# Classes The following declarations are available globally. - ` ### [AudioPart](https://developers.google.com/edge/api/mediapipe/swift/vision/Classes/AudioPart.md.txt) ` Audio part representing the audio content block of a multi-modal block. #### Declaration Swift class AudioPart: TaskPart - ` ### [BaseOptions](https://developers.google.com/edge/api/mediapipe/swift/vision/Classes/BaseOptions.md.txt) ` Holds the base options that is used for creation of any type of task. It has fields with important information acceleration configuration, TFLite model source etc. #### Declaration Swift class BaseOptions: NSObject, NSCopying - ` ### [ClassificationResult](https://developers.google.com/edge/api/mediapipe/swift/vision/Classes/ClassificationResult.md.txt) ` Represents the classification results of a model. Typically used as a result for classification tasks. #### Declaration Swift class ClassificationResult: NSObject - ` ### [Classifications](https://developers.google.com/edge/api/mediapipe/swift/vision/Classes/Classifications.md.txt) ` Represents the list of classification for a given classifier head. Typically used as a result for classification tasks. #### Declaration Swift class Classifications: NSObject - ` ### [ClassifierOptions](https://developers.google.com/edge/api/mediapipe/swift/vision/Classes/ClassifierOptions.md.txt) ` Classifier options shared across MediaPipe iOS classification tasks. #### Declaration Swift class ClassifierOptions: NSObject, NSCopying - ` ### [Connection](https://developers.google.com/edge/api/mediapipe/swift/vision/Classes/Connection.md.txt) ` The value class representing a landmark connection. #### Declaration Swift class Connection: NSObject - ` ### [Detection](https://developers.google.com/edge/api/mediapipe/swift/vision/Classes/Detection.md.txt) ` Represents one detected object in the results of `ObjectDetector`. #### Declaration Swift class Detection: NSObject - ` ### [Embedding](https://developers.google.com/edge/api/mediapipe/swift/vision/Classes/Embedding.md.txt) ` Represents the embedding for a given embedder head. Typically used in embedding tasks. One and only one of the two 'floatEmbedding' and 'quantizedEmbedding' will contain data, based on whether or not the embedder was configured to perform scala quantization. #### Declaration Swift class Embedding: NSObject - ` ### [EmbeddingResult](https://developers.google.com/edge/api/mediapipe/swift/vision/Classes/EmbeddingResult.md.txt) ` Represents the embedding results of a model. Typically used as a result for embedding tasks. #### Declaration Swift class EmbeddingResult: NSObject - ` ### [FaceDetector](https://developers.google.com/edge/api/mediapipe/swift/vision/Classes/FaceDetector.md.txt) ` Class that performs face detection on images. The API expects a TFLite model with mandatory TFLite Model Metadata. The API supports models with one image input tensor and one or more output tensors. To be more specific, here are the requirements: Input tensor (kTfLiteUInt8/kTfLiteFloat32) - image input of size `[batch x height x width x channels]`. - batch inference is not supported (`batch` is required to be 1). - only RGB inputs are supported (`channels` is required to be 3). - if type is kTfLiteFloat32, NormalizationOptions are required to be attached to the metadata for input normalization. Output tensors must be the 4 outputs of a `DetectionPostProcess` op, i.e:(kTfLiteFloat32) (kTfLiteUInt8/kTfLiteFloat32) - locations tensor of size `[num_results x 4]`, the inner array representing bounding boxes in the form \[top, left, right, bottom\]. - BoundingBoxProperties are required to be attached to the metadata and must specify type=BOUNDARIES and coordinate_type=RATIO. (kTfLiteFloat32) - classes tensor of size `[num_results]`, each value representing the integer index of a class. - scores tensor of size `[num_results]`, each value representing the score of the detected face. - optional score calibration can be attached using ScoreCalibrationOptions