在循环中评估 Tensorflow 操作非常慢

我试图通过编码一些简单的问题来学习张量流：我试图使用直接采样蒙特卡罗方法找到 pi 的值。

运行时间比我想象的要长得多for loop去做这个。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，但我认为我仍然一定做错了什么。

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，做一个for loopnumpy 中的类型解决方案速度快一个数量级

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

下面附上的图表显示了不同次数的试验的总体执行时间的差异。

请注意：我的问题不是关于“如何最快地执行此任务”，我认识到有更多有效的方法来计算 Pi。我仅使用它作为基准测试工具来根据我熟悉的东西（numpy）检查张量流的性能。

速度慢与 Python 和 Tensorflow 之间的一些通信开销有关sess.run，它在循环内执行多次。我建议使用tf.while_loop在 Tensorflow 中执行计算。这将是一个更好的比较numpy.

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)))