scipy convolve2d 输出错误的值 [英] scipy convolve2d outputs wrong values

问题描述

这是我用来检查 convolve2d 正确性的代码

Here is my code which I used for checking the correctness of convolve2d

import numpy as np
from scipy.signal import convolve2d

X = np.random.randint(5, size=(10,10))
K = np.random.randint(5, size=(3,3))
print "Input's top-left corner:"
print X[:3,:3]
print 'Kernel:'
print K

print 'Hardcording the calculation of a valid convolution (top-left)'
print (X[:3,:3]*K)
print 'Sums to'
print (X[:3,:3]*K).sum()
print 'However the top-left value of the convolve2d result'
Y = convolve2d(X, K, 'valid')
print Y[0,0]

在我的电脑上，结果如下:

On my computer this results in the following:

Input's top-left (3x3) corner:
[[0 0 0]
 [1 1 2]
 [1 3 0]]
Kernel:
[[4 1 1]
 [0 3 3]
 [2 1 2]]
Hardcording the calculation of a valid convolution (top-left)
[[0 0 0]
 [0 3 6]
 [2 3 0]]
Sums to
14
However the top-left value of the convolve2d result
10

背景故事:我一直在调试一个 convnet 库，不知何故梯度总是错误的.几周后，我得出结论，一切都应该正常运行，因此我徒手检查了 convolve2d 函数.

Background story: I've been debugging a convnet library, and somehow the gradients were always wrong. After a few weeks I concluded that everything should be working fine, so I checked the convolve2d function by bare hand.

推荐答案

表达式 (X[:3,:3]*K).sum() 不正确.对于卷积，您必须反转内核，例如(X[:3,:3]*K[::-1,::-1]).sum()

The expression (X[:3,:3]*K).sum() is not correct. For convolution, you have to reverse the kernel, e.g. (X[:3,:3]*K[::-1,::-1]).sum()

这篇关于scipy convolve2d 输出错误的值的文章就介绍到这了，希望我们推荐的答案对大家有所帮助，也希望大家多多支持IT屋！