Question

我使用的是CIFAR10示例。我按照提供的代码训练了网络。培训成功完成。由于我想在我的数据集上仅评估每个示例一次，因此我将cifar10_input.py中的输入修改为以下内容。

def inputs(eval_data, data_dir, batch_size):
  filename = os.path.join(data_dir, TEST_FILE)
  filename_queue = tf.train.string_input_producer([filename],num_epochs=1)
  image, label = read_and_decode(filename_queue)
  float_image = tf.image.per_image_whitening(image)
  min_fraction_of_examples_in_queue = 0.4
  min_queue_examples = int(NUM_EXAMPLES_PER_EPOCH_FOR_EVAL *
                           min_fraction_of_examples_in_queue)
  images, label_batch = tf.train.batch(
      [image, label],
      batch_size=batch_size,
      num_threads=1,
      capacity=min_queue_examples + 3 * batch_size)

  tf.image_summary('images', images)
  return images, tf.reshape(label_batch, [batch_size])

我已将问题分离到以下内容：

tf.train_string_input_producer（[filename]，num_epochs = 1）

如果我没有设置num_epochs = 1，那么一切正常。如果我这样做，我会收到以下错误。

0x2cf2700 Compute status: Not found: Tensor name "input_producer/limit_epochs/epochs" not found in checkpoint files /home/jkschin/tensorflow/my_code/data/svhn/train/model.ckpt-8000

感谢您的帮助！

编辑3 @mrry：

它仍然失败。这是追踪。

Traceback (most recent call last):
  File "cnn_eval.py", line 148, in <module>
    tf.app.run()
  File "/usr/local/lib/python2.7/dist-packages/tensorflow/python/platform/default/_app.py", line 30, in run
    sys.exit(main(sys.argv))
  File "cnn_eval.py", line 144, in main
    evaluate()
  File "cnn_eval.py", line 119, in evaluate
    saver = tf.train.Saver([v for v in variables_to_restore if v.name != "input_producer/limit_epochs/epochs"])
AttributeError: 'unicode' object has no attribute 'name'

编辑4 @mrry：

softmax_linear /偏压/ ExponentialMovingAverage

conv2/biases/ExponentialMovingAverage
local4/biases/ExponentialMovingAverage
local3/biases/ExponentialMovingAverage
softmax_linear/weights/ExponentialMovingAverage
conv1/biases/ExponentialMovingAverage
local4/weights/ExponentialMovingAverage
conv2/weights/ExponentialMovingAverage
input_producer/limit_epochs/epochs
local3/weights/ExponentialMovingAverage
conv1/weights/ExponentialMovingAverage

Traceback (most recent call last):
  File "cnn_eval.py", line 148, in <module>
    tf.app.run()
  File "/usr/local/lib/python2.7/dist-packages/tensorflow/python/platform/default/_app.py", line 30, in run
    sys.exit(main(sys.argv))
  File "cnn_eval.py", line 144, in main
    evaluate()
  File "cnn_eval.py", line 119, in evaluate
    saver = tf.train.Saver([v for v in variables_to_restore if v != "input_producer/limit_epochs/epochs"])
  File "/usr/local/lib/python2.7/dist-packages/tensorflow/python/training/saver.py", line 784, in __init__
    restore_sequentially=restore_sequentially)
  File "/usr/local/lib/python2.7/dist-packages/tensorflow/python/training/saver.py", line 437, in build
    vars_to_save = self._ValidateAndSliceInputs(names_to_variables)
  File "/usr/local/lib/python2.7/dist-packages/tensorflow/python/training/saver.py", line 340, in _ValidateAndSliceInputs
    names_to_variables = self._VarListToDict(names_to_variables)
  File "/usr/local/lib/python2.7/dist-packages/tensorflow/python/training/saver.py", line 314, in _VarListToDict
    raise TypeError("Variable to save is not a Variable: %s" % var)
TypeError: Variable to save is not a Variable: Tensor("Const:0", shape=(), dtype=string)

编辑5 @mrry：

saver = tf.train.Saver([tf.Variable(0.0,validate_shape=False,name=v) for v in variables_to_restore if v != "input_producer/limit_epochs/epochs"])

0x21d0cb0 Compute status: Invalid argument: Assign requires shapes of both tensors to match. lhs shape= [] rhs shape= [10]
     [[Node: save/Assign_8 = Assign[T=DT_FLOAT, use_locking=true, validate_shape=true, _device="/job:localhost/replica:0/task:0/gpu:0"](softmax_linear/biases/ExponentialMovingAverage, save/restore_slice_8/_20)]]

Answer 1

TL; DR：在cifar10_eval.py中，更改保护程序构造函数，使其成为：

saver = tf.train.Saver([v for v in variables_to_restore
                        if v != "input_producer/limit_epochs/epochs"])

出现此问题是因为tf.train.string_input_producer()在"input_producer/limit_epochs/epochs"参数不是num_epochs时在内部创建变量（称为None）。在cifar10_eval.py和tf.train.Saver is created中，它使用tf.all_variables()，其中包含来自tf.nn.string_input_producer()的隐式创建的变量。此变量列表确定TensorFlow在检查点文件中查找的名称集。

目前，除了名称之外，没有很好的方式来引用隐式创建的变量。因此，最好的解决方法是按名称从Saver构造函数中排除变量。

Answer 2

消除隐式变量cd /D D:\program\ser\conf D:\program\ser\int.exe D:\program\ser\conf\script.txt的另一种方法是仅加载可训练变量：

"input_producer/limit_epochs/epochs"

计算状态：未找到：张量名称＆＃34; input_producer / limit_epochs / epochs＆＃34;在检查点文件中找不到

2 个答案: