and categorize content based on your preferences.
Configurable options for gesture recognizer model.
mediapipe_model_maker.gesture_recognizer.ModelOptions(
dropout_rate: float = 0.05,
layer_widths: List[int] = dataclasses.field(default_factory=list)
)
Attributes |
dropout_rate
|
The fraction of the input units to drop, used in dropout
layer.
|
layer_widths
|
A list of hidden layer widths for the gesture model. Each
element in the list will create a new hidden layer with the specified
width. The hidden layers are separated with BatchNorm, Dropout, and ReLU.
Defaults to an empty list(no hidden layers).
|
Methods
__eq__
__eq__(
other
)
Class Variables |
|
dropout_rate
|
0.05
|
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 2026-05-28 UTC.
[null,null,["Last updated 2026-05-28 UTC."],[],[]]