Обучение новой модели CFG и веса файла в Yolo

Question

Я пытаюсь обучить свой собственный набор данных.

python flow --model cfg/tiny-yolo-voc-2c.cfg --load bin/tiny-yolo-voc.weights --train --annotation new_model_data/annotations  --dataset new_model_data/images2 --gpu 0.8 --epoch 200

Я получил такую ​​ошибку:

Parsing ./cfg/tiny-yolo-voc.cfg
Parsing cfg/tiny-yolo-voc-2c.cfg
Traceback (most recent call last):
  File "flow", line 6, in <module>
    cliHandler(sys.argv)
  File "C:\Users\User\Desktop\Disease-detection\darkflow\cli.py", line 26, in cliHandler
    tfnet = TFNet(FLAGS)
  File "C:\Users\User\Desktop\Disease-detection\darkflow\net\build.py", line 58, in __init__
    darknet = Darknet(FLAGS)
  File "C:\Users\User\Desktop\Disease-detection\darkflow\dark\darknet.py", line 24, in __init__
    des_parsed = self.parse_cfg(FLAGS.model, FLAGS)
  File "C:\Users\User\Desktop\Disease-detection\darkflow\dark\darknet.py", line 70, in parse_cfg
    else: new = create_darkop(*info)
  File "C:\Users\User\Desktop\Disease-detection\darkflow\dark\darkop.py", line 60, in create_darkop
    return op_class(ltype, num, *args)
  File "C:\Users\User\Desktop\Disease-detection\darkflow\dark\layer.py", line 19, in __init__
    size = np.prod(shp)
  File "C:\Users\User\Anaconda3\lib\site-packages\numpy\core\fromnumeric.py", line 2566, in prod
    out=out, **kwargs)
  File "C:\Users\User\Anaconda3\lib\site-packages\numpy\core\_methods.py", line 35, in _prod
    return umr_prod(a, axis, dtype, out, keepdims)


TypeError: cannot perform reduce with flexible type

Кто-нибудь может мне помочь?Большое спасибо.