如何从 .h5 文件正确加载带有自定义层的 Keras 模型？

Question

我构建了一个带有自定义层的 Keras 模型，并通过回调 ModelCheckPoint 将其保存到 .h5 文件中。当我在训练后尝试加载此模型时，出现以下错误消息：

__init__() missing 1 required positional argument: 'pool_size'

这是自定义层的定义及其__init__方法：

class MyMeanPooling(Layer):
    def __init__(self, pool_size, axis=1, **kwargs):
        self.supports_masking = True
        self.pool_size = pool_size
        self.axis = axis
        self.y_shape = None
        self.y_mask = None
        super(MyMeanPooling, self).__init__(**kwargs)

这就是我将这一层添加到我的模型中的方式：

x = MyMeanPooling(globalvars.pool_size)(x)

这是我加载模型的方式：

from keras.models import load_model

model = load_model(model_path, custom_objects={'MyMeanPooling': MyMeanPooling})

这些是完整的错误信息：

Traceback (most recent call last):
  File "D:/My Projects/Attention_BLSTM/script3.py", line 9, in <module>
    model = load_model(model_path, custom_objects={'MyMeanPooling': MyMeanPooling})
  File "D:\ProgramData\Anaconda3\envs\tf\lib\site-packages\keras\engine\saving.py", line 419, in load_model
    model = _deserialize_model(f, custom_objects, compile)
  File "D:\ProgramData\Anaconda3\envs\tf\lib\site-packages\keras\engine\saving.py", line 225, in _deserialize_model
    model = model_from_config(model_config, custom_objects=custom_objects)
  File "D:\ProgramData\Anaconda3\envs\tf\lib\site-packages\keras\engine\saving.py", line 458, in model_from_config
    return deserialize(config, custom_objects=custom_objects)
  File "D:\ProgramData\Anaconda3\envs\tf\lib\site-packages\keras\layers\__init__.py", line 55, in deserialize
    printable_module_name='layer')
  File "D:\ProgramData\Anaconda3\envs\tf\lib\site-packages\keras\utils\generic_utils.py", line 145, in deserialize_keras_object
    list(custom_objects.items())))
  File "D:\ProgramData\Anaconda3\envs\tf\lib\site-packages\keras\engine\network.py", line 1022, in from_config
    process_layer(layer_data)
  File "D:\ProgramData\Anaconda3\envs\tf\lib\site-packages\keras\engine\network.py", line 1008, in process_layer
    custom_objects=custom_objects)
  File "D:\ProgramData\Anaconda3\envs\tf\lib\site-packages\keras\layers\__init__.py", line 55, in deserialize
    printable_module_name='layer')
  File "D:\ProgramData\Anaconda3\envs\tf\lib\site-packages\keras\utils\generic_utils.py", line 147, in deserialize_keras_object
    return cls.from_config(config['config'])
  File "D:\ProgramData\Anaconda3\envs\tf\lib\site-packages\keras\engine\base_layer.py", line 1109, in from_config
    return cls(**config)
TypeError: __init__() missing 1 required positional argument: 'pool_size'

Answer 1

来自 "LiamHe commented on Sep 27, 2017" 对以下问题的回答：https://github.com/keras-team/keras/issues/4871。

我今天遇到了同样的问题：**类型错误：init() 缺少 1 个必需的位置参数**。这是我解决问题的方法：(Keras 2.0.2)

为层的位置参数提供一些默认值
用

def get_config(self):
    config = super().get_config()
    config['pool_size'] = # say self._pool_size  if you store the argument in __init__
    return config

加载模型时将图层 class 添加到 custom_objects。

Answer 2

其实我不认为你可以加载这个模型。

最有可能的问题是您没有在层中实现 get_config() 方法。此方法 returns 应保存的配置值字典：

def get_config(self):
    config = {'pool_size': self.pool_size,
              'axis': self.axis}
    base_config = super(MyMeanPooling, self).get_config()
    return dict(list(base_config.items()) + list(config.items()))

将此方法添加到图层后，您必须重新训练模型，因为之前保存的模型没有保存此图层的配置。这就是为什么你不能加载它的原因，它需要在进行此更改后重新训练。

Answer 3

如果您没有足够的时间以 Matias Valdenegro 的解决方案方式重新训练模型。可以在classMyMeanPooling中设置pool_size的默认值，如下代码。注意pool_size的值要和训练模型时的值保持一致。然后就可以加载模型了。

class MyMeanPooling(Layer):
    def __init__(self, pool_size, axis=1, **kwargs):
        self.supports_masking = True
        self.pool_size = 2  # The value should be consistent with the value while training the model
        self.axis = axis
        self.y_shape = None
        self.y_mask = None
        super(MyMeanPooling, self).__init__(**kwargs)

参考：https://www.jianshu.com/p/e97112c34e43

如何从 .h5 文件正确加载带有自定义层的 Keras 模型？

How to load the Keras model with custom layers from .h5 file correctly?

python-3.x

keras

keras-layer