计算状态:未找到:检查点文件中未找到张量名称“input_ files /files_epochs/epochs”

Question

我正在使用CIFAR10示例。我用所提供的代码训练了网络。训练成功了。由于我只想在我的数据集中对每个示例进行一次评估，所以我将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])

我把这个问题分为以下几点：

Tf.train_string_input_producer(文件名，num_epochs = 1)

如果我不设置num_epochs = 1，那么一切都会正常工作。如果我这样做了，我会得到以下错误。

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

谢谢你的帮助!

编辑3 @mrry：

但还是失败了。这是痕迹。

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/biases/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: In cifar10_eval.py，将保护程序构造函数更改为：

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

之所以会出现这个问题，是因为当tf.train.string_input_producer()的num_epochs参数不是None时，num_epochs内部会创建一个变量(称为None)。在cifar10_eval.py a is created中，它使用tf.all_variables()，其中包括从tf.nn.string_input_producer()中隐式创建的变量。此变量列表确定TensorFlow在检查点文件中查找的名称集。

目前没有一种很好的方法来引用隐式创建的变量，除了它们的名称。因此，最好的解决办法是按名称从Saver构造函数中排除变量。

Answer 2

消除隐式变量"input_producer/limit_epochs/epochs"的另一种方法是只加载可训练变量：

saver = tf.train.Saver(tf.trainable_variables())