and an AssociatedFile with type TENSOR_AXIS_SCORE_CALIBRATION. See metadata_schema.fbs \[1\] for more details. (kTfLiteFloat32) - integer num_results as a tensor of size `[1]` #### Declaration Swift class FaceDetector: NSObject - ` ### [FaceDetectorOptions](https://developers.google.com/edge/api/mediapipe/swift/vision/Classes/FaceDetectorOptions.md.txt) ` Options for setting up a `FaceDetector`. #### Declaration Swift class FaceDetectorOptions: TaskOptions, NSCopying - ` ### [FaceDetectorResult](https://developers.google.com/edge/api/mediapipe/swift/vision/Classes/FaceDetectorResult.md.txt) ` Represents the detection results generated by `FaceDetector`. #### Declaration Swift class FaceDetectorResult: TaskResult, NSCopying - ` ### [FaceLandmarker](https://developers.google.com/edge/api/mediapipe/swift/vision/Classes/FaceLandmarker.md.txt) ` Class that performs face landmark detection on images. The API expects a TFLite model with mandatory TFLite Model Metadata. #### Declaration Swift class FaceLandmarker: NSObject - ` ### [FaceLandmarkerOptions](https://developers.google.com/edge/api/mediapipe/swift/vision/Classes/FaceLandmarkerOptions.md.txt) ` Options for setting up a `FaceLandmarker`. #### Declaration Swift class FaceLandmarkerOptions: TaskOptions, NSCopying - ` ### [FaceLandmarkerResult](https://developers.google.com/edge/api/mediapipe/swift/vision/Classes/FaceLandmarkerResult.md.txt) ` Represents the detection results generated by `FaceLandmarker`. #### Declaration Swift class FaceLandmarkerResult: TaskResult, NSCopying - ` ### [GestureRecognizer](https://developers.google.com/edge/api/mediapipe/swift/vision/Classes/GestureRecognizer.md.txt) ` Performs gesture recognition on images. This API expects a pre-trained TFLite hand gesture recognizer model or a custom one created using MediaPipe Solutions Model Maker. See https://developers.google.com/mediapipe/solutions/model_maker. #### Declaration Swift class GestureRecognizer: NSObject - ` ### [GestureRecognizerOptions](https://developers.google.com/edge/api/mediapipe/swift/vision/Classes/GestureRecognizerOptions.md.txt) ` Options for setting up a `GestureRecognizer`. #### Declaration Swift class GestureRecognizerOptions: TaskOptions, NSCopying - ` ### [GestureRecognizerResult](https://developers.google.com/edge/api/mediapipe/swift/vision/Classes/GestureRecognizerResult.md.txt) ` Represents the gesture recognition results generated by `GestureRecognizer`. #### Declaration Swift class GestureRecognizerResult: TaskResult, NSCopying - ` ### [HandLandmarker](https://developers.google.com/edge/api/mediapipe/swift/vision/Classes/HandLandmarker.md.txt) ` Performs hand landmarks detection on images. This API expects a pre-trained hand landmarks model asset bundle. #### Declaration Swift class HandLandmarker: NSObject - ` ### [HandLandmarkerOptions](https://developers.google.com/edge/api/mediapipe/swift/vision/Classes/HandLandmarkerOptions.md.txt) ` Options for setting up a `HandLandmarker`. #### Declaration Swift class HandLandmarkerOptions: TaskOptions, NSCopying - ` ### [HandLandmarkerResult](https://developers.google.com/edge/api/mediapipe/swift/vision/Classes/HandLandmarkerResult.md.txt) ` Represents the hand landmarker results generated by `HandLandmarker`. #### Declaration Swift class HandLandmarkerResult: TaskResult, NSCopying - ` ### [HolisticLandmarker](https://developers.google.com/edge/api/mediapipe/swift/vision/Classes/HolisticLandmarker.md.txt) ` Performs holistic landmarks detection on images. This API expects a pre-trained holistic landmarks model asset bundle. #### Declaration Swift class HolisticLandmarker: NSObject - ` ### [HolisticLandmarkerOptions](https://developers.google.com/edge/api/mediapipe/swift/vision/Classes/HolisticLandmarkerOptions.md.txt) ` Options for setting up a `HolisticLandmarker`. #### Declaration Swift class HolisticLandmarkerOptions: TaskOptions, NSCopying - ` ### [HolisticLandmarkerResult](https://developers.google.com/edge/api/mediapipe/swift/vision/Classes/HolisticLandmarkerResult.md.txt) ` Represents holistic landmarks detection results generated by `HolisticLandmarker`. #### Declaration Swift class HolisticLandmarkerResult: TaskResult, NSCopying - ` ### [ImageClassifier](https://developers.google.com/edge/api/mediapipe/swift/vision/Classes/ImageClassifier.md.txt) ` Performs classification on images. The API expects a TFLite model with optional, but strongly recommended, \[TFLite Model Metadata.