Python 在两个线程中运行Keras模型

我想在两个单独的线程中运行tensorflow/keras模型（.json），但我遇到了以下错误：

if _SYMBOLIC_SCOPE.value:
AttributeError: '_thread._local' object has no attribute 'value'
terminate called without an active exception

有趣的是，我在另一台机器上使用的同一个脚本在相同的conda环境下正常工作，但在这台机器上，它出现故障，我找不到解决方案，我连续两天在谷歌上搜索，尝试了所有方法，但什么都不起作用，有人能帮忙吗： 以下是错误的完整回溯：

Traceback (most recent call last):
  File "/home/novapark/Desktop/alpr-unconstrained-master/VIDEO_DETECTION.py", line 74, in start_vlez
    Llp,LlpImgs,_ = detect_lp(wpod_net,im2single(frame),bound_dim,2**4,(240,80),lp_threshold)
  File "/home/novapark/Desktop/alpr-unconstrained-master/src/keras_utils.py", line 112, in detect_lp
    Yr      = model.predict(T)
  File "/home/novapark/anaconda3/envs/tf-cpu/lib/python3.7/site-packages/keras/engine/training.py", line 1452, in predict
    if self._uses_dynamic_learning_phase():
  File "/home/novapark/anaconda3/envs/tf-cpu/lib/python3.7/site-packages/keras/engine/training.py", line 382, in _uses_dynamic_learning_phase
    not isinstance(K.learning_phase(), int))
  File "/home/novapark/anaconda3/envs/tf-cpu/lib/python3.7/site-packages/keras/backend/tensorflow_backend.py", line 73, in symbolic_fn_wrapper
    if _SYMBOLIC_SCOPE.value:
AttributeError: '_thread._local' object has no attribute 'value'
Traceback (most recent call last):
  File "/home/novapark/Desktop/alpr-unconstrained-master/VIDEO_DETECTION.py", line 161, in start_izlez
    wpod_net = load_model(wpod_net_path)
  File "/home/novapark/Desktop/alpr-unconstrained-master/src/keras_utils.py", line 35, in load_model
    model = model_from_json(model_json, custom_objects=custom_objects)
  File "/home/novapark/anaconda3/envs/tf-cpu/lib/python3.7/site-packages/keras/engine/saving.py", line 664, in model_from_json
    return deserialize(config, custom_objects=custom_objects)
  File "/home/novapark/anaconda3/envs/tf-cpu/lib/python3.7/site-packages/keras/layers/__init__.py", line 168, in deserialize
    printable_module_name='layer')
  File "/home/novapark/anaconda3/envs/tf-cpu/lib/python3.7/site-packages/keras/utils/generic_utils.py", line 147, in deserialize_keras_object
    list(custom_objects.items())))
  File "/home/novapark/anaconda3/envs/tf-cpu/lib/python3.7/site-packages/keras/engine/network.py", line 1056, in from_config
    process_layer(layer_data)
  File "/home/novapark/anaconda3/envs/tf-cpu/lib/python3.7/site-packages/keras/engine/network.py", line 1042, in process_layer
    custom_objects=custom_objects)
  File "/home/novapark/anaconda3/envs/tf-cpu/lib/python3.7/site-packages/keras/layers/__init__.py", line 168, in deserialize
    printable_module_name='layer')
  File "/home/novapark/anaconda3/envs/tf-cpu/lib/python3.7/site-packages/keras/utils/generic_utils.py", line 149, in deserialize_keras_object
    return cls.from_config(config['config'])
  File "/home/novapark/anaconda3/envs/tf-cpu/lib/python3.7/site-packages/keras/engine/base_layer.py", line 1179, in from_config
    return cls(**config)
  File "/home/novapark/anaconda3/envs/tf-cpu/lib/python3.7/site-packages/keras/legacy/interfaces.py", line 91, in wrapper
    return func(*args, **kwargs)
  File "/home/novapark/anaconda3/envs/tf-cpu/lib/python3.7/site-packages/keras/engine/input_layer.py", line 87, in __init__
    name=self.name)
  File "/home/novapark/anaconda3/envs/tf-cpu/lib/python3.7/site-packages/keras/backend/tensorflow_backend.py", line 73, in symbolic_fn_wrapper
    if _SYMBOLIC_SCOPE.value:
AttributeError: '_thread._local' object has no attribute 'value'
terminate called without an active exception

Process finished with exit code 134 (interrupted by signal 6: SIGABRT)

以下是我如何称呼线程：

    wpod_net_path = ""Full Path"model.json"


    wpod_net = load_model(wpod_net_path)

    t = threading.Thread(target=start_vlez, args=(cam_vlez,)).start()

    t1 = threading.Thread(target=start_izlez, args=(cam_izlez,)).start()

PS：这是CPU版本，我也得到了Tensorflow的GPU版本