Question

我正在尝试编写自己的批量规范化代码。因此，我测试下面的代码。为了跟踪在线平均值和方差，我将它们作为参数传递给getsta（）函数。但是，我发现＆＃34; avg_mean＆＃34;和＆＃34; avg_variance＆＃34;改变。虽然我可以在以后手动强制更改其名称，但似乎Tensorflow将每个名称视为一个单独的变量。

def getsta(x,avg_mean,avg_variance):
  print('getsta start...')

  decay=0.9

  mean = tf.get_variable(
          'mean', [1], tf.float32,
          initializer=tf.constant_initializer(0.0, tf.float32))
  variance = tf.get_variable(
          'howvariance', [1], tf.float32,
          initializer=tf.constant_initializer(1.0, tf.float32))
  '''
  if (avg_mean == 0.0): 
      avg_mean = tf.get_variable(
              'avg_mean', [1], tf.float32,
              initializer=tf.constant_initializer(0.0, tf.float32))
  if (avg_variance == 0.0):
      avg_variance = tf.get_variable(
              'avg_variance', [1], tf.float32,
              initializer=tf.constant_initializer(0.0, tf.float32))
  '''
  mean, variance = tf.nn.moments(x, [0], name='moments')

  avg_mean -= (1.0 - decay) * (avg_mean - mean)
  avg_variance -= (1.0 - decay) * (avg_variance - variance)

  return x, mean, variance, avg_mean, avg_variance

def train():
  x1 = tf.constant([1,2,3,4], tf.float32)
  x2 = tf.constant([5,6,7,8], tf.float32)
  x3 = tf.constant([1,3,5,7], tf.float32)
  x4 = tf.constant([4,8,12,16], tf.float32)

  with tf.variable_scope("AAA") as scopeA:
    avg_mean1 = tf.get_variable(
              'test1', [1], tf.float32,
              initializer=tf.constant_initializer(0.0, tf.float32))
    avg_variance1 = tf.get_variable(
              'test2', [1], tf.float32,
              initializer=tf.constant_initializer(0.0, tf.float32))
    print([avg_mean1.name, avg_variance1.name])
    y1, mean1, variance1, avg_mean1, avg_variance1 = getsta(x1,avg_mean1,avg_variance1)
    print([avg_mean1.name, avg_variance1.name])
    scopeA.reuse_variables()
    print([avg_mean1.name, avg_variance1.name])
    y1, mean1, variance1, avg_mean1, avg_variance1 = getsta(x2,avg_mean1,avg_variance1)
    print([avg_mean1.name, avg_variance1.name])
    avg_mean1 = tf.identity(avg_mean1, name='avg_mean')
    avg_variance1 = tf.identity(avg_variance1, name='avg_variance')
    print([avg_mean1.name, avg_variance1.name])

  with tf.variable_scope("BBB") as scopeB:
    avg_mean2 = tf.get_variable(
              'test1', [1], tf.float32,
              initializer=tf.constant_initializer(0.0, tf.float32))
    avg_variance2 = tf.get_variable(
              'test2', [1], tf.float32,
              initializer=tf.constant_initializer(0.0, tf.float32))
    print([avg_mean2.name, avg_variance2.name])
    y2, mean2, variance2, avg_mean2, avg_variance2 = getsta(x3, avg_mean2, avg_variance2)
    print([avg_mean2.name, avg_variance2.name])
    scopeB.reuse_variables()
    print([avg_mean2.name, avg_variance2.name])
    y2, mean2, variance2, avg_mean2, avg_variance2 = getsta(x4, avg_mean2, avg_variance2)
    print([avg_mean2.name, avg_variance2.name])
    avg_mean2 = tf.identity(avg_mean2, name='avg_mean')
    avg_variance2 = tf.identity(avg_variance2, name='avg_variance')
    print([avg_mean2.name, avg_variance2.name])

  saver = tf.train.Saver()
  sess = tf.InteractiveSession()
  sess.run(tf.global_variables_initializer())
  print(sess.run([y1, mean1, variance1, avg_mean1, avg_variance1]))
  print(sess.run([y2, mean2, variance2, avg_mean2, avg_variance2]))

  allVars = tf.global_variables()
  values = sess.run(allVars)
  for var, val in zip(allVars, values):
    print(var.name, val)

  saver.save(sess, "/tmp/test_EMA/var_save.ckpt")

运行上面的train（）函数后，输出为

['AAA/test1:0', 'AAA/test2:0']
getsta start...
['AAA/sub_1:0', 'AAA/sub_3:0']
['AAA/sub_1:0', 'AAA/sub_3:0']
getsta start...
['AAA/sub_5:0', 'AAA/sub_7:0']
['AAA/avg_mean:0', 'AAA/avg_variance:0']
['BBB/test1:0', 'BBB/test2:0']
getsta start...
['BBB/sub_1:0', 'BBB/sub_3:0']
['BBB/sub_1:0', 'BBB/sub_3:0']
getsta start...
['BBB/sub_5:0', 'BBB/sub_7:0']
['BBB/avg_mean:0', 'BBB/avg_variance:0']
[array([ 5.,  6.,  7.,  8.], dtype=float32), 6.5, 1.25, array([ 0.875], dtype=float32), array([ 0.23750001], dtype=float32)]
[array([  4.,   8.,  12.,  16.], dtype=float32), 10.0, 20.0, array([ 1.36000001], dtype=float32), array([ 2.45000005], dtype=float32)]
AAA/test1:0 [ 0.]
AAA/test2:0 [ 0.]
AAA/mean:0 [ 0.]
AAA/howvariance:0 [ 1.]
BBB/test1:0 [ 0.]
BBB/test2:0 [ 0.]
BBB/mean:0 [ 0.]
BBB/howvariance:0 [ 1.]

