DetectorNode¶

class mmpose.apis.webcam.nodes.DetectorNode(name: str, model_config: str, model_checkpoint: str, input_buffer: str, output_buffer: Union[str, List[str]], enable_key: Optional[Union[str, int]] = None, enable: bool = True, device: str = 'cuda:0', bbox_thr: float = 0.5, multi_input: bool = False)[source]¶

Detect objects from the frame image using MMDetection model.

Note that MMDetection is required for this node. Please refer to MMDetection documentation for the installation guide.

Parameters

name (str) – The node name (also thread name)
model_cfg (str) – The model config file
model_checkpoint (str) – The model checkpoint file
input_buffer (str) – The name of the input buffer
output_buffer (str|list) – The name(s) of the output buffer(s)
enable_key (str|int, optional) – Set a hot-key to toggle enable/disable of the node. If an int value is given, it will be treated as an ascii code of a key. Please note: (1) If enable_key is set, the bypass() method need to be overridden to define the node behavior when disabled; (2) Some hot-keys are reserved for particular use. For example: ‘q’, ‘Q’ and 27 are used for exiting. Default: None
enable (bool) – Default enable/disable status. Default: True
device (str) – Specify the device to hold model weights and inference the model. Default: 'cuda:0'
bbox_thr (float) – Set a threshold to filter out objects with low bbox scores. Default: 0.5
multi_input (bool) – Whether load all frames in input buffer. If True, all frames in buffer will be loaded and stacked. The latest frame is used to detect objects of interest. Default: False

Example::

>>> cfg = dict(
...     type='DetectorNode',
...     name='detector',
...     model_config='demo/mmdetection_cfg/'
...     'ssdlite_mobilenetv2_scratch_600e_coco.py',
...     model_checkpoint='https://download.openmmlab.com'
...     '/mmdetection/v2.0/ssd/'
...     'ssdlite_mobilenetv2_scratch_600e_coco/ssdlite_mobilenetv2_'
...     'scratch_600e_coco_20210629_110627-974d9307.pth',
...     # `_input_` is an executor-reserved buffer
...     input_buffer='_input_',
...     output_buffer='det_result')

>>> from mmpose.apis.webcam.nodes import NODES
>>> node = NODES.build(cfg)

bypass(input_msgs)[source]¶

The method that defines the node behavior when disabled.

Note that a node must override this method if it has enable_key. This method has the same signature as process().

Parameters: input_msgs (dict[str, Message]) – The input data collected from the buffers. For each item, the key is the input_name of the registered input buffer, and the value is a Message instance fetched from the buffer (or None if the buffer is non-trigger and not ready).
Returns: The output message of the node which will be send to all registered output buffers.
Return type: Message

process(input_msgs)[source]¶

The method that implements the function of the node.

This method will be invoked when the node is enabled and the input data is ready. All subclasses of Node should override this method.

Parameters: input_msgs (dict[str, Message]) – The input data collected from the buffers. For each item, the key is the input_name of the registered input buffer, and the value is a Message instance fetched from the buffer (or None if the buffer is non-trigger and not ready).
Returns: The output message of the node which will be send to all registered output buffers.
Return type: Message