darcyai.perceptor.cpu.object_detection_perceptor

ObjectDetectionPerceptor Objects

class ObjectDetectionPerceptor(CpuPerceptorBase)

ObjectDetectionPerceptor is a class that implements the Perceptor interface for object detection.

Arguments

  • threshold (float): The threshold for object detection.
  • labels_file (str): The path to the labels file.
  • labels (dict): A dictionary of labels.
  • quantized (bool): Whether the model is quantized.
  • num_cpu_threads (int): The number of threads to use for inference (CPU). Defaults to 1.

run

def run(input_data: Any, config: ConfigRegistry = None) -> List[Object]

Runs the object detection model on the input data.

Arguments

  • input_data (Any): The input data to run the model on.
  • config (ConfigRegistry): The configuration for the Perceptor.

Returns

(list[Any], list(str)): A tuple containing the detected objects and the labels.

load

def load(accelerator_idx: [int, None] = None) -> None

Loads the object detection model.

Arguments

  • accelerator_idx (int): Not used.