mp.tasks.vision.FaceLandmarker

Class that performs face landmarks detection on images.

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

close

View source

Shuts down the mediapipe vision task instance.

Raises
RuntimeError If the mediapipe vision task failed to close.

convert_to_normalized_rect

View source

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

Creates an FaceLandmarker object from a TensorFlow Lite model and the default FaceLandmarkerOptions.

Note that the created FaceLandmarker instance is in image mode, for detecting face landmarks on single image inputs.

Args
model_path Path to the model.

Returns
FaceLandmarker object that's created from the model file and the default FaceLandmarkerOptions.

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

create_from_options

View source

Creates the FaceLandmarker object from face landmarker options.

Args
options Options for the face landmarker task.

Returns
FaceLandmarker object that's created from options.

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

detect

View source

Performs face landmarks detection on the given image.

Only use this method when the FaceLandmarker is created with the image running mode.

The image can be of any size with format RGB or RGBA.

support is implemented.

Args
image MediaPipe Image.
image_processing_options Options for image processing.

Returns
The face landmarks detection results.

Raises
ValueError If any of the input arguments is invalid.
RuntimeError If face landmarker detection failed to run.

detect_async

View source

Sends live image data to perform face landmarks detection.

The results will be available via the "result_callback" provided in the FaceLandmarkerOptions. Only use this method when the FaceLandmarker is created with the live stream running mode.

Only use this method when the FaceLandmarker 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 FaceLandmarkerOptions. The detect_async method is designed to process live stream data such as camera input. To lower the overall latency, face landmarker may drop the input images if needed. In other words, it's not guaranteed to have output per input image.

The result_callback provides:

  • The face landmarks detection results.
  • The input image that the face landmarker 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 face landmarker has already processed.

detect_for_video

View source

Performs face landmarks detection on the provided video frame.

Only use this method when the FaceLandmarker is created with the video running mode.

Only use this method when the FaceLandmarker 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
The face landmarks detection results.