tf.train.ExponentialMovingAverage(decay, steps)

shadow_variable是影子变量，variable表示待更新的变量，也就是变量被赋予的值，decay为衰减速率。decay一般设为接近于1的数（0.99,0.999）。decay越大模型越稳定，因为decay越大，参数更新的速度就越慢，趋于稳定。

steps是迭代的次数，可以自己设定。

view plain 输出：

[0.0, 0.0]
[5.0, 4.5]
[10.0, 4.5549998]
[10.0, 4.6094499]

例如：

[python]

v:0
v1:0
global_step:0

with g.control_dependencies([a, b, c]):
  # `d` and `e` will only run after `a`, `b`, and `c` have executed.
  d = ...
  e = ...
  • 1
  • 2
  • 3
  • 4
with g.control_dependencies([a, b]):
  # Ops constructed here run after `a` and `b`.
  with g.control_dependencies([c, d]):
    # Ops constructed here run after `a`, `b`, `c`, and `d`.
  • 1
  • 2
  • 3
  • 4
with g.control_dependencies([a, b]):
  # Ops constructed here run after `a` and `b`.
  with g.control_dependencies(None):
    # Ops constructed here run normally, not waiting for either `a` or `b`.
    with g.control_dependencies([c, d]):
      # Ops constructed here run after `c` and `d`, also not waiting
      # for either `a` or `b`.
  • 1
  • 2
  • 3
  • 4
  • 5
  • 6
  • 7
# WRONG
def my_func(pred, tensor):
  t = tf.matmul(tensor, tensor)
  with tf.control_dependencies([pred]):
    # The matmul op is created outside the context, so no control
    # dependency will be added.
    return t

# RIGHT
def my_func(pred, tensor):
  with tf.control_dependencies([pred]):
    # The matmul op is created in the context, so a control dependency
    # will be added.
    return tf.matmul(tensor, tensor)
  • 1
  • 2
  • 3
  • 4
  • 5
  • 6
  • 7
  • 8
  • 9
  • 10
  • 11
  • 12
  • 13
  • 14
with tf.control_dependencies([a, b]):
    c= tf.no_op(name='train')#tf.no_op；什么也不做
sess.run(c)
  • 1
  • 2
  • 3
c= tf.group([a, b])
sess.run(c)