我正在尝试使用花哨的索引而不是循环来加速 Numpy 中的函数。据我所知,我已经正确实现了精美的索引版本。问题是这两个函数(循环和花式索引)不返回相同的结果。我不确定为什么。值得指出的是,如果使用较小的数组(例如,20 x 20 x 20),这些函数会返回相同的结果。
下面我已经包含了重现错误所需的所有内容。如果函数确实返回相同的结果,则该行find_maxdiff(data) - find_maxdiff_fancy(data)
应返回一个全零的数组。
from numpy import *
def rms(data, axis=0):
return sqrt(mean(data ** 2, axis))
def find_maxdiff(data):
samples, channels, epochs = shape(data)
window_size = 50
maxdiff = zeros(epochs)
for epoch in xrange(epochs):
signal = rms(data[:, :, epoch], axis=1)
for t in xrange(window_size, alen(signal) - window_size):
amp_a = mean(signal[t-window_size:t], axis=0)
amp_b = mean(signal[t:t+window_size], axis=0)
the_diff = abs(amp_b - amp_a)
if the_diff > maxdiff[epoch]:
maxdiff[epoch] = the_diff
return maxdiff
def find_maxdiff_fancy(data):
samples, channels, epochs = shape(data)
window_size = 50
maxdiff = zeros(epochs)
signal = rms(data, axis=1)
for t in xrange(window_size, alen(signal) - window_size):
amp_a = mean(signal[t-window_size:t], axis=0)
amp_b = mean(signal[t:t+window_size], axis=0)
the_diff = abs(amp_b - amp_a)
maxdiff[the_diff > maxdiff] = the_diff
return maxdiff
data = random.random((600, 20, 100))
find_maxdiff(data) - find_maxdiff_fancy(data)
data = random.random((20, 20, 20))
find_maxdiff(data) - find_maxdiff_fancy(data)