Sends live image data to perform face detection with default image processing options, i.e. without any rotation applied, and the results will be avai

Returns default settings for KeyFrameCropOptions. Populates target size to be the default target size.

Returns a const pointer to the model metadata extractor.

Validates and builds the {@link ConditionOptions} instance.

Creates an {@link ObjectDetector} instance from an {@link ObjectDetectorOptions}. @param context an Android {@link Context}. @param detectorOptions a

Pose landmarks of detected poses.

Stores the input audio samples {@code src} in the ring buffer. @param src input audio samples in {@link android.media.AudioFormat#ENCODING_PCM_FLOAT}

Updates the image view with the latest {@link HandsResult}.

Creates a new internal::PacketWithContext object, and returns the native handle.

Examples: BLAH:0:blah1 BLAH:1:blah2 A:a B:b A:0:a0 A:1:a1 A:2:a2 B:0:b0 B:1:b1 C:c0

Returns true if the key is in the sequence's context and the feature has at least one value.

A range value is anything between Min() and Max() (inclusive). Any number of packets with range values can be sent over a stream as long as they are s

Validates and builds the {@link HolisticLandmarkerOptions} instance. @throws IllegalArgumentException if the result listener and the running mode are

Converts a {@link BaseOptions} instance to a {@link BaseOptionsProto.BaseOptions} protobuf message.

Creates an `TextEmbedder` object from a TensorFlow Lite model and the default `TextEmbedderOptions`. Args: model_path: Path to the model.

Returns the calculator context.

Returns true if the halide buffers of two input GrayBuffer are identical. Otherwise, returns false;

Reports packet timestamp and string contents, or "<empty>"".

Returns default settings for SceneKeyFrameCropSummary. Sets scene frame size to be the default size. Sets each key frame compact info in accordance to

Returns a pointer to the extracted TFLite Model Metadata, or nullptr if no metadata was present in the Model FlatBuffer provided at creation time.

Constructs the field path for a string of field names.

Reads the next token, joining two symbols if needed.

Return the value in units of seconds (the underlying value is in microseconds).

Creates an {@link ImageClassifier} instance from an {@link ImageClassifierOptions} instance. @param context an Android {@link Context}. @param option

Creates a PoseLandmarkerResult from a ctypes struct.

* Resolve the value from `value`. Invokes `value` with `data` if it is a * function.

Sets the maximum number of hands can be detected by the HandLandmarker.

* Sets new options for this `HolisticLandmarker`. * * Calling `setOptions()` with a subset of options only affects those options. * You can r

Sets the MediaPipe task name.

Returns a ctypes callback function that can be passed to a C library. This function calls the converter function and schedules the user callback

Shuts down the ObjectDetector when all works are done.

Fill a halide_buffer_t channel with the given value.

Test template. No processing/assertions should be done after the function is invoked.

When true, Process is called for every new timestamp bound, with or without new packets. A call to Process with only an input timestamp bound is norma

Specifies the maximum difference between input and output timestamps. When specified, the mediapipe framework automatically computes output timestamp

Convenience function to access the current data size.

Creates a {@link HandLandmarker} instance from a {@link HandLandmarkerOptions}. @param context an Android {@link Context}. @param landmarkerOptions a

Creates a {@link FaceDetector} instance from a {@link FaceDetectorOptions}. @param context an Android {@link Context}. @param detectorOptions a {@lin

Creates the input tensor metadata based on the information. Returns: A Flatbuffers Python object of the input metadata.