MediaPipeTasksVision Framework Reference

ImageClassifier

class ImageClassifier : NSObject

@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.

  • Creates a new instance of ImageClassifier from an absolute path to a TensorFlow Lite model file stored locally on the device and the default ImageClassifierOptions.

    Declaration

    Swift

    convenience init(modelPath: String) throws

    Parameters

    modelPath

    An absolute path to a TensorFlow Lite model file stored locally on the device.

    Return Value

    A new instance of ImageClassifier with the given model path. nil if there is an error in initializing the image classifier.

  • Creates a new instance of ImageClassifier from the given ImageClassifierOptions.

    Declaration

    Swift

    init(options: ImageClassifierOptions) throws

    Parameters

    options

    The options of type ImageClassifierOptions to use for configuring the ImageClassifier.

    Return Value

    A new instance of ImageClassifier with the given options. nil if there is an error in initializing the image classifier.

  • Performs image classification on the provided MPImage using the whole image as region of interest. Rotation will be applied according to the orientation property of the provided MPImage. Only use this method when the ImageClassifier is created with running mode, .image.

    This method supports classification of RGBA images. If your MPImage has a source type of .pixelBuffer or .sampleBuffer, the underlying pixel buffer must use kCVPixelFormatType_32BGRA as its pixel format.

    If your MPImage has a source type of