# Beta Features

Beta Features are the staging area for new DepthAI nodes and features. They let us ship support earlier while the public API is
still evolving.

The beta label reflects API stability rather than implementation quality. These nodes are designed to be useful in real
applications and deployments, but you should expect interface updates while the API matures.

> **Beta API stability**
> Beta APIs may change without prior notice. If you use them in a deployed system, plan to pin your DepthAI version and make small integration updates as the feature matures.

## Platform behavior

 * Beta nodes run natively on [RVC4](https://docs.luxonis.com/hardware/platform/rvc/rvc4.md)
 * On [RVC2](https://docs.luxonis.com/hardware/platform/rvc/rvc2.md), the same beta nodes run on the host
 * Most beta parsers currently have both Python and C++ examples so you can evaluate the current beta surface quickly

## Examples

The current `main` branch beta examples in `depthai-core` are:

 * `Classification_parser`: Parse emotion-recognition outputs into labeled class predictions.
   [Python](https://github.com/luxonis/depthai-core/blob/main/examples/python/Beta/classification_parser.py) |
   [C++](https://github.com/luxonis/depthai-core/blob/main/examples/cpp/Beta/classification_parser.cpp)
 * `Classification_sequence_parser`: Parse sequence-classification output for OCR-style text recognition.
   [Python](https://github.com/luxonis/depthai-core/blob/main/examples/python/Beta/classification_sequence_parser.py) |
   [C++](https://github.com/luxonis/depthai-core/blob/main/examples/cpp/Beta/classification_sequence_parser.cpp)
 * `Embeddings_parser`: Parse embedding vectors for similarity and retrieval workflows.
   [Python](https://github.com/luxonis/depthai-core/blob/main/examples/python/Beta/embeddings_parser.py) |
   [C++](https://github.com/luxonis/depthai-core/blob/main/examples/cpp/Beta/embeddings_parser.cpp)
 * `Fastsam_parser`: Parse FastSAM segmentation output into an overlaid mask view.
   [Python](https://github.com/luxonis/depthai-core/blob/main/examples/python/Beta/fastsam_parser.py) |
   [C++](https://github.com/luxonis/depthai-core/blob/main/examples/cpp/Beta/fastsam_parser.cpp)
 * `Hrnet_parser`: Parse HRNet pose output into keypoints and skeleton edges.
   [Python](https://github.com/luxonis/depthai-core/blob/main/examples/python/Beta/hrnet_parser.py) |
   [C++](https://github.com/luxonis/depthai-core/blob/main/examples/cpp/Beta/hrnet_parser.cpp)
 * `Image_output_parser`: Parse image-producing network output into a displayable frame.
   [Python](https://github.com/luxonis/depthai-core/blob/main/examples/python/Beta/image_output_parser.py) |
   [C++](https://github.com/luxonis/depthai-core/blob/main/examples/cpp/Beta/image_output_parser.cpp)
 * `Img_detections_filter`: Filter `ImgDetections` messages by confidence before downstream processing.
   [Python](https://github.com/luxonis/depthai-core/blob/main/examples/python/Beta/img_detections_filter.py)
 * `Keypoint_parser`: Parse face-landmark keypoints into connected overlay points.
   [Python](https://github.com/luxonis/depthai-core/blob/main/examples/python/Beta/keypoint_parser.py) |
   [C++](https://github.com/luxonis/depthai-core/blob/main/examples/cpp/Beta/keypoint_parser.cpp)
 * `Lane_detection_parser`: Parse lane-detection output into lane overlays on the input frame.
   [Python](https://github.com/luxonis/depthai-core/blob/main/examples/python/Beta/lane_detection_parser.py) |
   [C++](https://github.com/luxonis/depthai-core/blob/main/examples/cpp/Beta/lane_detection_parser.cpp)
 * `Map_output_parser`: Parse dense map output into a normalized heatmap visualization.
   [Python](https://github.com/luxonis/depthai-core/blob/main/examples/python/Beta/map_output_parser.py) |
   [C++](https://github.com/luxonis/depthai-core/blob/main/examples/cpp/Beta/map_output_parser.cpp)
 * `Mlsd_parser`: Parse MLSD line-segment output into line overlays.
   [Python](https://github.com/luxonis/depthai-core/blob/main/examples/python/Beta/mlsd_parser.py) |
   [C++](https://github.com/luxonis/depthai-core/blob/main/examples/cpp/Beta/mlsd_parser.cpp)
 * `Mp_palm_detection_parser`: Parse MediaPipe palm detections into rotated bounding boxes.
   [Python](https://github.com/luxonis/depthai-core/blob/main/examples/python/Beta/mp_palm_detection_parser.py) |
   [C++](https://github.com/luxonis/depthai-core/blob/main/examples/cpp/Beta/mp_palm_detection_parser.cpp)
 * `Pp_text_detection_parser`: Parse Paddle text-detection output into text region polygons.
   [Python](https://github.com/luxonis/depthai-core/blob/main/examples/python/Beta/pp_text_detection_parser.py) |
   [C++](https://github.com/luxonis/depthai-core/blob/main/examples/cpp/Beta/pp_text_detection_parser.cpp)
 * `scrfd_parser`: Parse SCRFD face detections and landmarks.
   [Python](https://github.com/luxonis/depthai-core/blob/main/examples/python/Beta/scrfd_parser.py) |
   [C++](https://github.com/luxonis/depthai-core/blob/main/examples/cpp/Beta/scrfd_parser.cpp)
 * `superanimal_parser`: Parse SuperAnimal keypoints into an animal-pose skeleton overlay.
   [Python](https://github.com/luxonis/depthai-core/blob/main/examples/python/Beta/superanimal_parser.py) |
   [C++](https://github.com/luxonis/depthai-core/blob/main/examples/cpp/Beta/superanimal_parser.cpp)
 * `yunet_parser`: Parse YuNet face detections and landmarks.
   [Python](https://github.com/luxonis/depthai-core/blob/main/examples/python/Beta/yunet_parser.py) |
   [C++](https://github.com/luxonis/depthai-core/blob/main/examples/cpp/Beta/yunet_parser.cpp)

## Example usage

In Python, access beta nodes through `dai.beta.node`.

```python
parserNode = pipeline.create(dai.beta.node.ClassificationParser).build(
    neuralNetwork.out,
    modelArchive,
)
```