crashing Edgetpu Accelerator with multi-thread access

multi_crash.py

import argparse
from edgetpu.classification.engine import ClassificationEngine
from edgetpu.utils import dataset_utils
from PIL import Image
import multiprocessing
from multiprocessing import Process

def main():
  parser = argparse.ArgumentParser()
  parser.add_argument(
      '--model', help='File path of Tflite model.', required=True)
  parser.add_argument('--label', help='File path of label file.', required=True)
  parser.add_argument(
      '--image', help='File path of the image to be recognized.', required=True)
  args = parser.parse_args()

  # Prepare labels.
  labels = dataset_utils.read_label_file(args.label)
  # Initialize engine.
  # Run inference.
  img = Image.open(args.image)
  def f(args, img):
      engine = ClassificationEngine(args.model)
      for result in engine.ClassifyWithImage(img, top_k=3):
        print('---------------------------')
        print(labels[result[0]])
        print('Score : ', result[1])
  p1 = Process(target=f, args=(args, img))
  p2 = Process(target=f, args=(args, img))
  p3 = Process(target=f, args=(args, img))
  p4 = Process(target=f, args=(args, img))
  p1.start()
  p2.start()
  p3.start()
  p4.start()
  p1.join()
  p2.join()
  p3.join()
  p4.join()

if __name__ == '__main__':
  main()