darcyai.perceptor.object_detection_perceptor

ObjectDetectionPerceptor Objects

class ObjectDetectionPerceptor(MultiPlatformPerceptorBase)

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

__init__

def __init__(processor_preference: dict,
             threshold: float,
             quantized: bool = True,
             num_cpu_threads: int = 1)

Arguments

• processor_preference: A dictionary of processor preference. The key is the processor. Values are dictionaries of model paths and labels.
• threshold (float): The threshold for object detection.
• quantized (bool): Whether the model is quantized (CPU).
• num_cpu_threads (int): The number of threads to use for inference (CPU). Defaults to 1.

Example

from darcyai.perceptor.object_detection_perceptor import ObjectDetectionPerceptor
from darcyai.perceptor.processor import Processor
processor_preference = {
                           Processor.CORAL_EDGE_TPU: {
                               "model_path": "/path/to/model.tflite",
                               "labels_file": "/path/to/labels.txt",
                           },
                           Processor.CPU: {
                               "model_path": "/path/to/model.tflite",
                               "labels": {
                                   "label_1": "label_1_name",
                                   "label_2": "label_2_name",
                               },
                           },
                       }
object_detection_perceptor = ObjectDetectionPerceptor(
    processor_preference=processor_preference,
    threshold=0.5,
    top_k=5)