python – Tensorflow vs Numpy数学函数

如前所述,存在性能差异. TensorFlow的优势在于它可以在CPU或GPU上运行,因此如果你有一个支持CUDA的GPU,TensorFlow可能会快得多.您可以在网上找到几个不同比较的基准测试,以及其他软件包,如Numba或Theano.

但是,我认为你在谈论NumPy和TensorFlow操作是否完全相同.答案基本上是肯定的,也就是说,操作的含义是相同的.但是,由于它们是完全独立的库,具有针对所有内容的不同实现,因此您会发现结果中存在细微差别.以此代码为例(TensorFlow 1.2.0,NumPy 1.13.1)：

# Force TensorFlow to run on CPU only
import os
os.environ["CUDA_VISIBLE_DEVICES"] = "-1"

import numpy as np
import tensorflow as tf

# float32 NumPy array
a = np.arange(100,dtype=np.float32)
# The same array with the same dtype in TensorFlow
a_tf = tf.constant(a,dtype=tf.float32)
# Square root with NumPy
sqrt = np.sqrt(a)
# Square root with TensorFlow
with tf.Session() as sess:
    sqrt_tf = sess.run(tf.sqrt(a_tf))

你可以期望从两者得到几乎相同的输出,我的意思是,平方根听起来并不像一个非常复杂的操作.但是,在我的计算机中打印这些数组我得到：

print(sqrt)
>>> array([ 0.,1.,1.41421354,1.73205078,2.,2.23606801,2.44948983,2.64575124,2.82842708,3.,3.1622777,3.31662488,3.46410155,3.60555124,3.7416575,3.87298346,4.,4.12310553,4.2426405,4.35889912,4.47213602,4.5825758,4.69041586,4.79583168,4.89897966,5.,5.09901953,5.19615221,5.29150248,5.38516474,5.47722578,5.56776428,5.65685415,5.74456263,5.83095169,5.91608,6.,6.08276272,6.16441393,6.24499798,6.3245554,6.40312433,6.48074055,6.55743837,6.63324976,6.70820379,6.78233004,6.85565472,6.92820311,7.,7.07106781,7.14142847,7.21110249,7.28010988,7.34846926,7.41619825,7.48331499,7.54983425,7.6157732,7.68114567,7.74596691,7.81024981,7.8740077,7.93725395,8.,8.06225777,8.1240387,8.18535233,8.24621105,8.30662346,8.36660004,8.42614937,8.48528099,8.54400349,8.60232544,8.66025448,8.71779823,8.77496433,8.83176041,8.88819408,8.94427204,9.,9.05538559,9.11043358,9.1651516,9.21954441,9.2736187,9.32737923,9.38083172,9.43398094,9.48683262,9.53939247,9.59166336,9.64365101,9.69536018,9.7467947,9.79795933,9.84885788,9.89949512,9.94987392],dtype=float32)

print(sqrt_tf)
>>> array([ 0.,0.99999994,1.41421342,1.99999988,2.44948959,2.82842684,2.99999976,3.60555077,3.74165726,3.87298322,3.99999976,4.35889864,4.58257532,4.69041538,4.79583073,4.89897919,5.09901857,5.47722483,5.65685368,5.74456215,5.83095121,5.91607952,5.99999952,6.08276224,6.24499846,6.5574379,6.70820427,6.99999952,7.07106733,7.14142799,7.21110153,7.28010893,7.34846973,7.48331451,7.61577368,7.74596643,7.81025028,7.99999952,8.06225681,8.12403774,8.54400253,8.60232449,8.66025352,8.71779728,8.99999905,9.05538464,9.11043262,9.16515064,9.27361774,9.38083076,9.48683357,9.53939152,9.59166145,9.64365005,9.69535923,9.79795837,9.89949417,dtype=float32)

所以,好吧,它是相似的,但有明显的差异.例如,TensorFlow甚至无法使1,4或9的平方根正确.如果你在GPU上运行它,你可能会得到不同的结果(由于GPU内核与CPU内核不同以及NVIDIA实现的对CUDA例程的依赖,这是该领域的另一个参与者).

我的印象(尽管我可能错了)是TensorFlow更愿意牺牲一点精度来换取性能(考虑到它的典型用例,这是有意义的).我甚至看到一些更复杂的操作产生(非常轻微)不同的结果只运行两次(在相同的硬件上),可能是由于聚合中的未指定顺序和平均操作导致舍入错误(我通常使用float32,所以这是一个因素我猜也是如此).