我正在尝试将Keras模型保存在H5文件中。 Keras模型具有自定义层。 当我尝试还原模型时，出现以下错误：
---------------------------------------------------------------------------
ValueError Traceback (most recent call last)
<ipython-input-5-0fbff9b56a9d> in <module>()
1 model.save('model.h5')
2 del model
----> 3 model = tf.keras.models.load_model('model.h5')
8 frames
/usr/local/lib/python3.6/dist-packages/tensorflow/python/keras/utils/generic_utils.py in class_and_config_for_serialized_keras_object(config, module_objects, custom_objects, printable_module_name)
319 cls = get_registered_object(class_name, custom_objects, module_objects)
320 if cls is None:
--> 321 raise ValueError('Unknown ' + printable_module_name + ': ' + class_name)
322
323 cls_config = config['config']
ValueError: Unknown layer: CustomLayer
您能告诉我如何保存和加载所有自定义Keras图层的权重吗？ （此外，保存时没有警告，是否可以从我已经保存但现在无法加载的H5文件中加载模型？）
以下是此错误的最小工作代码示例（MCVE），以及完整的扩展消息：Google Colab Notebook
为了完整起见，这是我用来制作自定义图层的代码。
get_config和from_config都可以正常工作。
class CustomLayer(tf.keras.layers.Layer):
def __init__(self, k, name=None):
super(CustomLayer, self).__init__(name=name)
self.k = k
def get_config(self):
return {'k': self.k}
def call(self, input):
return tf.multiply(input, 2)
model = tf.keras.models.Sequential([
tf.keras.Input(name='input_layer', shape=(10,)),
CustomLayer(10, name='custom_layer'),
tf.keras.layers.Dense(1, activation='sigmoid', name='output_layer')
])
model.save('model.h5')
model = tf.keras.models.load_model('model.h5')
答案 0 :(得分：3)
您可以按照答案https://stackoverflow.com/a/62326857/8056572中所述，在custom_objects方法中手动提供映射load_model，但是当您有很多自定义图层（或任何自定义可调用对象）时，这可能很乏味定义的指标，例如指标，损失，优化工具...）。
Tensorflow提供了一个utils函数来自动执行此操作：tf.keras.utils.register_keras_serializable
您必须按照以下步骤更新CustomLayer：
import tensorflow as tf
@tf.keras.utils.register_keras_serializable()
class CustomLayer(tf.keras.layers.Layer):
def __init__(self, k, **kwargs):
self.k = k
super(CustomLayer, self).__init__(**kwargs)
def get_config(self):
config = super().get_config()
config["k"] = self.k
return config
def call(self, input):
return tf.multiply(input, 2)
这是完整的工作代码：
import tensorflow as tf
@tf.keras.utils.register_keras_serializable()
class CustomLayer(tf.keras.layers.Layer):
def __init__(self, k, **kwargs):
self.k = k
super(CustomLayer, self).__init__(**kwargs)
def get_config(self):
config = super().get_config()
config["k"] = self.k
return config
def call(self, input):
return tf.multiply(input, 2)
def main():
model = tf.keras.models.Sequential(
[
tf.keras.Input(name='input_layer', shape=(10,)),
CustomLayer(10, name='custom_layer'),
tf.keras.layers.Dense(1, activation='sigmoid', name='output_layer')
]
)
print("SUMMARY OF THE MODEL CREATED")
print("-" * 60)
print(model.summary())
model.save('model.h5')
del model
print()
print()
model = tf.keras.models.load_model('model.h5')
print("SUMMARY OF THE MODEL LOADED")
print("-" * 60)
print(model.summary())
if __name__ == "__main__":
main()
和相应的输出：
SUMMARY OF THE MODEL CREATED
------------------------------------------------------------
Model: "sequential"
_________________________________________________________________
Layer (type) Output Shape Param #
=================================================================
custom_layer (CustomLayer) (None, 10) 0
_________________________________________________________________
output_layer (Dense) (None, 1) 11
=================================================================
Total params: 11
Trainable params: 11
Non-trainable params: 0
_________________________________________________________________
None
WARNING:tensorflow:No training configuration found in the save file, so the model was *not* compiled. Compile it manually.
SUMMARY OF THE MODEL LOADED
------------------------------------------------------------
Model: "sequential"
_________________________________________________________________
Layer (type) Output Shape Param #
=================================================================
custom_layer (CustomLayer) (None, 10) 0
_________________________________________________________________
output_layer (Dense) (None, 1) 11
=================================================================
Total params: 11
Trainable params: 11
Non-trainable params: 0
_________________________________________________________________
None
答案 1 :(得分：2)
更正数字1是使用Custom_Objects，而loading是Saved Model，即替换代码，
new_model = tf.keras.models.load_model('model.h5')
与
new_model = tf.keras.models.load_model('model.h5', custom_objects={'CustomLayer': CustomLayer})
由于我们正在使用Custom Layers至build Model，并且在Saving之前，我们应该在Custom Objects的同时使用Loading。 / p>
更正数字2是在自定义层的**kwargs功能中添加__init__，例如
def __init__(self, k, name=None, **kwargs):
super(CustomLayer, self).__init__(name=name)
self.k = k
super(CustomLayer, self).__init__(**kwargs)
完整的工作代码如下所示：
import tensorflow as tf
class CustomLayer(tf.keras.layers.Layer):
def __init__(self, k, name=None, **kwargs):
super(CustomLayer, self).__init__(name=name)
self.k = k
super(CustomLayer, self).__init__(**kwargs)
def get_config(self):
config = super(CustomLayer, self).get_config()
config.update({"k": self.k})
return config
def call(self, input):
return tf.multiply(input, 2)
model = tf.keras.models.Sequential([
tf.keras.Input(name='input_layer', shape=(10,)),
CustomLayer(10, name='custom_layer'),
tf.keras.layers.Dense(1, activation='sigmoid', name='output_layer')
])
tf.keras.models.save_model(model, 'model.h5')
new_model = tf.keras.models.load_model('model.h5', custom_objects={'CustomLayer': CustomLayer})
print(new_model.summary())
以上代码的输出如下所示：
WARNING:tensorflow:No training configuration found in the save file, so the model was *not* compiled. Compile it manually.
Model: "sequential_1"
_________________________________________________________________
Layer (type) Output Shape Param #
=================================================================
custom_layer_1 (CustomLayer) (None, 10) 0
_________________________________________________________________
output_layer (Dense) (None, 1) 11
=================================================================
Total params: 11
Trainable params: 11
Non-trainable params: 0
希望这会有所帮助。学习愉快！