<br />

|---|
| [![](https://www.tensorflow.org/images/GitHub-Mark-32px.png) View source on GitHub](https://github.com/google-ai-edge/mediapipe/blob/master/mediapipe/tasks/python/vision/pose_landmarker.py#L334-L611) |

Class that performs pose landmarks detection on images.

    mp.tasks.vision.PoseLandmarker(
        lib: serial_dispatcher.SerialDispatcher,
        handle: ctypes.c_void_p,
        dispatcher: _AsyncResultDispatcher,
        async_callback: _C_TYPES_RESULT_CALLBACK
    )

<br />

<br />

<br />

| ## Args ||
|---|---|
| `lib` | The dispatch library to use for the pose landmarker. |
| `handle` | The C pointer to the pose landmarker. |
| `dispatcher` | The async result handler for the pose landmarker. |
| `async_callback` | The c callback for the pose landmarker. |

<br />

## Methods

### `close`

[View source](https://github.com/google-ai-edge/mediapipe/blob/master/mediapipe/tasks/python/vision/pose_landmarker.py#L582-L589)

    close()

Closes the PoseLandmarker.

### `create_from_model_path`

[View source](https://github.com/google-ai-edge/mediapipe/blob/master/mediapipe/tasks/python/vision/pose_landmarker.py#L362-L385)

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

Creates a `PoseLandmarker` object from a model bundle file and the default `PoseLandmarkerOptions`.

Note that the created `PoseLandmarker` instance is in image mode, for
detecting pose landmarks on single image inputs.

<br />

<br />

<br />

| Args ||
|---|---|
| `model_path` | Path to the model. |

<br />

<br />

<br />

<br />

| Returns ||
|---|---|
| `PoseLandmarker` object that's created from the model file and the default `PoseLandmarkerOptions`. ||

<br />

<br />

<br />

<br />

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

<br />

### `create_from_options`

[View source](https://github.com/google-ai-edge/mediapipe/blob/master/mediapipe/tasks/python/vision/pose_landmarker.py#L387-L442)

    @classmethod
    create_from_options(
        options: https://developers.google.com/edge/api/mediapipe/python/mp/tasks/vision/PoseLandmarkerOptions
    ) -> 'PoseLandmarker'

Creates the `PoseLandmarker` object from pose landmarker options.

<br />

<br />

<br />

| Args ||
|---|---|
| `options` | Options for the pose landmarker task. |

<br />

<br />

<br />

<br />

| Returns ||
|---|---|
| `PoseLandmarker` object that's created from `options`. ||

<br />

<br />

<br />

<br />

| Raises ||
|---|---|
| `ValueError` | If failed to create `PoseLandmarker` object from `PoseLandmarkerOptions` such as missing the model. |
| `RuntimeError` | If other types of error occurred. |

<br />

### `detect`

[View source](https://github.com/google-ai-edge/mediapipe/blob/master/mediapipe/tasks/python/vision/pose_landmarker.py#L444-L482)

    detect(
        image: https://developers.google.com/edge/api/mediapipe/python/mp/Image,
        image_processing_options: Optional[https://developers.google.com/edge/api/mediapipe/python/mp/tasks/vision/ImageProcessingOptions] = None
    ) -> https://developers.google.com/edge/api/mediapipe/python/mp/tasks/vision/PoseLandmarkerResult

Performs pose landmarks detection on the given image.

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

<br />

<br />

<br />

| Args ||
|---|---|
| `image` | MediaPipe Image. |
| `image_processing_options` | Options for image processing. |

<br />

<br />

<br />

<br />

| Returns ||
|---|---|
| The pose landmarker detection results. ||

<br />

<br />

<br />

<br />

| Raises ||
|---|---|
| `ValueError` | If any of the input arguments is invalid. |
| `RuntimeError` | If pose landmarker detection failed to run. |

<br />

### `detect_async`

[View source](https://github.com/google-ai-edge/mediapipe/blob/master/mediapipe/tasks/python/vision/pose_landmarker.py#L532-L580)

    detect_async(
        image: https://developers.google.com/edge/api/mediapipe/python/mp/Image,
        timestamp_ms: int,
        image_processing_options: Optional[https://developers.google.com/edge/api/mediapipe/python/mp/tasks/vision/ImageProcessingOptions] = None
    ) -> None

Sends live image data to perform pose landmarks detection.

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

Only use this method when the PoseLandmarker 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 `PoseLandmarkerOptions`. The
`detect_async` method is designed to process live stream data such as
camera input. To lower the overall latency, pose 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 pose landmarker detection results.
- The input image that the pose landmarker runs on.
- The input timestamp in milliseconds.

<br />

<br />

<br />

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

<br />

<br />

<br />

<br />

| Raises ||
|---|---|
| `ValueError` | If the current input timestamp is smaller than what the pose landmarker has already processed. |

<br />

### `detect_for_video`

[View source](https://github.com/google-ai-edge/mediapipe/blob/master/mediapipe/tasks/python/vision/pose_landmarker.py#L484-L530)

    detect_for_video(
        image: https://developers.google.com/edge/api/mediapipe/python/mp/Image,
        timestamp_ms: int,
        image_processing_options: Optional[https://developers.google.com/edge/api/mediapipe/python/mp/tasks/vision/ImageProcessingOptions] = None
    ) -> https://developers.google.com/edge/api/mediapipe/python/mp/tasks/vision/PoseLandmarkerResult

Performs pose landmarks detection on the provided video frame.

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

Only use this method when the PoseLandmarker 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.

<br />

<br />

<br />

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

<br />

<br />

<br />

<br />

| Returns ||
|---|---|
| The pose landmarker detection results. ||

<br />

<br />

<br />

<br />

| Raises ||
|---|---|
| `ValueError` | If any of the input arguments is invalid. |
| `RuntimeError` | If pose landmarker detection failed to run. |

<br />

### `__enter__`

[View source](https://github.com/google-ai-edge/mediapipe/blob/master/mediapipe/tasks/python/vision/pose_landmarker.py#L591-L593)

    __enter__()

Returns `self` upon entering the runtime context.

### `__exit__`

[View source](https://github.com/google-ai-edge/mediapipe/blob/master/mediapipe/tasks/python/vision/pose_landmarker.py#L595-L608)

    __exit__(
        exc_type, exc_value, traceback
    )

Shuts down the MediaPipe task instance on exit of the context manager.

<br />

<br />

<br />

| Args ||
|---|---|
| `exc_type` | The exception type that caused the context manager to exit. |
| `exc_value` | The exception value that caused the context manager to exit. |
| `traceback` | The exception traceback that caused the context manager to exit. |

<br />

<br />

<br />

<br />

| Raises ||
|---|---|
| `RuntimeError` | If the MediaPipe PoseLandmarker task failed to close. |

<br />