mp.tasks.vision.ImageClassifier

Class that performs image classification on images.

mp.tasks.vision.ImageClassifier(
    graph_config: mp.calculators.core.constant_side_packet_calculator_pb2.mediapipe_dot_framework_dot_calculator__pb2.CalculatorGraphConfig,
    running_mode: mp.tasks.vision.RunningMode,
    packet_callback: Optional[Callable[[Mapping[str, packet_module.Packet]], None]] = None
) -> None

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

(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.

An example of such model can be found at: https://tfhub.dev/bohemian-visual-recognition-alliance/lite-model/models/mushroom-identification_v1/1

graph_config The mediapipe vision task graph config proto.
running_mode The running mode of the mediapipe vision task.
packet_callback The optional packet callback for getting results asynchronously in the live stream mode.

ValueError The packet callback is not properly set based on the task's running mode.

Methods

classify

View source

classify(
    image: mp.Image,
    image_processing_options: Optional[mp.tasks.vision.holistic_landmarker.image_processing_options_module.ImageProcessingOptions] = None
) -> mp.tasks.audio.AudioClassifierResult

Performs image classification on the provided MediaPipe Image.

Args
image MediaPipe Image.
image_processing_options Options for image processing.

Returns
A classification result object that contains a list of classifications.

Raises
ValueError If any of the input arguments is invalid.
RuntimeError If image classification failed to run.

classify_async

View source

classify_async(
    image: mp.Image,
    timestamp_ms: int,
    image_processing_options: Optional[mp.tasks.vision.holistic_landmarker.image_processing_options_module.ImageProcessingOptions] = None
) -> None

Sends live image data (an Image with a unique timestamp) to perform image classification.

Only use this method when the ImageClassifier is created with the live stream running mode. The input timestamps should be monotonically increasing for adjacent calls of this method. This method will return immediately after the input image is accepted. The results will be available via the result_callback provided in the ImageClassifierOptions. The classify_async method is designed to process live stream data such as camera input. To lower the overall latency, image classifier may drop the input images if needed. In other words, it's not guaranteed to have output per input image.

The result_callback provides:

  • A classification result object that contains a list of classifications.
  • The input image that the image classifier runs on.
  • The input timestamp in milliseconds.

Args
image MediaPipe Image.
timestamp_ms The timestamp of the input image in milliseconds.
image_processing_options Options for image processing.

Raises
ValueError If the current input timestamp is smaller than what the image classifier has already processed.

classify_for_video

View source

classify_for_video(
    image: mp.Image,
    timestamp_ms: int,
    image_processing_options: Optional[mp.tasks.vision.holistic_landmarker.image_processing_options_module.ImageProcessingOptions] = None
) -> mp.tasks.audio.AudioClassifierResult

Performs image classification on the provided video frames.

Only use this method when the ImageClassifier is created with the video running mode. It's required to provide the video frame's timestamp (in milliseconds) along with the video frame. The input timestamps should be monotonically increasing for adjacent calls of this method.

Args
image MediaPipe Image.
timestamp_ms The timestamp of the input video frame in milliseconds.
image_processing_options Options for image processing.

Returns
A classification result object that contains a list of classifications.

Raises
ValueError If any of the input arguments is invalid.
RuntimeError If image classification failed to run.

close

View source

close() -> None

Shuts down the mediapipe vision task instance.

Raises
RuntimeError If the mediapipe vision task failed to close.

convert_to_normalized_rect

View source

convert_to_normalized_rect(
    options: mp.tasks.vision.holistic_landmarker.image_processing_options_module.ImageProcessingOptions,
    image: mp.Image,
    roi_allowed: bool = True
) -> mp.tasks.components.containers.NormalizedRect

Converts from ImageProcessingOptions to NormalizedRect, performing sanity checks on-the-fly.

If the input ImageProcessingOptions is not present, returns a default NormalizedRect covering the whole image with rotation set to 0. If 'roi_allowed' is false, an error will be returned if the input ImageProcessingOptions has its 'region_of_interest' field set.

Args
options Options for image processing.
image The image to process.
roi_allowed Indicates if the region_of_interest field is allowed to be set. By default, it's set to True.

Returns
A normalized rect proto that represents the image processing options.

create_from_model_path

View source

@classmethod
create_from_model_path(
    model_path: str
) -> 'ImageClassifier'

Creates an ImageClassifier object from a TensorFlow Lite model and the default ImageClassifierOptions.

Note that the created ImageClassifier instance is in image mode, for classifying objects on single image inputs.

Args
model_path Path to the model.

Returns
ImageClassifier object that's created from the model file and the default ImageClassifierOptions.

Raises
ValueError If failed to create ImageClassifier object from the provided file such as invalid file path.
RuntimeError If other types of error occurred.

create_from_options

View source

@classmethod
create_from_options(
    options: mp.tasks.vision.ImageClassifierOptions
) -> 'ImageClassifier'

Creates the ImageClassifier object from image classifier options.

Args
options Options for the image classifier task.

Returns
ImageClassifier object that's created from options.

Raises
ValueError If failed to create ImageClassifier object from ImageClassifierOptions such as missing the model.
RuntimeError If other types of error occurred.

get_graph_config

View source

get_graph_config() -> mp.calculators.core.constant_side_packet_calculator_pb2.mediapipe_dot_framework_dot_calculator__pb2.CalculatorGraphConfig

Returns the canonicalized CalculatorGraphConfig of the underlying graph.

__enter__

View source

__enter__()

Return self upon entering the runtime context.

__exit__

View source

__exit__(
    unused_exc_type, unused_exc_value, unused_traceback
)

Shuts down the mediapipe vision task instance on exit of the context manager.

Raises
RuntimeError If the mediapipe vision task failed to close.