Question

我似乎对Image的工作方式有误解。在tensorflow documentation中，给出以下示例：

tf.cond

如果z = tf.multiply(a, b) result = tf.cond(x < y, lambda: tf.add(x, z), lambda: tf.square(y))为x<y为True的示例结果，否则为tf.add(x,z)

在此示例之后，我尝试使用tf.cond构建一个小示例，其结果与文档中提到的内容不符。

在我的示例中，tf.square(y)，deterministic_action = 4，random_action = 11。 chose_random=False应该是stochastic_action，而不是4。值1是从哪里来的？

这是输出：

#!/usr/bin/env python3

import tensorflow as tf
import numpy as np

with tf.Graph().as_default():
    with tf.device('/cpu:0'):
        stochastic_ph = tf.placeholder(tf.bool, (), name="stochastic")
        eps = tf.get_variable("eps", (), initializer=tf.constant_initializer(0))
        with tf.variable_scope('test_cond') as sc:
            deterministic_action = tf.random_uniform([], minval=0, maxval=15, dtype=tf.int64, seed=0) # 4
            random_action = tf.random_uniform([], minval=0, maxval=15, dtype=tf.int64, seed=1) # 11
            chose_random = tf.random_uniform([], minval=0, maxval=1, dtype=tf.float32) < eps # False because eps = 0
            stochastic_action = tf.cond(chose_random, lambda: random_action, lambda: deterministic_action) # S_action should be 4 but it is 1
            #output_action = tf.cond(stochastic_ph, lambda: stochastic_action, lambda: deterministic_action)


    init = tf.global_variables_initializer()
    sess = tf.Session()
    sess.run(init, feed_dict={stochastic_ph: True})
    print ("s_ph = ", stochastic_ph)
    d_action = sess.run(deterministic_action)
    print ("det_action= ", d_action)
    r_action = sess.run(random_action)
    print ("rand_action= ", r_action)
    e = sess.run(eps)
    c_action = sess.run(chose_random)
    print ("chose_rand= ", c_action)
    s_action = sess.run(stochastic_action)
    print ("s_action= ", s_action)
    #output = sess.run(output_action)

Answer 1

这是因为您要在新的sess.run中再次进行评估。由于您正在为deterministic_action生成一个随机数，因此结果是4之后的下一个随机数，即1。这也是您在最后一步中提取deterministic_action的值时，代码的结果。

修改：

print ("s_ph = ", stochastic_ph)
d_action = sess.run(deterministic_action)
print ("det_action= ", d_action)
r_action = sess.run(random_action)
print ("rand_action= ", r_action)
e = sess.run(eps)
c_action = sess.run(chose_random)
print ("chose_rand= ", c_action)
s_action, d_action = sess.run([stochastic_action, deterministic_action])
print ("s_action= ", s_action)
print ("det_action= ", d_action)

结果：

s_ph =  Tensor("stochastic:0", shape=(), dtype=bool, device=/device:CPU:0)
det_action=  4
rand_action=  11
chose_rand=  False
s_action=  1
det_action=  1

现在您需要做的就是将所有内容运行在一个sess.run

中。

d_action, r_action, e,  c_action, s_action = sess.run([deterministic_action, random_action, eps, chose_random, stochastic_action])
print ("det_action= ", d_action)
print ("rand_action= ", r_action)
print ("chose_rand= ", c_action)
print ("s_action= ", s_action)

结果：

s_ph =  Tensor("stochastic:0", shape=(), dtype=bool, device=/device:CPU:0)
det_action=  4
rand_action=  11
chose_rand=  False
s_action=  4

更新：

我不清楚为什么设置种子时random_uniform会生成不同的值。这是因为代码使用与初始化变量相同的会话对象运行。使用新的会话对象修改代码，结果如下：

print ("s_ph = ", stochastic_ph)
d_action = sess.run(deterministic_action)
print ("det_action= ", d_action)
sess.close()
sess = tf.Session()
sess.run(init, feed_dict={stochastic_ph: True})
s_action = sess.run(stochastic_action)
print ("s_action= ", s_action)

结果：

s_ph =  Tensor("stochastic:0", shape=(), dtype=bool, device=/device:CPU:0)
det_action=  4
s_action=  4

tensorflow Tf.cond提供意外的输出

1 个答案: