Module: mp.tasks.vision

MediaPipe Tasks Vision API.

Modules

holistic_landmarker module: MediaPipe holistic landmarker task.

Classes

class FaceAligner : Class that performs face alignment on images.

class FaceAlignerOptions : Options for the face aligner task.

class FaceDetector : Class that performs face detection on images.

class FaceDetectorOptions : Options for the face detector task.

class FaceDetectorResult : Represents the list of detected objects.

class FaceLandmarker : Class that performs face landmarks detection on images.

class FaceLandmarkerOptions : Options for the face landmarker task.

class FaceLandmarkerResult : The face landmarks detection result from FaceLandmarker, where each vector element represents a single face detected in the image.

class FaceLandmarksConnections : The connections between face landmarks.

class FaceStylizer : Class that performs face stylization on images.

class FaceStylizerOptions : Options for the face stylizer task.

class GestureRecognizer : Class that performs gesture recognition on images.

class GestureRecognizerOptions : Options for the gesture recognizer task.

class GestureRecognizerResult : The gesture recognition result from GestureRecognizer, where each vector element represents a single hand detected in the image.

class HandLandmarker : Class that performs hand landmarks detection on images.

class HandLandmarkerOptions : Options for the hand landmarker task.

class HandLandmarkerResult : The hand landmarks result from HandLandmarker, where each vector element represents a single hand detected in the image.

class HandLandmarksConnections : The connections between hand landmarks.

class HolisticLandmarker : Class that performs holistic landmarks detection on images.

class HolisticLandmarkerOptions : Options for the holistic landmarker task.

class HolisticLandmarkerResult : The holistic landmarks result from HolisticLandmarker, where each vector element represents a single holistic detected in the image.

class ImageClassifier : Class that performs image classification on images.

class ImageClassifierOptions : Options for the image classifier task.

class ImageClassifierResult : Contains the classification results of a model.

class ImageEmbedder : Class that performs embedding extraction on images.

class ImageEmbedderOptions : Options for the image embedder task.

class ImageEmbedderResult : Embedding results for a given embedder model.

class ImageSegmenter : Class that performs image segmentation on images.

class ImageSegmenterOptions : Options for the image segmenter task.

class InteractiveSegmenter : Class that performs interactive segmentation on images.

class InteractiveSegmenterOptions : Options for the interactive segmenter task.

class InteractiveSegmenterRegionOfInterest : The Region-Of-Interest (ROI) to interact with.

class ObjectDetector : Class that performs object detection on images.

class ObjectDetectorOptions : Options for the object detector task.

class ObjectDetectorResult : Represents the list of detected objects.

class PoseLandmarker : Class that performs pose landmarks detection on images.

class PoseLandmarkerOptions : Options for the pose landmarker task.

class PoseLandmarkerResult : The pose landmarks detection result from PoseLandmarker, where each vector element represents a single pose detected in the image.

class PoseLandmarksConnections : The connections between pose landmarks.

class RunningMode : MediaPipe vision task running mode.