使用元图张量流运行模型失败

Question

我已经尝试在程序中加载模型，以便可以实时运行它。
以下是我正在尝试的方式：
储蓄者 =

tf.train.import_meta_graph(tf.train.latest_checkpoint(model_path)+".meta")
graph = tf.get_default_graph()
outputs = graph.get_operation_by_name('output')
native = graph.get_operation_by_name('input')
sess  = tf.Session()
sess.run(tf.global_variables_initializer())   
sess.run(tf.local_variables_initializer()) 
if(tf.train.checkpoint_exists(tf.train.latest_checkpoint(model_path))):
    saver.restore(sess, tf.train.latest_checkpoint(model_path))
    print(tf.train.latest_checkpoint(model_path) + "Session Loaded for Testing")  

我试图得到输出：

y_test_output= sess.run(outputs, feed_dict={native: x_test})

我收到以下错误：

Traceback (most recent call last):
  File "testing_reality.py", line 90, in <module>
    main()
  File "testing_reality.py", line 62, in main
    handle_client_connection(client_sock)
  File "testing_reality.py", line 45, in handle_client_connection
    y_train_pred= sess.run(outputs, feed_dict={native: x_test})
  File "C:\Python35\lib\site-packages\tensorflow\python\client\session.py", line 929, in run
    run_metadata_ptr)
  File "C:\Python35\lib\site-packages\tensorflow\python\client\session.py", line 1095, in _run
    'Cannot interpret feed_dict key as Tensor: ' + e.args[0])
TypeError: Cannot interpret feed_dict key as Tensor: Can not convert a Operation into a Tensor.

请让我知道我在这种情况下缺少什么。
在 Windows 10 上使用最新版本的 Tensorflow '1.12.0'。

Answer 1

feed_dict 中的 keys 必须是占位符。该错误表明您使用Operation 作为feed_dict 中的键。如果input 变量确实是placeholder，则按以下方式加载它：

native = graph.get_tensor_by_name("input:0")

outputs 也是如此：

outputs = graph.get_tensor_by_name("output:0")