無法使用tf.train.Saver還原模型中的變量

Question

我的計算機的一些信息：系統：Windows10。IDE：Spyder3（Anaconda / python3.5.2）。 TensorFlow版本：r1.1（cpu）

以下是我的問題：

在我訓練了CNN模型（training.py）之后。 我使用tf.train.Saver保存模型變量。 我想將它們還原到另一個文件（testing.py）中以測試測試數據集。 我已經嘗試了很多次，但是alwaws無法還原Variable。 例如，我嘗試了一個示例（兩個文件：save.py和restore.py）：

import tensorflow as tf
w1 = tf.Variable(tf.random_normal(shape=[2]), name='w1')
w2 = tf.Variable(tf.random_normal(shape=[5]), name='w2')
saver = tf.train.Saver()
sess = tf.Session()
sess.run(tf.global_variables_initializer())
print(sess.run(w1))
print(sess.run(w2))
saver.save(sess, "./model")

import tensorflow as tf
w1 = tf.Variable(tf.random_normal(shape=[2]), name='w1')
w2 = tf.Variable(tf.random_normal(shape=[5]), name='w2')
saver = tf.train.Saver()
sess = tf.Session()
saver.restore(sess, "./model")
print(sess.run(w1))
print(sess.run(w2))

當我運行restore.py時，它出錯了：

INFO:tensorflow:Restoring parameters from ./model
Traceback (most recent call last):

  File "<ipython-input-2-cb3aa43151bc>", line 1, in <module>
    runfile('F:/tensorflow/saver_test/tensor_restore.py', wdir='F:/tensorflow/saver_test')

  File "D:\Anaconda3\lib\site-packages\spyder\utils\site\sitecustomize.py", line 866, in runfile
    execfile(filename, namespace)

  File "D:\Anaconda3\lib\site-packages\spyder\utils\site\sitecustomize.py", line 102, in execfile
    exec(compile(f.read(), filename, 'exec'), namespace)

  File "F:/tensorflow/saver_test/tensor_restore.py", line 7, in <module>
    saver.restore(sess, "./model")

  File "D:\Anaconda3\lib\site-packages\tensorflow\python\training\saver.py", line 1457, in restore
    {self.saver_def.filename_tensor_name: save_path})

  File "D:\Anaconda3\lib\site-packages\tensorflow\python\client\session.py", line 778, in run
    run_metadata_ptr)

  File "D:\Anaconda3\lib\site-packages\tensorflow\python\client\session.py", line 982, in _run
    feed_dict_string, options, run_metadata)

  File "D:\Anaconda3\lib\site-packages\tensorflow\python\client\session.py", line 1032, in _do_run
    target_list, options, run_metadata)

  File "D:\Anaconda3\lib\site-packages\tensorflow\python\client\session.py", line 1052, in _do_call
    raise type(e)(node_def, op, message)

NotFoundError: Key w1_1 not found in checkpoint
     [[Node: save_1/RestoreV2_1 = RestoreV2[dtypes=[DT_FLOAT], _device="/job:localhost/replica:0/task:0/cpu:0"](_recv_save_1/Const_0, save_1/RestoreV2_1/tensor_names, save_1/RestoreV2_1/shape_and_slices)]]

Caused by op 'save_1/RestoreV2_1', defined at:
  File "D:\Anaconda3\lib\site-packages\spyder\utils\ipython\start_kernel.py", line 223, in <module>
    main()
  File "D:\Anaconda3\lib\site-packages\spyder\utils\ipython\start_kernel.py", line 219, in main
    kernel.start()
  File "D:\Anaconda3\lib\site-packages\ipykernel\kernelapp.py", line 474, in start
    ioloop.IOLoop.instance().start()
  File "D:\Anaconda3\lib\site-packages\zmq\eventloop\ioloop.py", line 162, in start
    super(ZMQIOLoop, self).start()
  File "D:\Anaconda3\lib\site-packages\tornado\ioloop.py", line 887, in start
    handler_func(fd_obj, events)
  File "D:\Anaconda3\lib\site-packages\tornado\stack_context.py", line 275, in null_wrapper
    return fn(*args, **kwargs)
  File "D:\Anaconda3\lib\site-packages\zmq\eventloop\zmqstream.py", line 440, in _handle_events
    self._handle_recv()
  File "D:\Anaconda3\lib\site-packages\zmq\eventloop\zmqstream.py", line 472, in _handle_recv
    self._run_callback(callback, msg)
  File "D:\Anaconda3\lib\site-packages\zmq\eventloop\zmqstream.py", line 414, in _run_callback
    callback(*args, **kwargs)
  File "D:\Anaconda3\lib\site-packages\tornado\stack_context.py", line 275, in null_wrapper
    return fn(*args, **kwargs)
  File "D:\Anaconda3\lib\site-packages\ipykernel\kernelbase.py", line 276, in dispatcher
    return self.dispatch_shell(stream, msg)
  File "D:\Anaconda3\lib\site-packages\ipykernel\kernelbase.py", line 228, in dispatch_shell
    handler(stream, idents, msg)
  File "D:\Anaconda3\lib\site-packages\ipykernel\kernelbase.py", line 390, in execute_request
    user_expressions, allow_stdin)
  File "D:\Anaconda3\lib\site-packages\ipykernel\ipkernel.py", line 196, in do_execute
    res = shell.run_cell(code, store_history=store_history, silent=silent)
  File "D:\Anaconda3\lib\site-packages\ipykernel\zmqshell.py", line 501, in run_cell
    return super(ZMQInteractiveShell, self).run_cell(*args, **kwargs)
  File "D:\Anaconda3\lib\site-packages\IPython\core\interactiveshell.py", line 2717, in run_cell
    interactivity=interactivity, compiler=compiler, result=result)
  File "D:\Anaconda3\lib\site-packages\IPython\core\interactiveshell.py", line 2827, in run_ast_nodes
    if self.run_code(code, result):
  File "D:\Anaconda3\lib\site-packages\IPython\core\interactiveshell.py", line 2881, in run_code
    exec(code_obj, self.user_global_ns, self.user_ns)
  File "<ipython-input-2-cb3aa43151bc>", line 1, in <module>
    runfile('F:/tensorflow/saver_test/tensor_restore.py', wdir='F:/tensorflow/saver_test')
  File "D:\Anaconda3\lib\site-packages\spyder\utils\site\sitecustomize.py", line 866, in runfile
    execfile(filename, namespace)
  File "D:\Anaconda3\lib\site-packages\spyder\utils\site\sitecustomize.py", line 102, in execfile
    exec(compile(f.read(), filename, 'exec'), namespace)
  File "F:/tensorflow/saver_test/tensor_restore.py", line 5, in <module>
    saver = tf.train.Saver()
  File "D:\Anaconda3\lib\site-packages\tensorflow\python\training\saver.py", line 1056, in __init__
    self.build()
  File "D:\Anaconda3\lib\site-packages\tensorflow\python\training\saver.py", line 1086, in build
    restore_sequentially=self._restore_sequentially)
  File "D:\Anaconda3\lib\site-packages\tensorflow\python\training\saver.py", line 691, in build
    restore_sequentially, reshape)
  File "D:\Anaconda3\lib\site-packages\tensorflow\python\training\saver.py", line 407, in _AddRestoreOps
    tensors = self.restore_op(filename_tensor, saveable, preferred_shard)
  File "D:\Anaconda3\lib\site-packages\tensorflow\python\training\saver.py", line 247, in restore_op
    [spec.tensor.dtype])[0])
  File "D:\Anaconda3\lib\site-packages\tensorflow\python\ops\gen_io_ops.py", line 669, in restore_v2
    dtypes=dtypes, name=name)
  File "D:\Anaconda3\lib\site-packages\tensorflow\python\framework\op_def_library.py", line 768, in apply_op
    op_def=op_def)
  File "D:\Anaconda3\lib\site-packages\tensorflow\python\framework\ops.py", line 2336, in create_op
    original_op=self._default_original_op, op_def=op_def)
  File "D:\Anaconda3\lib\site-packages\tensorflow\python\framework\ops.py", line 1228, in __init__
    self._traceback = _extract_stack()

NotFoundError (see above for traceback): Key w1_1 not found in checkpoint
     [[Node: save_1/RestoreV2_1 = RestoreV2[dtypes=[DT_FLOAT], _device="/job:localhost/replica:0/task:0/cpu:0"](_recv_save_1/Const_0, save_1/RestoreV2_1/tensor_names, save_1/RestoreV2_1/shape_and_slices)]]

我已經嘗試了好幾天來解決它，但是失敗了，我的代碼找不到任何錯誤。 謝謝！！！

Answer 1

保存訓練好的模型后，您是否看到一個后綴名為.meta的文件？ 如果是這樣，則在恢復時，不要通過調用以下命令來創建保護程序：saver = tf.train.Saver（）。 而是嘗試通過調用tf.train.import_meta_graph（）方法來創建您的保護程序。

當您嘗試從頭開始創建圖形時，很可能某些變量的名稱不同，因此無法恢復已保存的數據。