我有几个问题：

有没有办法记录＆＃34; avg_mean＆＃34;没有改名字？我想在加载模型时加载最终更新的值。
是否可以定义＆＃34; avg_mean＆＃34;在getsta（）函数中，仍然保持它像一个静态变量，即它的初始值来自上次调用但不总是从0开始。
当我打印出所有变量时，为什么名称和值似乎都不正确，因为输出中的最后八行？我希望输出是
```
AAA/avg_mean:0 [0.875]
AAA/avg_variance:0 [0.23750001]
BBB/avg_mean:0 [1.36000001]
BBB/avg_variance:0 [2.45000005]
```

提前感谢您的帮助！

--------------------更新--------------------

我修改了我的代码，如下所示

def train():
  x1 = tf.constant([1,2,3,4], tf.float32)
  x2 = tf.constant([5,6,7,8], tf.float32)
  x3 = tf.constant([1,3,5,7], tf.float32)
  x4 = tf.constant([4,8,12,16], tf.float32)

  with tf.variable_scope("AAA") as scopeA:
    avg_mean1 = tf.get_variable(
              'avg_mean', [1], tf.float32,
              initializer=tf.constant_initializer(0.0, tf.float32))
    avg_variance1 = tf.get_variable(
              'avg_variance', [1], tf.float32,
              initializer=tf.constant_initializer(0.0, tf.float32))
    y1, mean1, variance1 = getsta(x1,avg_mean1,avg_variance1)
    scopeA.reuse_variables()
    y1, mean1, variance1 = getsta(x2,avg_mean1,avg_variance1)
    print([avg_mean1.name, avg_variance1.name])

  with tf.variable_scope("BBB") as scopeB:
    avg_mean2 = tf.get_variable(
              'avg_mean', [1], tf.float32,
              initializer=tf.constant_initializer(0.0, tf.float32))
    avg_variance2 = tf.get_variable(
              'avg_variance', [1], tf.float32,
              initializer=tf.constant_initializer(0.0, tf.float32))
    y2, mean2, variance2 = getsta(x3, avg_mean2, avg_variance2)
    scopeB.reuse_variables()
    y2, mean2, variance2 = getsta(x4, avg_mean2, avg_variance2)
    print([avg_mean2.name, avg_variance2.name])

  saver = tf.train.Saver()
  sess = tf.InteractiveSession()
  sess.run(tf.global_variables_initializer())
  print(sess.run([y1, mean1, variance1, avg_mean1, avg_variance1]))
  print(sess.run([y2, mean2, variance2, avg_mean2, avg_variance2]))

  allVars = tf.global_variables()
  values = sess.run(allVars)
  for var, val in zip(allVars, values):
    print(var.name, val)

  saver.save(sess, "/tmp/test_EMA/var_save.ckpt")

现在变量＆＃39;名字是固定的。但是，输出（变量＆＃39;值）似乎不正确。输出

[array([ 5.,  6.,  7.,  8.], dtype=float32), 6.5, 1.25, array([ 0.], dtype=float32), array([ 0.], dtype=float32)]
[array([  4.,   8.,  12.,  16.], dtype=float32), 10.0, 20.0, array([ 0.], dtype=float32), array([ 0.], dtype=float32)]
AAA/avg_mean:0 [ 0.]
AAA/avg_variance:0 [ 0.]
AAA/mean:0 [ 0.]
AAA/variance:0 [ 1.]
BBB/avg_mean:0 [ 0.]
BBB/avg_variance:0 [ 0.]
BBB/mean:0 [ 0.]

我应该如何修改我的代码才能获得正确的结果？谢谢。

Answer 1

以下是您的代码中需要修复的问题：

1-在以下行中，您将avg_variance1替换为operation返回的getsta。你不能这样做。当您创建变量avg_variance1并将其传递给getsta时，变量将在计算图中的任何位置更新，而TensorFlow将负责处理，您不需要明确地执行此操作。只要您指的是variable name，就可以了。 TensorFlow变量与常规Python变量不同。

y1, mean1, variance1, avg_mean1, avg_variance1 = getsta(x1,avg_mean1,avg_variance1)

（你需要为avg_mean1，avg_mean2等修复此问题）

2- avg_mean2，avg_variance2，avg_mean2和avg_variance2为Tensor而非variable。因此，它们不在您正在打印的variables列表中。

张量变量＆＃39;函数调用后名称已更改

1 个答案: