darcyai.perceptor.cpu.image_classification_perceptor

ImageClassificationPerceptor Objects

class ImageClassificationPerceptor(CpuPerceptorBase)

ImageClassificationPerceptor is a class that implements the Perceptor interface for image classification.

Arguments

  • threshold (float): The threshold for object detection.
  • top_k (int): The number of top predictions to return.
  • 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[Class]

Runs the image classification model.

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 classes and the labels.

load

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

Loads the image classification model.

Arguments

  • accelerator_idx (int): Not used.