时间戳

首页 > 解决方案 > 在张量流中恢复模型时出现FailedPreconditionError

python-3.x - 在张量流中恢复模型时出现FailedPreconditionError

问题描述

成功训练模型后，我无法恢复它。这种方法以前可以工作，但不知何故它给出了一个错误“FailedPreconditionError”。Tensorflow 应该在保存时存储了所有变量，所以我不确定错误的原因。

我在训练期间保存了模型，并尝试稍后使用保存和恢复选项进行恢复。


validation_accuracy_track = []
train_accuracy_track = []
connection_probability_track = []
number_of_ex = X_train.shape[0]
total_steps_for_one_pass = number_of_ex//BATCH_SIZE + 1

print_every = 10
with tf.Session() as sess:
    sess.run(tf.global_variables_initializer())
    num_examples = len(X_train)
    best_accuracy_valid = 0
    print("Training...")
    print()
    for i in range(EPOCHS):
        X_train, y_train = shuffle(X_train, y_train)
        for step in range(0, total_steps_for_one_pass):        
          if step>=number_of_ex//BATCH_SIZE:
            batch_x, batch_y = X_train[step*BATCH_SIZE:,:],y_train[step*BATCH_SIZE:]
            step = 0
          else:
            start = step*BATCH_SIZE
            finish = (step+1)*BATCH_SIZE
            batch_x, batch_y = X_train[step:finish,:],y_train[step:finish]
          tr_op  = sess.run([training_operation], feed_dict={x: batch_x, y: batch_y, is_testing : False})
        prob = sess.run(new_prob)
        if i%print_every == 0:
          tr_accuracy = sess.run(accuracy*100, feed_dict={x: X_train,y:y_train, is_testing: True})  # evaluate(X_train, y_train)
          print("Train Accuracy = {:.5f}".format(tr_accuracy))
          validation_accuracy = sess.run(accuracy*100, feed_dict={x: validation_data,y:validation_label_one_hot, is_testing: True}) #evaluate(X_validation, y_validation)
          validation_accuracy_track.append(validation_accuracy)
          train_accuracy_track.append(tr_accuracy)
          connection_probability_track.append(prob)
          print("EPOCH {} ...".format(i+1))
          print("Validation Accuracy = {:.5f}".format(validation_accuracy))
          print(prob)
          print()
          if (validation_accuracy >= best_accuracy_valid):
            best_accuracy_valid = validation_accuracy
            saver.save(sess, './PendigitSGDBased')

    saver.save(sess, './lenet')
    print("Model saved")

这是训练时的输出

Training...

Train Accuracy = 99.94996
EPOCH 1 ...
Validation Accuracy = 99.26617
0.83325

Train Accuracy = 99.93328
EPOCH 11 ...
Validation Accuracy = 99.13275
0.1345745

Train Accuracy = 99.94996
EPOCH 21 ...
Validation Accuracy = 99.53302
0.021734525

Train Accuracy = 99.96664
EPOCH 31 ...
Validation Accuracy = 99.59973
0.0035102463

Train Accuracy = 99.96664
EPOCH 41 ...
Validation Accuracy = 99.59973
0.0005669242

Model saved

恢复时我得到了这个

with tf.Session() as sess:
  saver.restore(sess, './lenet')
  sess.run(accuracy*100, feed_dict={x: validation_data,y:validation_label_one_hot, is_testing: True})

这是错误

INFO:tensorflow:Restoring parameters from ./lenet
---------------------------------------------------------------------------
FailedPreconditionError                   Traceback (most recent call last)
/usr/local/lib/python3.6/dist-packages/tensorflow/python/client/session.py in _do_call(self, fn, *args)
   1333     try:
-> 1334       return fn(*args)
   1335     except errors.OpError as e:

6 frames
/usr/local/lib/python3.6/dist-packages/tensorflow/python/client/session.py in _run_fn(feed_dict, fetch_list, target_list, options, run_metadata)
   1318       return self._call_tf_sessionrun(
-> 1319           options, feed_dict, fetch_list, target_list, run_metadata)
   1320 

/usr/local/lib/python3.6/dist-packages/tensorflow/python/client/session.py in _call_tf_sessionrun(self, options, feed_dict, fetch_list, target_list, run_metadata)
   1406         self._session, options, feed_dict, fetch_list, target_list,
-> 1407         run_metadata)
   1408 

FailedPreconditionError: Attempting to use uninitialized value Variable_14
     [[{{node Variable_14/read}}]]
     [[{{node mul_26}}]]

During handling of the above exception, another exception occurred:

FailedPreconditionError                   Traceback (most recent call last)
<ipython-input-34-3e0c62c51f1c> in <module>()
      1 with tf.Session() as sess:
      2   saver.restore(sess, './lenet')
----> 3   sess.run(accuracy*100, feed_dict={x: validation_data,y:validation_label_one_hot, is_testing: True})

/usr/local/lib/python3.6/dist-packages/tensorflow/python/client/session.py in run(self, fetches, feed_dict, options, run_metadata)
    927     try:
    928       result = self._run(None, fetches, feed_dict, options_ptr,
--> 929                          run_metadata_ptr)
    930       if run_metadata:
    931         proto_data = tf_session.TF_GetBuffer(run_metadata_ptr)

/usr/local/lib/python3.6/dist-packages/tensorflow/python/client/session.py in _run(self, handle, fetches, feed_dict, options, run_metadata)
   1150     if final_fetches or final_targets or (handle and feed_dict_tensor):
   1151       results = self._do_run(handle, final_targets, final_fetches,
-> 1152                              feed_dict_tensor, options, run_metadata)
   1153     else:
   1154       results = []

/usr/local/lib/python3.6/dist-packages/tensorflow/python/client/session.py in _do_run(self, handle, target_list, fetch_list, feed_dict, options, run_metadata)
   1326     if handle is None:
   1327       return self._do_call(_run_fn, feeds, fetches, targets, options,
-> 1328                            run_metadata)
   1329     else:
   1330       return self._do_call(_prun_fn, handle, feeds, fetches)

/usr/local/lib/python3.6/dist-packages/tensorflow/python/client/session.py in _do_call(self, fn, *args)
   1346           pass
   1347       message = error_interpolation.interpolate(message, self._graph)
-> 1348       raise type(e)(node_def, op, message)
   1349 
   1350   def _extend_graph(self):

FailedPreconditionError: Attempting to use uninitialized value Variable_14
     [[node Variable_14/read (defined at <ipython-input-12-95a60851d74f>:1) ]]
     [[node mul_26 (defined at <ipython-input-34-3e0c62c51f1c>:3) ]]

Caused by op 'Variable_14/read', defined at:
  File "/usr/lib/python3.6/runpy.py", line 193, in _run_module_as_main
    "__main__", mod_spec)
  File "/usr/lib/python3.6/runpy.py", line 85, in _run_code
    exec(code, run_globals)
  File "/usr/local/lib/python3.6/dist-packages/ipykernel_launcher.py", line 16, in <module>
    app.launch_new_instance()
  File "/usr/local/lib/python3.6/dist-packages/traitlets/config/application.py", line 658, in launch_instance
    app.start()
  File "/usr/local/lib/python3.6/dist-packages/ipykernel/kernelapp.py", line 477, in start
    ioloop.IOLoop.instance().start()
  File "/usr/local/lib/python3.6/dist-packages/tornado/ioloop.py", line 888, in start
    handler_func(fd_obj, events)
  File "/usr/local/lib/python3.6/dist-packages/tornado/stack_context.py", line 277, in null_wrapper
    return fn(*args, **kwargs)
  File "/usr/local/lib/python3.6/dist-packages/zmq/eventloop/zmqstream.py", line 450, in _handle_events
    self._handle_recv()
  File "/usr/local/lib/python3.6/dist-packages/zmq/eventloop/zmqstream.py", line 480, in _handle_recv
    self._run_callback(callback, msg)
  File "/usr/local/lib/python3.6/dist-packages/zmq/eventloop/zmqstream.py", line 432, in _run_callback
    callback(*args, **kwargs)
  File "/usr/local/lib/python3.6/dist-packages/tornado/stack_context.py", line 277, in null_wrapper
    return fn(*args, **kwargs)
  File "/usr/local/lib/python3.6/dist-packages/ipykernel/kernelbase.py", line 283, in dispatcher
    return self.dispatch_shell(stream, msg)
  File "/usr/local/lib/python3.6/dist-packages/ipykernel/kernelbase.py", line 235, in dispatch_shell
    handler(stream, idents, msg)
  File "/usr/local/lib/python3.6/dist-packages/ipykernel/kernelbase.py", line 399, in execute_request
    user_expressions, allow_stdin)
  File "/usr/local/lib/python3.6/dist-packages/ipykernel/ipkernel.py", line 196, in do_execute
    res = shell.run_cell(code, store_history=store_history, silent=silent)
  File "/usr/local/lib/python3.6/dist-packages/ipykernel/zmqshell.py", line 533, in run_cell
    return super(ZMQInteractiveShell, self).run_cell(*args, **kwargs)
  File "/usr/local/lib/python3.6/dist-packages/IPython/core/interactiveshell.py", line 2718, in run_cell
    interactivity=interactivity, compiler=compiler, result=result)
  File "/usr/local/lib/python3.6/dist-packages/IPython/core/interactiveshell.py", line 2822, in run_ast_nodes
    if self.run_code(code, result):
  File "/usr/local/lib/python3.6/dist-packages/IPython/core/interactiveshell.py", line 2882, in run_code
    exec(code_obj, self.user_global_ns, self.user_ns)
  File "<ipython-input-12-95a60851d74f>", line 1, in <module>
    connection_probability = tf.Variable(.9999)
  File "/usr/local/lib/python3.6/dist-packages/tensorflow/python/ops/variables.py", line 213, in __call__
    return cls._variable_v1_call(*args, **kwargs)
  File "/usr/local/lib/python3.6/dist-packages/tensorflow/python/ops/variables.py", line 176, in _variable_v1_call
    aggregation=aggregation)
  File "/usr/local/lib/python3.6/dist-packages/tensorflow/python/ops/variables.py", line 155, in <lambda>
    previous_getter = lambda **kwargs: default_variable_creator(None, **kwargs)
  File "/usr/local/lib/python3.6/dist-packages/tensorflow/python/ops/variable_scope.py", line 2495, in default_variable_creator
    expected_shape=expected_shape, import_scope=import_scope)
  File "/usr/local/lib/python3.6/dist-packages/tensorflow/python/ops/variables.py", line 217, in __call__
    return super(VariableMetaclass, cls).__call__(*args, **kwargs)
  File "/usr/local/lib/python3.6/dist-packages/tensorflow/python/ops/variables.py", line 1395, in __init__
    constraint=constraint)
  File "/usr/local/lib/python3.6/dist-packages/tensorflow/python/ops/variables.py", line 1557, in _init_from_args
    self._snapshot = array_ops.identity(self._variable, name="read")
  File "/usr/local/lib/python3.6/dist-packages/tensorflow/python/util/dispatch.py", line 180, in wrapper
    return target(*args, **kwargs)
  File "/usr/local/lib/python3.6/dist-packages/tensorflow/python/ops/array_ops.py", line 81, in identity
    ret = gen_array_ops.identity(input, name=name)
  File "/usr/local/lib/python3.6/dist-packages/tensorflow/python/ops/gen_array_ops.py", line 3890, in identity
    "Identity", input=input, name=name)
  File "/usr/local/lib/python3.6/dist-packages/tensorflow/python/framework/op_def_library.py", line 788, in _apply_op_helper
    op_def=op_def)
  File "/usr/local/lib/python3.6/dist-packages/tensorflow/python/util/deprecation.py", line 507, in new_func
    return func(*args, **kwargs)
  File "/usr/local/lib/python3.6/dist-packages/tensorflow/python/framework/ops.py", line 3300, in create_op
    op_def=op_def)
  File "/usr/local/lib/python3.6/dist-packages/tensorflow/python/framework/ops.py", line 1801, in __init__
    self._traceback = tf_stack.extract_stack()

FailedPreconditionError (see above for traceback): Attempting to use uninitialized value Variable_14
     [[node Variable_14/read (defined at <ipython-input-12-95a60851d74f>:1) ]]
     [[node mul_26 (defined at <ipython-input-34-3e0c62c51f1c>:3) ]]

可能的原因是什么 - 为什么训练和测试的行为会发生变化？任何帮助，将不胜感激。

标签： python-3.xtensorflow

解决方案

推荐阅读