Tensorflow tf.cond评估两个pedicate

时间:2016-03-02 05:42:47

标签: tensorflow

import tensorflow as tf
import numpy as np

isTrain = tf.placeholder(tf.bool)
user_input = tf.placeholder(tf.float32)

# ema = tf.train.ExponentialMovingAverage(decay=.5)

with tf.device('/cpu:0'):
    beta = tf.Variable(tf.ones([1]))

    batch_mean = beta.assign(user_input)
    ema = tf.train.ExponentialMovingAverage(decay=0.5)
    ema_apply_op = ema.apply([batch_mean])
    ema_mean = ema.average(batch_mean)

    def mean_var_with_update():
        with tf.control_dependencies([ema_apply_op]):
            return tf.identity(batch_mean)

    mean = tf.cond(isTrain,
        mean_var_with_update,
        lambda: (ema_mean))

# ======= End Here ==========
saver = tf.train.Saver()
init = tf.initialize_all_variables()
sess = tf.Session()
sess.run(init)

u_input = [[2], [3], [4] ]
for u in u_input:
    aa = sess.run([mean], feed_dict={user_input:u, isTrain: True })
    print("Train", aa)

for u in u_input:
    aa = sess.run([ema_mean], feed_dict={user_input:u, isTrain: False })
    print("Test correct", aa)

for u in u_input:
    aa = sess.run([mean], feed_dict={user_input:u, isTrain: False })
    print("Test", aa)

此代码段应计算训练阶段的user_input平均值和测试阶段的输出平均值。

这是输出结果:

('Train', [array([ 2.], dtype=float32)])
('Train', [array([ 3.], dtype=float32)])
('Train', [array([ 4.], dtype=float32)])
('Test correct', [array([ 3.], dtype=float32)])
('Test correct', [array([ 3.], dtype=float32)])
('Test correct', [array([ 3.], dtype=float32)])
('Test', [array([ 2.5], dtype=float32)])
('Test', [array([ 2.75], dtype=float32)])
('Test', [array([ 3.375], dtype=float32)])

但是,即使ema_mean,在调用sess.run([mean])时始终会对isTrain = False进行评估。

代码中有错误吗? tensorflow版本是0.7.1

2 个答案:

答案 0 :(得分:1)

我认为这与answered here相同。条件语句中的tf.control_dependencies会将依赖项添加到tf.cond本身。

因此,请尝试在ema_apply_op函数中创建mean_var_with_update

答案 1 :(得分:0)

我添加了一些日志记录语句,ema_mean似乎仅在isTrain为假时进行评估

tf.reset_default_graph()

isTrain = tf.placeholder(tf.bool)
user_input = tf.placeholder(tf.float32)

# ema = tf.train.ExponentialMovingAverage(decay=.5)

with tf.device('/cpu:0'):
    beta = tf.Variable(tf.ones([1]))

    batch_mean = beta.assign(user_input)
    ema = tf.train.ExponentialMovingAverage(decay=0.5)
    ema_apply_op = ema.apply([batch_mean])
    ema_mean = ema.average(batch_mean)

    def mean_var_with_update():
        with tf.control_dependencies([ema_apply_op]):
            return tf.Print(tf.identity(batch_mean), ["mean_var_with_update"])
            #return tf.identity(batch_mean)

    mean = tf.Print(tf.cond(isTrain,
        mean_var_with_update,
        lambda: (tf.Print(ema_mean, ["ema_mean"]))),
                    ["evaluating mean", isTrain])

# ======= End Here ==========
saver = tf.train.Saver()
init = tf.initialize_all_variables()
sess = tf.Session()
sess.run(init)

u_input = [[2], [3], [4] ]
for u in u_input:
    aa = sess.run([mean], feed_dict={user_input:u, isTrain: True })
    print("Train", aa)

for u in u_input:
    aa = sess.run([ema_mean], feed_dict={user_input:u, isTrain: False })
    print("Test correct", aa)

for u in u_input:
    aa = sess.run([mean], feed_dict={user_input:u, isTrain: False })
    print("Test", aa)

你看

[mean_var_with_update]
[evaluating mean][True]
[mean_var_with_update]
[evaluating mean][True]
[mean_var_with_update]
[evaluating mean][True]
[ema_mean]
[evaluating mean][False]
[ema_mean]
[evaluating mean][False]
[ema_mean]
[evaluating mean][False]

请注意,在评估完所有输入后评估Print语句,以便最后打印外部打印语句