加载预训练模型会引发ValueError:封送处理数据错误（未知类型代码）

Question

File "train.py", line 43, in <module>
    FR=FR_model()
  File "/home/arsh/Desktop/machine learning/Outlier_dataset/Face_recognition.py", line 19, in __init__
    self.model = load_model('Facenet/facenet_model.h5')
  File "/home/arsh/.virtualenvs/conditional_slim_gan/lib/python3.8/site-packages/tensorflow/python/keras/saving/save.py", line 184, in load_model
    return hdf5_format.load_model_from_hdf5(filepath, custom_objects, compile)
  File "/home/arsh/.virtualenvs/conditional_slim_gan/lib/python3.8/site-packages/tensorflow/python/keras/saving/hdf5_format.py", line 177, in load_model_from_hdf5
    model = model_config_lib.model_from_config(model_config,
  File "/home/arsh/.virtualenvs/conditional_slim_gan/lib/python3.8/site-packages/tensorflow/python/keras/saving/model_config.py", line 55, in model_from_config
    return deserialize(config, custom_objects=custom_objects)
  File "/home/arsh/.virtualenvs/conditional_slim_gan/lib/python3.8/site-packages/tensorflow/python/keras/layers/serialization.py", line 105, in deserialize
    return deserialize_keras_object(
  File "/home/arsh/.virtualenvs/conditional_slim_gan/lib/python3.8/site-packages/tensorflow/python/keras/utils/generic_utils.py", line 369, in deserialize_keras_object
    return cls.from_config(
  File "/home/arsh/.virtualenvs/conditional_slim_gan/lib/python3.8/site-packages/tensorflow/python/keras/engine/network.py", line 986, in from_config
    input_tensors, output_tensors, created_layers = reconstruct_from_config(
  File "/home/arsh/.virtualenvs/conditional_slim_gan/lib/python3.8/site-packages/tensorflow/python/keras/engine/network.py", line 2019, in reconstruct_from_config
    process_layer(layer_data)
  File "/home/arsh/.virtualenvs/conditional_slim_gan/lib/python3.8/site-packages/tensorflow/python/keras/engine/network.py", line 2001, in process_layer
    layer = deserialize_layer(layer_data, custom_objects=custom_objects)
  File "/home/arsh/.virtualenvs/conditional_slim_gan/lib/python3.8/site-packages/tensorflow/python/keras/layers/serialization.py", line 105, in deserialize
    return deserialize_keras_object(
  File "/home/arsh/.virtualenvs/conditional_slim_gan/lib/python3.8/site-packages/tensorflow/python/keras/utils/generic_utils.py", line 369, in deserialize_keras_object
    return cls.from_config(
  File "/home/arsh/.virtualenvs/conditional_slim_gan/lib/python3.8/site-packages/tensorflow/python/keras/layers/core.py", line 990, in from_config
    function = cls._parse_function_from_config(
  File "/home/arsh/.virtualenvs/conditional_slim_gan/lib/python3.8/site-packages/tensorflow/python/keras/layers/core.py", line 1042, in _parse_function_from_config
    function = generic_utils.func_load(
  File "/home/arsh/.virtualenvs/conditional_slim_gan/lib/python3.8/site-packages/tensorflow/python/keras/utils/generic_utils.py", line 471, in func_load
    code = marshal.loads(raw_code)
ValueError: bad marshal data (unknown type code)

我正在尝试使用代码从.h5文件加载一个经过预训练的keras模型- self.model = load_model('Facenet/facenet_model.h5')

代码在GoogleColab上运行平稳，但是当我在本地运行它时，它会抛出上述错误，即使我的tensorflow和keras是最新的

要重现错误，请导航到my github存储库上的Face_recognition.py

Answer 1

如果您查看generic_utils.py的源代码：

https://github.com/keras-team/keras/blob/master/keras/utils/generic_utils.py

您将看到没有第471行，因此您似乎正在运行一些旧的keras实例，这些实例可能与使用较新（或只是不同）版本生成的数据不兼容