MediaPipeTasksVision Framework Reference

Classes

The following classes are available globally.

• BaseOptions

  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

• ResultCategory

  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

• Classifications

  Represents the list of classification for a given classifier head. Typically used as a result for classification tasks.

  Declaration

  Swift

  class Classifications : NSObject

• ClassificationResult

  Represents the classification results of a model. Typically used as a result for classification tasks.

  Declaration

  Swift

  class ClassificationResult : NSObject

• ClassifierOptions

  Classifier options shared across MediaPipe iOS classification tasks.

  Declaration

  Swift

  class ClassifierOptions : NSObject, NSCopying

• Connection

  The value class representing a landmark connection.

  Declaration

  Swift

  class Connection : NSObject

• NormalizedKeypoint

  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

• Detection

  Represents one detected object in the results of ObjectDetector.

  Declaration

  Swift

  class Detection : NSObject

• Embedding

  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

  Represents the embedding results of a model. Typically used as a result for embedding tasks.

  Declaration

  Swift

  class EmbeddingResult : NSObject

• FaceDetector

  @brief 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

  Options for setting up a FaceDetector.

  Declaration

  Swift

  class FaceDetectorOptions : TaskOptions, NSCopying

• FaceDetectorResult

  Represents the detection results generated by FaceDetector.

  Declaration

  Swift

  class FaceDetectorResult : TaskResult

• FaceLandmarker

  @brief 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

  Options for setting up a FaceLandmarker.

  Declaration

  Swift

  class FaceLandmarkerOptions : TaskOptions, NSCopying

• TransformMatrix

  A matrix that can be used for tansformations.

  Declaration

  Swift

  class TransformMatrix : NSObject

• FaceLandmarkerResult

  Represents the detection results generated by FaceLandmarker.

  Declaration

  Swift

  class FaceLandmarkerResult : TaskResult

• FaceStylizer

  Class that performs face stylization on images.

  Declaration

  Swift

  class FaceStylizer : NSObject

• FaceStylizerOptions

  Options for setting up a FaceStylizer.

  Declaration

  Swift

  class FaceStylizerOptions : TaskOptions, NSCopying

• FaceStylizerResult

  Represents the stylized image generated by FaceStylizer.

  Declaration

  Swift

  class FaceStylizerResult : TaskResult

• GestureRecognizer

  @brief 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

  Options for setting up a GestureRecognizer.

  Declaration

  Swift

  class GestureRecognizerOptions : TaskOptions, NSCopying

• GestureRecognizerResult

  Represents the gesture recognition results generated by GestureRecognizer.

  Declaration

  Swift

  class GestureRecognizerResult : TaskResult

• HandLandmarker

  @brief Performs hand landmarks detection on images.

  This API expects a pre-trained hand landmarks model asset bundle.

  Declaration

  Swift

  class HandLandmarker : NSObject

• HandLandmarkerOptions

  Options for setting up a HandLandmarker.

  Declaration

  Swift

  class HandLandmarkerOptions : TaskOptions, NSCopying

• HandLandmarkerResult

  Represents the hand landmarker results generated by HandLandmarker.

  Declaration

  Swift

  class HandLandmarkerResult : TaskResult

• MPImage

  An image used in on-device machine learning using MediaPipe Task library.

  Declaration

  Swift

  class MPImage : NSObject

• ImageClassifier

  @brief Performs classification on images.

  The API expects a TFLite model with optional, but strongly recommended, 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.

  At least one output tensor with: (kTfLiteUInt8/kTfLiteFloat32)

  • Nclasses 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

  Options for setting up a ImageClassifier.

  Declaration

  Swift

  class ImageClassifierOptions : TaskOptions, NSCopying

• ImageClassifierResult

  Represents the classification results generated by ImageClassifier. *

  Declaration

  Swift

  class ImageClassifierResult : TaskResult

• ImageEmbedder

  @brief Performs embedding extraction on images.

  The API expects a TFLite model with optional, but strongly recommended, 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 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

• ImageEmbedderOptions

  Options for setting up a ImageEmbedder.

  Declaration

  Swift

  class ImageEmbedderOptions : TaskOptions, NSCopying

• ImageEmbedderResult

  Represents the embedding results generated by ImageEmbedder. *

  Declaration

  Swift

  class ImageEmbedderResult : TaskResult

• ImageSegmenter

  @brief Class that performs segmentation on images.

  The API expects a TFLite model with mandatory TFLite Model Metadata.

  Declaration

  Swift

  class ImageSegmenter : NSObject

• ImageSegmenterOptions

  Options for setting up a ImageSegmenter.

  Declaration

  Swift

  class ImageSegmenterOptions : TaskOptions, NSCopying

• ImageSegmenterResult

  Represents the segmentation results generated by ImageSegmenter.

  Declaration

  Swift

  class ImageSegmenterResult : TaskResult

• InteractiveSegmenter

  @brief Class that performs interactive segmentation on images.

  Users can represent user interaction through RegionOfInterest, which gives a hint to InteractiveSegmenter 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 InteractiveSegmenter : NSObject

• InteractiveSegmenterOptions

  Options for setting up a InteractiveSegmenter.

  Declaration

  Swift

  class InteractiveSegmenterOptions : TaskOptions, NSCopying

• InteractiveSegmenterResult

  Represents the segmentation results generated by ImageSegmenter.

  Declaration

  Swift

  class InteractiveSegmenterResult : TaskResult

• Landmark

  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

• NormalizedLandmark

  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

• Mask

  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

• ObjectDetector

  @brief 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

  Options for setting up a ObjectDetector.

  Declaration

  Swift

  class ObjectDetectorOptions : TaskOptions, NSCopying

• ObjectDetectorResult

  Represents the detection results generated by ObjectDetector.

  Declaration

  Swift

  class ObjectDetectorResult : TaskResult

• PoseLandmarker

  @brief Performs pose landmarks detection on images.

  This API expects a pre-trained pose landmarks model asset bundle.

  Declaration

  Swift

  class PoseLandmarker : NSObject

• PoseLandmarkerOptions

  Options for setting up a PoseLandmarker.

  Declaration

  Swift

  class PoseLandmarkerOptions : TaskOptions, NSCopying

• PoseLandmarkerResult

  Represents the pose landmarks deection results generated by PoseLandmarker.

  Declaration

  Swift

  class PoseLandmarkerResult : TaskResult

• RegionOfInterest

  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

• TaskOptions

  MediaPipe Tasks options base class. Any MediaPipe task-specific options class should extend this class.

  Declaration

  Swift

  class TaskOptions : NSObject, NSCopying

• TaskResult

  MediaPipe Tasks result base class. Any MediaPipe task result class should extend this class.

  Declaration

  Swift

  class TaskResult : NSObject, NSCopying