We read every piece of feedback, and take your input very seriously.
To see all available qualifiers, see our documentation.
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
我是在sift1M上测试的,看论文,两个方法应该效果差不多的,但是我自己没测出来:( 1)NSSG的构建时间是32.9728+35.99(s);最关注的搜索时间是search_L=100, k=10,时间是17.3324s,而NSG可以3.29968s跑出来,显然是NSG的QPS高了; 2)在我设置多个参数,绘制 QPS vs Recall@10 曲线时,SSG也确实没有outperformNSG; 请问您能给我一些可能的原因嘛~
The text was updated successfully, but these errors were encountered:
上面的数据取k=10,其余的参数参考您github上的参数设置的~ k=100也绘制了 QPS vs Recall@10 曲线,仍然是NSG更胜一筹
Sorry, something went wrong.
我也有同样的问题,是否有合理的解释?
可能有几个原因:
作者CMakeLists.txt写的有问题,导致O3和AVX都没用上,而这些优化NSG都有。 #11
No branches or pull requests
我是在sift1M上测试的,看论文,两个方法应该效果差不多的,但是我自己没测出来:(
1)NSSG的构建时间是32.9728+35.99(s);最关注的搜索时间是search_L=100, k=10,时间是17.3324s,而NSG可以3.29968s跑出来,显然是NSG的QPS高了;
2)在我设置多个参数,绘制 QPS vs Recall@10 曲线时,SSG也确实没有outperformNSG;
请问您能给我一些可能的原因嘛~
The text was updated successfully, but these errors were encountered: