Introducing Google AI Edge Portal: Benchmark Edge AI at scale. Sign-up to request access during private preview.

mp.tasks.vision.GestureRecognizerOptions

View source on GitHub

Options for the gesture recognizer task.

mp.tasks.vision.GestureRecognizerOptions(
 base_options: mp.tasks.BaseOptions ,
 running_mode: mp.tasks.vision.RunningMode = mp.tasks.vision.FaceDetectorOptions.running_mode ,
 num_hands: int = 1,
 min_hand_detection_confidence: float = 0.5,
 min_hand_presence_confidence: float = 0.5,
 min_tracking_confidence: float = 0.5,
 canned_gesture_classifier_options: mp.tasks.components.processors.ClassifierOptions = dataclasses.field(default_factory=_ClassifierOptions),
 custom_gesture_classifier_options: mp.tasks.components.processors.ClassifierOptions = dataclasses.field(default_factory=_ClassifierOptions),
 result_callback: Optional[Callable[[GestureRecognizerResult, image_module.Image, int], None]] = None
)

Attributes

base_options Base options for the hand gesture recognizer task.
running_mode The running mode of the task. Default to the image mode. Gesture recognizer task has three running modes: 1) The image mode for recognizing hand gestures on single image inputs. 2) The video mode for recognizing hand gestures on the decoded frames of a video. 3) The live stream mode for recognizing hand gestures on a live stream of input data, such as from camera.
num_hands The maximum number of hands can be detected by the recognizer.
min_hand_detection_confidence The minimum confidence score for the hand detection to be considered successful.
min_hand_presence_confidence The minimum confidence score of hand presence score in the hand landmark detection.
min_tracking_confidence The minimum confidence score for the hand tracking to be considered successful.
canned_gesture_classifier_options Options for configuring the canned gestures classifier, such as score threshold, allow list and deny list of gestures. The categories for canned gesture classifiers are: ["None", "Closed_Fist", "Open_Palm", "Pointing_Up", "Thumb_Down", "Thumb_Up", "Victory", "ILoveYou"]. Note this option is subject to change.
custom_gesture_classifier_options Options for configuring the custom gestures classifier, such as score threshold, allow list and deny list of gestures. Note this option is subject to change.
result_callback The user-defined result callback for processing live stream data. The result callback should only be specified when the running mode is set to the live stream mode.

Methods

__eq__

__eq__(
 other
)

Class Variables

min_hand_detection_confidence 0.5
min_hand_presence_confidence 0.5
min_tracking_confidence 0.5
num_hands 1
result_callback None
running_mode <VisionTaskRunningMode.IMAGE: 'IMAGE'>

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年05月01日 UTC.