如何在 Keras 的输出中添加 tf.constant

Question

我有一个正在运行的模型，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，则会收到一条错误消息。前任：

output = output + [tf.constant(['label1', 'label2'], dtype = tf.string)]
model = tf.keras.Model(inputs=input_layers, outputs=outputs)

错误信息 ： AttributeError: Tensor.op is meaningless when eager execution is enabled.

有没有办法将它添加到模型中，即使在训练之后或在 save() 时间。

这个想法是在服务时间将常量作为输出。

带有错误的完整网络示例：

import tensorflow as tf
import tensorflow.keras as keras

input = 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   @property

AttributeError: Tensor.op is meaningless when eager execution is enabled.

使用 Python 3.6 和 Tensorflow 2.0

Answer 1

将常量放在 Lambda 层中。Keras 会做一些额外的记账，因此您需要的不仅仅是 tf 操作才能使事情工作。使用 Lambda 层将为您做到这一点。

编辑以举例说明其工作原理：您的最后一个示例将转换为以下代码

import tensorflow as tf
import tensorflow.keras as keras

inputs = keras.layers.Input(shape=(2,))
hidden = keras.layers.Dense(10)(inputs)
output1 = keras.layers.Dense(3, activation='sigmoid')(hidden)

@tf.function
def 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：这让我想起了我之前的一个项目，我不得不在 Keras 模型中使用很多常量。那时我为它写了一个层

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)

它可能需要对 tf2 进行一些更新，并且代码肯定可以以更好的方式编写，但是如果您需要大量常量，这可能为比使用大量 Lambda 层更优雅的解决方案提供基础。