文件名称:net
- 所属分类：
- Linux驱动
- 资源属性：
- [Windows] [Visual.Net] [源码]
- 上传时间：
- 2015-08-28
- 文件大小：
- 12.17mb
- 下载次数：
- 0次
- 提 供 者：
- 王*
- 相关连接：
- 无
- 下载说明：
- 别用迅雷下载，失败请重下，重下不扣分！
介绍说明－－下载内容均来自于网络，请自行研究使用
机器学习irect和unrolling乘法数一模一样，所以图上只有direct的。unrolling方法就是为blas/gemm设计的，至于blas/gemm把矩阵乘复杂度、乘法数降到多少还没见，但是那就到blas优化的范畴了。
-Machine Learning irect and unrolling exactly the number of multiplications, so the figure of only direct. unrolling method is to blas/gemm design, as blas/gemm the complexity of matrix multiplication, multiply the number of how many drops did not see, but it is to optimize the scope of the blas.
-Machine Learning irect and unrolling exactly the number of multiplications, so the figure of only direct. unrolling method is to blas/gemm design, as blas/gemm the complexity of matrix multiplication, multiply the number of how many drops did not see, but it is to optimize the scope of the blas.
(系统自动生成,下载前可以参看下载内容)
下载文件列表
net
...\29x29-20C4.0-MP2-40C5.0-MP3-150N.txt
...\29x29-5C4.0-MP2-10C5.0-MP3-50N.txt
...\29x29-test-images.idx
...\29x29-test-labels.idx
...\29x29-train-images.idx
...\29x29-train-labels.idx
...\idx.cpp
...\idx.h
...\IDXviewer.exe
...\main.cpp
...\net.sln
...\net.vcxproj
...\neuralnetwork.cpp
...\NeuralNetwork.h
...\readme.txt