Returns the number of color channels (3, or 4 if RGBA).

Helper function to create a tuple (inside an initializer list).

Get a mutable pointer to the underlying image data. The ImageFrame retains ownership.

Returns 1 if the container includes a certain key.

Predicts the language of the input `text`. Args: text: The input text. Returns: A `LanguageDetectorResult` object that contains

Makes a rectangle given the corner (x, y) and the size (width, height).

Helper to run a graph with the given inputs and generate outputs, asserting each step along the way. Inputs: graph_config_proto - graph config protobu

Wrapper for np.testing.assert_allclose().

TODO Consider moving the output bound computing logic to OutputStreamHandler.

Returns node options pointer (never null) for population.

Returns the iterator after the last element. The end() iterator doesn't belong to any shard.

The index of the label in the corresponding label file. Returns -1 if the index is not set.

Returns the size of the dataset. Same functionality as calling __len__. See the __len__ method definition for more information. Raises:

Generates an ImageEmbedderOptionsC object.

Validates and builds the {@link PoseLandmarkerOptions} instance. @throws IllegalArgumentException if the result listener and the running mode are not

The current C* for this thread.

* Attaches a listener that will be invoked when the MediaPipe framework * receives an empty packet on the provided output stream. This can be used

Creates a {@link Category} instance. @param score the probability score of this label category. @param index the index of the label in the correspond

Returns FrameBuffer dimension.

Sets a callback to be invoked when task result objects become available. @param listener the user-defined {@link ResultListener} callback.

Sets the min and max values, and min greater than max is allowable, but the user has to be aware of the consequences such as negative width and height

Calls {@link GLES20#glGetError} and raises an exception if there was an error.

Populates loaded metadata and associated files into the model file.

To ensure that the selected thresholds are robust, it is recommend to run this test mutiple times with time seed, if changes are made.

Row size in bytes.

Returns the height of the image.

Returns the width of the image.

For use with APIs that prefer a string_view.

Contains one embedding per embedder head.

Sets the minimum confidence score for the face detection to be considered successful. The default minDetectionConfidence is 0.5.

Return the value in units of microseconds. The underlying value is already in microseconds, but this function should be preferred over Value() in cas

Generates a batched tf.data.Dataset for training/evaluation. Args: batch_size: An integer, the returned dataset will be batched by this siz

The presentation time of the frame in microseconds

Performs face detection on the provided video frames. Only use this method when the FaceDetector is created with the video running mode. It's

Sends live image data (an Image with a unique timestamp) to perform face detection. Only use this method when the FaceDetector is created with th

Returns the AHardwareBuffer handle. Note that writes to the handle may be pending. To enable synchronized read access, a fence FD can be obtained from