python之在循环中评估 Tensorflow 操作非常慢

我试图通过编写一些简单的问题来学习 tensorflow :我试图使用直接采样蒙特卡罗方法找到 pi 的值。

当使用 for 循环 执行此操作时，运行时间比我想象的要长得多。我看过其他关于类似事情的帖子，并且我尝试遵循解决方案，但我认为我仍然做错了什么。

下面附上我的代码:

import tensorflow as tf 
import numpy as np 
import time 
 
n_trials = 50000 
 
tf.reset_default_graph() 
 
 
x = tf.random_uniform(shape=(), name='x') 
y = tf.random_uniform(shape=(), name='y') 
r = tf.sqrt(x**2 + y**2) 
 
hit = tf.Variable(0, name='hit') 
 
# perform the monte carlo step 
is_inside = tf.cast(tf.less(r, 1), tf.int32) 
hit_op = hit.assign_add(is_inside)  
 
with tf.Session() as sess: 
    init_op = tf.global_variables_initializer() 
    sess.run(init_op) 
 
    # Make sure no new nodes are added to the graph 
    sess.graph.finalize() 
 
    start = time.time()    
 
    # Run monte carlo trials  -- This is very slow 
    for _ in range(n_trials): 
        sess.run(hit_op) 
 
    hits = hit.eval() 
    print("Pi is {}".format(4*hits/n_trials)) 
    print("Tensorflow operation took {:.2f} s".format((time.time()-start))) 
 
>>> Pi is 3.15208 
>>> Tensorflow operation took 8.98 s 

相比之下，在 numpy 中执行 for 循环 类型的解决方案要快一个数量级

start = time.time()    
hits = [ 1 if np.sqrt(np.sum(np.square(np.random.uniform(size=2)))) < 1 else 0 for _ in range(n_trials) ] 
a = 0 
for hit in hits: 
    a+=hit 
print("numpy operation took {:.2f} s".format((time.time()-start))) 
print("Pi is {}".format(4*a/n_trials)) 
 
>>> Pi is 3.14032 
>>> numpy operation took 0.75 s 

下面附上了不同试验次数的总执行时间差异图。

请注意:我的问题不是关于“如何以最快的速度执行此任务”，我知道有更有效的计算 Pi 的方法。我只将它用作基准测试工具来检查 tensorflow 与我熟悉的东西 (numpy) 的性能。

请您参考如下方法:

速度慢与 sess.run 中 Python 和 Tensorflow 之间的一些通信开销有关，它在您的循环中执行了多次。我建议使用 tf.while_loop 在 Tensorflow 中执行计算。这比 numpy 更好。

import tensorflow as tf 
import numpy as np 
import time 
 
n_trials = 50000 
 
tf.reset_default_graph() 
 
hit = tf.Variable(0, name='hit') 
 
def body(ctr): 
    x = tf.random_uniform(shape=[2], name='x') 
    r = tf.sqrt(tf.reduce_sum(tf.square(x)) 
    is_inside = tf.cond(tf.less(r,1), lambda: tf.constant(1), lambda: tf.constant(0)) 
    hit_op = hit.assign_add(is_inside) 
    with tf.control_dependencies([hit_op]): 
        return ctr + 1 
 
def condition(ctr): 
    return ctr < n_trials 
 
with tf.Session() as sess: 
    tf.global_variables_initializer().run() 
    result = tf.while_loop(condition, body, [tf.constant(0)]) 
 
    start = time.time() 
    sess.run(result) 
 
    hits = hit.eval() 
    print("Pi is {}".format(4.*hits/n_trials)) 
    print("Tensorflow operation took {:.2f} s".format((time.time()-start)))