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

mp.tasks.vision.FaceDetectorOptions

View source on GitHub

Options for the face detector task.

mp.tasks.vision.FaceDetectorOptions(
 base_options: mp.tasks.BaseOptions ,
 running_mode: mp.tasks.vision.RunningMode = mp.tasks.vision.FaceDetectorOptions.running_mode ,
 min_detection_confidence: float = 0.5,
 min_suppression_threshold: float = 0.3,
 result_callback: Optional[Callable[[detections_module.DetectionResult, image_module.Image,
 int], None]] = None
)

Attributes

base_options Base options for the face detector task.
running_mode The running mode of the task. Default to the image mode. Face detector task has three running modes: 1) The image mode for detecting faces on single image inputs. 2) The video mode for detecting faces on the decoded frames of a video. 3) The live stream mode for detecting faces on a live stream of input data, such as from camera.
min_detection_confidence The minimum confidence score for the face detection to be considered successful.
min_suppression_threshold The minimum non-maximum-suppression threshold for face detection to be considered overlapped.
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_detection_confidence 0.5
min_suppression_threshold 0.3
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.