// 700 ms
cv::Mat in(height,width,CV_8UC1);
in /= 4;
替换为
//40 ms
cv::Mat in(height,width,CV_8UC1);
for (int y=0; y < in.rows; ++y)
{
unsigned char* ptr = in.data + y*in.step1();
for (int x=0; x < in.cols; ++x)
{
ptr[x] /= 4;
}
}
什么可能导致这种行为?这是由于opencv&#34;促进&#34;使用Scalar乘法来匹配Mat乘法Mat,或者它是针对arm的特定失败优化? (已启用NEON)。
答案 0 :(得分:1)
通过测量cpu时间来尝试相同的操作。
int main()
{
clock_t startTime;
clock_t endTime;
int height =1024;
int width =1024;
// 700 ms
cv::Mat in(height,width,CV_8UC1, cv::Scalar(255));
std::cout << "value: " << (int)in.at<unsigned char>(0,0) << std::endl;
cv::Mat out(height,width,CV_8UC1);
startTime = clock();
out = in/4;
endTime = clock();
std::cout << "1: " << (float)(endTime-startTime)/(float)CLOCKS_PER_SEC << std::endl;
std::cout << "value: " << (int)out.at<unsigned char>(0,0) << std::endl;
startTime = clock();
in /= 4;
endTime = clock();
std::cout << "2: " << (float)(endTime-startTime)/(float)CLOCKS_PER_SEC << std::endl;
std::cout << "value: " << (int)in.at<unsigned char>(0,0) << std::endl;
//40 ms
cv::Mat in2(height,width,CV_8UC1, cv::Scalar(255));
startTime = clock();
for (int y=0; y < in2.rows; ++y)
{
//unsigned char* ptr = in2.data + y*in2.step1();
unsigned char* ptr = in2.ptr(y);
for (int x=0; x < in2.cols; ++x)
{
ptr[x] /= 4;
}
}
std::cout << "value: " << (int)in2.at<unsigned char>(0,0) << std::endl;
endTime = clock();
std::cout << "3: " << (float)(endTime-startTime)/(float)CLOCKS_PER_SEC << std::endl;
cv::namedWindow("...");
cv::waitKey(0);
}
结果:
value: 255
1: 0.016
value: 64
2: 0.016
value: 64
3: 0.003
value: 63
您看到结果不同,可能是因为mat.divide()
执行浮点除法并舍入到下一个。虽然你在更快的版本中使用整数除法,但速度更快但结果不同。
另外,在openCV计算中有一个saturate_cast,但我想更大的计算负载差异将是双精度除法。