连接两个不同图形张量流的输入和输出张量

我有2个ProtoBuf文件,我目前正在加载和转发,分别通过调用 –

out1=session.run(graph1out, feed_dict={graph1inp:inp1})

其次是

final=session.run(graph2out, feed_dict={graph2inp:out1})

其中graph1inp和graph1out是图1的输入节点和输出节点,图2的类似术语

现在,我想将graph1out与graph2inp连接起来,这样我只需要在使用inp1提供graph1inp时运行graph2out.换句话说,连接2个相关图形的输入和输出张量,使得一次运行足以在两个训练的ProtoBuf文件上运行推理.

假设您的Protobuf文件包含序列化的 tf.GraphDef原型,您可以使用 tf.import_graph_def()的input_map参数连接两个图：

# Import graph1.
graph1_def = ...  # tf.GraphDef object
out1_name = "..."  # name of the graph1out tensor in graph1_def.
graph1out, = tf.import_graph_def(graph1_def, return_elements=[out_name])

# Import graph2 and connect it to graph1.
graph2_def = ...  # tf.GraphDef object
inp2_name = "..."  # name of the graph2inp tensor in graph2_def.
out2_name = "..."  # name of the graph2out tensor in graph2_def.
graph2out, = tf.import_graph_def(graph2_def, input_map={inp2_name: graph1out},
                                 return_elements=[out2_name])