我正在尝试使用C ++ API在Tensorflow中运行从Keras导出的模型。该模型已正确导出和导入，但是当我尝试在C ++中运行会话时，我在get Run成员中传递的变量名称tensorflow::Session被修改，从而导致错误：
Invalid argument: Tensor Output0:0, specified in either feed_devices or fetch_devices was not found in the Graph
这是我在Keras中建立的模型：
Invalid argument: Tensor Output0:0, specified in either feed_devices or fetch_devices was not found in the Graph
遵循https://github.com/amir-abdi/keras_to_tensorflow中实现的方法，使用tensorflow.python.framework.graph_util
和导出模型tensorflow.python.framework.graph_io
然后使用C ++ API将模型导入Tensorflow：
S = Input(shape=[state_size], name='Input')
h0 = Dense(self.HIDDEN1_UNITS, name='Hidden1', kernel_initializer=keras.initializers.RandomUniform())(S)
h0_a = Activation('relu')(h0)
h1 = Dense(self.HIDDEN2_UNITS, name='Hidden2', kernel_initializer=keras.initializers.RandomUniform())(h0_a)
h1_a = Activation('relu')(h1)
output = Dense(1)(h1_a)
output_a = Activation('tanh', name='Output0')(output)
model = Model(S,output_a) …