我有一个正在运行的模型，使用以下代码构建：
model = tf.keras.Model(inputs=input_layers, outputs=outputs)
如果我尝试向输出添加一个简单的常量，会得到一个错误消息。例如：
output = output + [tf.constant(['label1', 'label2'], dtype = tf.string)]model = tf.keras.Model(inputs=input_layers, outputs=outputs)错误消息： AttributeError: Tensor.op is meaningless when eager execution is enabled.
有没有办法在训练后或保存模型时将常量添加到模型中？
我的想法是在服务时将常量作为输出的一部分。
包含错误的完整网络示例：
import tensorflow as tfimport tensorflow.keras as kerasinput = keras.layers.Input(shape=(2,))hidden = keras.layers.Dense(10)(input)output = keras.layers.Dense(3, activation='sigmoid')(hidden)model = keras.models.Model(inputs=input, outputs=[output, tf.constant(['out1','out2','out3'], dtype=tf.string)])错误
in <module> 5 hidden = keras.layers.Dense(10)(input) 6 output = keras.layers.Dense(3, activation='sigmoid')(input)----> 7 model = keras.models.Model(inputs=input, outputs=[output, tf.constant(['out1','out2','out3'], dtype=tf.string)])/lib/python3.6/site-packages/tensorflow_core/python/keras/engine/training.py in __init__(self, *args, **kwargs) 144 145 def __init__(self, *args, **kwargs):--> 146 super(Model, self).__init__(*args, **kwargs) 147 _keras_api_gauge.get_cell('model').set(True) 148 # initializing _distribution_strategy here since it is possible to call/lib/python3.6/site-packages/tensorflow_core/python/keras/engine/network.py in __init__(self, *args, **kwargs) 165 'inputs' in kwargs and 'outputs' in kwargs): 166 # Graph network--> 167 self._init_graph_network(*args, **kwargs) 168 else: 169 # Subclassed network/lib/python3.6/site-packages/tensorflow_core/python/training/tracking/base.py in _method_wrapper(self, *args, **kwargs) 455 self._self_setattr_tracking = False # pylint: disable=protected-access 456 try:--> 457 result = method(self, *args, **kwargs) 458 finally: 459 self._self_setattr_tracking = previous_value # pylint: disable=protected-access/lib/python3.6/site-packages/tensorflow_core/python/keras/engine/network.py in _init_graph_network(self, inputs, outputs, name, **kwargs) 268 269 if any(not hasattr(tensor, '_keras_history') for tensor in self.outputs):--> 270 base_layer_utils.create_keras_history(self._nested_outputs) 271 272 self._base_init(name=name, **kwargs)/lib/python3.6/site-packages/tensorflow_core/python/keras/engine/base_layer_utils.py in create_keras_history(tensors) 182 keras_tensors: The Tensors found that came from a Keras Layer. 183 """--> 184 _, created_layers = _create_keras_history_helper(tensors, set(), []) 185 return created_layers 186 /lib/python3.6/site-packages/tensorflow_core/python/keras/engine/base_layer_utils.py in _create_keras_history_helper(tensors, processed_ops, created_layers) 208 if getattr(tensor, '_keras_history', None) is not None: 209 continue--> 210 op = tensor.op # The Op that created this Tensor. 211 if op not in processed_ops: 212 # Recursively set `_keras_history`./lib/python3.6/site-packages/tensorflow_core/python/framework/ops.py in op(self) 1078 def op(self): 1079 raise AttributeError(-> 1080 "Tensor.op is meaningless when eager execution is enabled.") 1081 1082 @propertyAttributeError: Tensor.op is meaningless when eager execution is enabled.使用Python 3.6和TensorFlow 2.0
回答：
将常量放入Lambda层中。Keras会进行一些额外的记录，因此仅使用tf操作是不够的。使用Lambda层可以解决这个问题。
编辑以提供如何操作的示例：您的最后一个示例将转换为以下代码
import tensorflow as tfimport tensorflow.keras as kerasinputs = keras.layers.Input(shape=(2,))hidden = keras.layers.Dense(10)(inputs)output1 = keras.layers.Dense(3, activation='sigmoid')(hidden)@tf.functiondef const(tensor): batch_size = tf.shape(tensor)[0] constant = tf.constant(['out1','out2','out3'], dtype=tf.string) constant = tf.expand_dims(constant, axis=0) return tf.broadcast_to(constant, shape=(batch_size, 3))output2 = keras.layers.Lambda(const)(inputs)model = keras.models.Model(inputs=inputs, outputs=[output1, output2])编辑：这让我想起了之前的一个项目，我在Keras模型中使用了很多常量。当时我为此编写了一个层
class ConstantOnBatch(keras.layers.Layer): def __init__(self, constant, *args, **kwargs): self._initial_constant = copy.deepcopy(constant) self.constant = K.constant(constant) self.out_shape = self.constant.shape.as_list() self.constant = tf.reshape(self.constant, [1]+self.out_shape) super().__init__(*args, **kwargs) def build(self, input_shape): super().build(input_shape) def call(self, inputs): batch_size = tf.shape(inputs)[0] output_shape = [batch_size]+self.out_shape return tf.broadcast_to(self.constant, output_shape) def compute_output_shape(self, input_shape): input_shape = input_shape.as_list() return [input_shape[0]]+self.out_shape def get_config(self): base_config = super().get_config() base_config['constant'] = self._initial_constant @classmethod def from_config(cls, config): return cls(**config)它可能需要更新到tf2，并且代码可以用更好的方式编写，但如果您需要很多常量，这可能会为使用大量Lambda层提供一个更优雅的解决方案的基础。
