w1的滑动平均值 = min( 0.99, 1/10 ) * 0 + ( 1 - min( 0.99, 1/10 ) * 1 = 0.9

w1滑动平均值 = min(0.99, 101/110) * 0.9 + ( 1 - min( 0.99, 101/110) * 10 = 1.644

w1滑动平均值 = min(0.99, 101/110) * 1.644 + ( 1 - min( 0.99, 101/110) * 10 = 2.328

w1滑动平均值 = 2.956

ema = tf.train.ExponentialMovingAverage(MOVING_AVERAGE_DECAY(滑动平均衰减率),global_step(轮数计数器，表示当前轮数)
)

ema_op = ema.apply([])

ema_op = ema.apply(tf.trainable_variables())

with tf.control_dependencies([ train_step, ema_op ]):train_op = tf.no_op(name = 'train')

# 待优化参数w1，不断更新w1参数，求w1的滑动平均(影子)import tensorflow as tf# 1. 定义变量及滑动平均类# 定义一个32位浮点变量并赋初值为0.0，
w1 = tf.Variable(0, dtype=tf.float32)# 轮数计数器，表示NN的迭代轮数，赋初始值为0，同时不可被优化（不参数训练）
global_step = tf.Variable(0, trainable=False)# 设定衰减率为0.99
MOVING_AVERAGE_DECAY = 0.99# 实例化滑动平均类
ema = tf.train.ExponentialMovingAverage(MOVING_AVERAGE_DECAY, global_step)# ema.apply()函数中的参数为待优化更新列表
# 每运行sess.run(ema_op)时，会对函数中的参数求算滑动平均值
# tf.trainable_variables()函数会自动将所有待训练的参数汇总为待列表
# 因该段代码中仅有w1一个参数，ema_op = ema.apply([w1])与下段代码等价
ema_op = ema.apply(tf.trainable_variables())# 2. 查看不同迭代中变量取值的变化。
with tf.Session() as sess:# 初始化init_op = tf.global_variables_initializer()sess.run(init_op)# 用ema.average(w1)获取w1滑动平均值 （要运行多个节点，作为列表中的元素列出，写在sess.run中）# 打印出当前参数w1和w1滑动平均值print("current global_step:", sess.run(global_step))print("current w1", sess.run([w1, ema.average(w1)]))# 参数w1的值赋为1sess.run(tf.assign(w1, 1))sess.run(ema_op)print("current global_step:", sess.run(global_step))print("current w1", sess.run([w1, ema.average(w1)]))# 更新global_step和w1的值,模拟出轮数为100时，参数w1变为10, 以下代码global_step保持为100，每次执行滑动平均操作，影子值会更新 sess.run(tf.assign(global_step, 100))sess.run(tf.assign(w1, 10))sess.run(ema_op)print("current global_step:", sess.run(global_step))print("current w1:", sess.run([w1, ema.average(w1)]))# 每次sess.run会更新一次w1的滑动平均值
    sess.run(ema_op)print("current global_step:", sess.run(global_step))print("current w1:", sess.run([w1, ema.average(w1)]))sess.run(ema_op)print("current global_step:", sess.run(global_step))print("current w1:", sess.run([w1, ema.average(w1)]))sess.run(ema_op)print("current global_step:" , sess.run(global_step))print("current w1:", sess.run([w1, ema.average(w1)]))sess.run(ema_op)print("current global_step:" , sess.run(global_step))print("current w1:", sess.run([w1, ema.average(w1)]))

current global_step: 0
current w1 [0.0, 0.0]
current global_step: 0
current w1 [1.0, 0.9]
current global_step: 100
current w1: [10.0, 1.6445453]
current global_step: 100
current w1: [10.0, 2.3281732]
current global_step: 100
current w1: [10.0, 2.955868]
current global_step: 100
current w1: [10.0, 3.532206]
current global_step: 100
current w1: [10.0, 4.061389]