\](https://www.tensorflow.org/lite/convert/metadata"). The API supports models with one image input tensor and one or more output tensors. To be more specific, here are the requirements. Input tensor (kTfLiteUInt8/kTfLiteFloat32) - image input of size `[batch x height x width x channels]`. - batch inference is not supported (`batch` is required to be 1). - only RGB inputs are supported (`channels` is required to be 3). - if type is kTfLiteFloat32, NormalizationOptions are required to be attached to the metadata for input normalization. At least one output tensor with: (kTfLiteUInt8/kTfLiteFloat32) - `N `classes and either 2 or 4 dimensions, i.e. `[1 x N]` or `[1 x 1 x 1 x N]` - optional (but recommended) label map(s) as AssociatedFiles with type TENSOR_AXIS_LABELS, containing one label per line. The first such AssociatedFile (if any) is used to fill the `class_name` field of the results. The `display_name` field is filled from the AssociatedFile (if any) whose locale matches the `display_names_locale` field of the `ImageClassifierOptions` used at creation time ("en" by default, i.e. English). If none of these are available, only the `index` field of the results will be filled. - optional score calibration can be attached using ScoreCalibrationOptions and an AssociatedFile with type TENSOR_AXIS_SCORE_CALIBRATION. See metadata_schema.fbs \[1\] for more details. #### Declaration Swift class ImageClassifier: NSObject - ` ### [ImageClassifierOptions](https://developers.google.com/edge/api/mediapipe/swift/vision/Classes/ImageClassifierOptions.md.txt) ` Options for setting up a `ImageClassifier`. #### Declaration Swift class ImageClassifierOptions: TaskOptions, NSCopying - ` ### [ImageClassifierResult](https://developers.google.com/edge/api/mediapipe/swift/vision/Classes/ImageClassifierResult.md.txt) ` Represents the classification results generated by `ImageClassifier`. \* #### Declaration Swift class ImageClassifierResult: TaskResult, NSCopying - ` ### [ImageEmbedder](https://developers.google.com/edge/api/mediapipe/swift/vision/Classes/ImageEmbedder.md.txt) ` Performs embedding extraction on images. The API expects a TFLite model with optional, but strongly recommended, \[TFLite Model Metadata.\](https://www.tensorflow.org/lite/convert/metadata"). The API supports models with one image input tensor and one or more output tensors. To be more specific, here are the requirements. Input image tensor (kTfLiteUInt8/kTfLiteFloat32) - image input of size `[batch x height x width x channels]`. - batch inference is not supported (`batch` is required to be 1). - only RGB inputs are supported (`channels` is required to be 3). - if type is kTfLiteFloat32, NormalizationOptions are required to be attached to the metadata for input normalization. At least one output tensor (kTfLiteUInt8/kTfLiteFloat32) with shape `[1 x N]` where N is the number of dimensions in the produced embeddings. #### Declaration Swift class ImageEmbedder: NSObject, EmbeddingProvider - ` ### [ImageEmbedderOptions](https://developers.google.com/edge/api/mediapipe/swift/vision/Classes/ImageEmbedderOptions.md.txt) ` Options for setting up a `ImageEmbedder`. #### Declaration Swift class ImageEmbedderOptions: TaskOptions, NSCopying - ` ### [ImageEmbedderResult](https://developers.google.com/edge/api/mediapipe/swift/vision/Classes/ImageEmbedderResult.md.txt) ` Represents the embedding results generated by `ImageEmbedder`. \* #### Declaration Swift class ImageEmbedderResult: TaskResult, NSCopying - ` ### [ImagePart](https://developers.google.com/edge/api/mediapipe/swift/vision/Classes/ImagePart.md.txt) ` Image part representing the image content block of a multi-modal block. #### Declaration Swift class ImagePart: TaskPart - ` ### [ImageSegmenter](https://developers.google.com/edge/api/mediapipe/swift/vision/Classes/ImageSegmenter.md.txt) ` Class that performs segmentation on images. The API expects a TFLite model with mandatory TFLite Model Metadata. #### Declaration Swift class ImageSegmenter: NSObject - ` ### [ImageSegmenterOptions](https://developers.google.com/edge/api/mediapipe/swift/vision/Classes/ImageSegmenterOptions.md.txt) ` Options for setting up a `ImageSegmenter`. #### Declaration Swift class ImageSegmenterOptions: TaskOptions, NSCopying - ` ### [ImageSegmenterResult](https://developers.google.com/edge/api/mediapipe/swift/vision/Classes/ImageSegmenterResult.md.txt) ` Represents the segmentation results generated by `ImageSegmenter`. #### Declaration Swift class ImageSegmenterResult: TaskResult, NSCopying - ` ### [InteractiveSegmenter](https://developers.google.com/edge/api/mediapipe/swift/vision/Classes/InteractiveSegmenter.md.txt) ` Class that performs interactive segmentation on images using split mode. This API optimizes performance by splitting the model into an encoder (feature extraction that runs once per image) and a decoder (lightweight heatmap generation that runs per user stroke). #### Declaration Swift class InteractiveSegmenter: NSObject - ` ### [InteractiveSegmenterLegacy](https://developers.google.com/edge/api/mediapipe/swift/vision/Classes/InteractiveSegmenterLegacy.md.txt) ` Class that performs interactive segmentation on images. Users can represent user interaction through `RegionOfInterest`, which gives a hint to `InteractiveSegmenterLegacy` to perform segmentation focusing on the given region of interest. The API expects a TFLite model with mandatory TFLite Model Metadata. Input tensor: (kTfLiteUInt8/kTfLiteFloat32) - image input of size `[batch x height x width x channels]`. - batch inference is not supported (`batch` is required to be 1). - RGB and greyscale inputs are supported (`channels` is required to be 1 or 3). - if type is kTfLiteFloat32, NormalizationOptions are required to be attached to the metadata for input normalization. Output tensors: (kTfLiteUInt8/kTfLiteFloat32) - list of segmented masks. - if `output_type` is CATEGORY_MASK, uint8 Image, Image vector of size 1. - if `output_type` is CONFIDENCE_MASK, float32 Image list of size `channels`. - batch is always 1. An example of such model can be found at: https://tfhub.dev/tensorflow/lite-model/deeplabv3/1/metadata/2 #### Declaration Swift class InteractiveSegmenterLegacy: NSObject - ` ### [InteractiveSegmenterLegacyOptions](https://developers.google.com/edge/api/mediapipe/swift/vision/Classes/InteractiveSegmenterLegacyOptions.md.txt) ` Options for setting up a `InteractiveSegmenterLegacy`. #### Declaration Swift class InteractiveSegmenterLegacyOptions: TaskOptions, NSCopying - ` ### [InteractiveSegmenterLegacyResult](https://developers.google.com/edge/api/mediapipe/swift/vision/Classes/InteractiveSegmenterLegacyResult.md.txt) ` Represents the segmentation results generated by `ImageSegmenter`. #### Declaration Swift class InteractiveSegmenterLegacyResult: TaskResult, NSCopying - ` ### [InteractiveSegmenterOptions](https://developers.google.com/edge/api/mediapipe/swift/vision/Classes/InteractiveSegmenterOptions.md.txt) ` Options for setting up a `InteractiveSegmenter`. #### Declaration Swift class InteractiveSegmenterOptions: TaskOptions, NSCopying - ` ### [Landmark](https://developers.google.com/edge/api/mediapipe/swift/vision/Classes/Landmark.md.txt) ` Landmark represents a point in 3D space with x, y, z coordinates. The landmark coordinates are in meters. z represents the landmark depth, and the smaller the value the closer the world landmark is to the camera. #### Declaration Swift class Landmark: NSObject - ` ### [MPImage](https://developers.google.com/edge/api/mediapipe/swift/vision/Classes/MPImage.md.txt) ` An image used in on-device machine learning using MediaPipe Task library. #### Declaration Swift class MPImage: NSObject - ` ### [Mask](https://developers.google.com/edge/api/mediapipe/swift/vision/Classes/Mask.md.txt) ` The wrapper class for MediaPipe segmentation masks. Masks are stored as `UInt8 *` or `float *` objects. Every mask has an underlying type which can be accessed using `dataType`. You can access the mask as any other type using the appropriate properties. For example, if the underlying type is `uInt8`, in addition to accessing the mask using `uint8Data`, you can access `float32Data` to get the 32 bit float data (with values ranging from 0.0 to 1.0). The first time you access the data as a type different from the underlying type, an expensive type conversion is performed. Subsequent accesses return a pointer to the memory location for the same type converted array. As type conversions can be expensive, it is recommended to limit the accesses to data of types different from the underlying type. Masks that are returned from a MediaPipe Tasks are owned by by the underlying C++ Task. If you need to extend the lifetime of these objects, you can invoke the `copy()` method. #### Declaration Swift class Mask: NSObject, NSCopying - ` ### [NormalizedKeypoint](https://developers.google.com/edge/api/mediapipe/swift/vision/Classes/NormalizedKeypoint.md.txt) ` Normalized keypoint represents a point in 2D space with x, y coordinates. x and y are normalized to \[0.0, 1.0\] by the image width and height respectively. #### Declaration Swift class NormalizedKeypoint: NSObject - ` ### [NormalizedLandmark](https://developers.google.com/edge/api/mediapipe/swift/vision/Classes/NormalizedLandmark.md.txt) ` Normalized Landmark represents a point in 3D space with x, y, z coordinates. x and y are normalized to \[0.0, 1.0\] by the image width and height respectively. z represents the landmark depth, and the smaller the value the closer the landmark is to the camera. The magnitude of z uses roughly the same scale as x. #### Declaration Swift class NormalizedLandmark: NSObject - ` ### [ObjectDetector](https://developers.google.com/edge/api/mediapipe/swift/vision/Classes/ObjectDetector.md.txt) ` Class that performs object detection on images. The API expects a TFLite model with mandatory TFLite Model Metadata. The API supports models with one image input tensor and one or more output tensors. To be more specific, here are the requirements: Input tensor (kTfLiteUInt8/kTfLiteFloat32) - image input of size `[batch x height x width x channels]`. - batch inference is not supported (`batch` is required to be 1). - only RGB inputs are supported (`channels` is required to be 3). - if type is kTfLiteFloat32, NormalizationOptions are required to be attached to the metadata for input normalization. Output tensors must be the 4 outputs of a `DetectionPostProcess` op, i.e:(kTfLiteFloat32) (kTfLiteUInt8/kTfLiteFloat32) - locations tensor of size `[num_results x 4]`, the inner array representing bounding boxes in the form \[top, left, right, bottom\]. - BoundingBoxProperties are required to be attached to the metadata and must specify type=BOUNDARIES and coordinate_type=RATIO. (kTfLiteFloat32) - classes tensor of size `[num_results]`, each value representing the integer index of a class. - optional (but recommended) label map(s) can be attached as AssociatedFiles with type TENSOR_VALUE_LABELS, containing one label per line. The first such AssociatedFile (if any) is used to fill the `class_name` field of the results. The `display_name` field is filled from the AssociatedFile (if any) whose locale matches the `display_names_locale` field of the `ObjectDetectorOptions` used at creation time ("en" by default, i.e. English). If none of these are available, only the `index` field of the results will be filled. (kTfLiteFloat32) - scores tensor of size `[num_results]`, each value representing the score of the detected object. - optional score calibration can be attached using ScoreCalibrationOptions and an AssociatedFile with type TENSOR_AXIS_SCORE_CALIBRATION. See metadata_schema.fbs \[1\] for more details. (kTfLiteFloat32) - integer num_results as a tensor of size `[1]` #### Declaration Swift class ObjectDetector: NSObject - ` ### [ObjectDetectorOptions](https://developers.google.com/edge/api/mediapipe/swift/vision/Classes/ObjectDetectorOptions.md.txt) ` Options for setting up a `ObjectDetector`. #### Declaration Swift class ObjectDetectorOptions: TaskOptions, NSCopying - ` ### [ObjectDetectorResult](https://developers.google.com/edge/api/mediapipe/swift/vision/Classes/ObjectDetectorResult.md.txt) ` Represents the detection results generated by `ObjectDetector`. #### Declaration Swift class ObjectDetectorResult: TaskResult, NSCopying - ` ### [PoseLandmarker](https://developers.google.com/edge/api/mediapipe/swift/vision/Classes/PoseLandmarker.md.txt) ` Performs pose landmarks detection on images. This API expects a pre-trained pose landmarks model asset bundle. #### Declaration Swift class PoseLandmarker: NSObject - ` ### [PoseLandmarkerOptions](https://developers.google.com/edge/api/mediapipe/swift/vision/Classes/PoseLandmarkerOptions.md.txt) ` Options for setting up a `PoseLandmarker`. #### Declaration Swift class PoseLandmarkerOptions: TaskOptions, NSCopying - ` ### [PoseLandmarkerResult](https://developers.google.com/edge/api/mediapipe/swift/vision/Classes/PoseLandmarkerResult.md.txt) ` Represents the pose landmarks deection results generated by `PoseLandmarker`. #### Declaration Swift class PoseLandmarkerResult: TaskResult, NSCopying - ` ### [RegionOfInterest](https://developers.google.com/edge/api/mediapipe/swift/vision/Classes/RegionOfInterest.md.txt) ` The Region-Of-Interest (ROI) to interact with in an interactive segmentation inference. An instance can contain erither contain a single normalized point pointing to the object that the user wants to segment or array of normalized key points that make up scribbles over the object that the user wants to segment. #### Declaration Swift class RegionOfInterest: NSObject - ` ### [ResultCategory](https://developers.google.com/edge/api/mediapipe/swift/vision/Classes/ResultCategory.md.txt) ` Category is a util class that contains a label, its display name, a float value as score, and the index of the label in the corresponding label file. Typically it's used as the result of classification tasks. #### Declaration Swift class ResultCategory: NSObject - ` ### [Stroke](https://developers.google.com/edge/api/mediapipe/swift/vision/Classes/Stroke.md.txt) ` Represents a single user-drawn stroke for interactive segmentation. #### Declaration Swift class Stroke: NSObject - ` ### [TaskOptions](https://developers.google.com/edge/api/mediapipe/swift/vision/Classes/TaskOptions.md.txt) ` MediaPipe Tasks options base class. Any MediaPipe task-specific options class should extend this class. #### Declaration Swift class TaskOptions: NSObject, NSCopying - ` ### [TaskPart](https://developers.google.com/edge/api/mediapipe/swift/vision/Classes/TaskPart.md.txt) ` Represents a part of a multi-modal content block. #### Declaration Swift class TaskPart: NSObject - ` ### [TaskResult](https://developers.google.com/edge/api/mediapipe/swift/vision/Classes/TaskResult.md.txt) ` MediaPipe Tasks result base class. Any MediaPipe task result class should extend this class. #### Declaration Swift class TaskResult: NSObject, NSCopying - ` ### [TextPart](https://developers.google.com/edge/api/mediapipe/swift/vision/Classes/TextPart.md.txt) ` Text part representing the text content block of a multi-modal block. #### Declaration Swift class TextPart: TaskPart - ` ### [TransformMatrix](https://developers.google.com/edge/api/mediapipe/swift/vision/Classes/TransformMatrix.md.txt) ` A matrix that can be used for tansformations. #### Declaration Swift class TransformMatrix: NSObject