深度学习之卷积神经网络CNN模式识别VS代码
深度学习之卷积神经网络CNN做手写体识别的VS代码。支持linux版本和VS2012版本。
tiny-cnn: A C++11 implementation of convolutional neural networks
========
tiny-cnn is a C++11 implementation of convolutional neural networks.
design principle
-----
* fast, without GPU
98.8% accuracy on MNIST in 13 minutes training (@Core i7-3520M)
* header only, policy-based design
supported networks
-----
### layer-types
* fully-connected layer
* convolutional layer
* average pooling layer
### activation functions
* tanh
* sigmoid
* rectified linear
* identity
### loss functions
* cross-entropy
* mean-squared-error
### optimization algorithm
* stochastic gradient descent (with/without L2 normalization)
* stochastic gradient levenberg marquardt
dependencies
-----
* boost C++ library
* Intel TBB
sample code
------
```cpp
#include "tiny_cnn.h"
using namespace tiny_cnn;
// specify loss-function and optimization-algorithm
typedef network CNN;
// tanh, 32x32 input, 5x5 window, 1-6 feature-maps convolution
convolutional_layer C1(32, 32, 5, 1, 6);
// tanh, 28x28 input, 6 feature-maps, 2x2 subsampling
average_pooling_layer S2(28, 28, 6, 2);
// fully-connected layers
fully_connected_layer F3(14*14*6, 120);
fully_connected_layer F4(120, 10);
// connect all
CNN mynet;
mynet.add(&C1); mynet.add(&S2); mynet.add(&F3); mynet.add(&F4);
assert(mynet.in_dim() == 32*32);
assert(mynet.out_dim() == 10);
```
more sample, read main.cpp
build sample program
------
### gcc(4.6~)
without tbb
./waf configure --BOOST_ROOT=your-boost-root
./waf build
with tbb
./waf configure --TBB --TBB_ROOT=your-tbb-root --BOOST_ROOT=your-boost-root
./waf build
with tbb and SSE/AVX
./waf configure --AVX --TBB --TBB_ROOT=your-tbb-root --BOOST_ROOT=your-boost-root
./waf build
./waf configure --SSE --TBB --TBB_ROOT=your-tbb-root --BOOST_ROOT=your-boost-root
./waf build
or edit inlude/co
文件下载
资源详情
[{"title":"（ 35 个子文件 10.29MB ） 深度学习之卷积神经网络CNN模式识别VS代码","children":[{"title":"cnn_vs2012","children":[{"title":"vc","children":[{"title":"train-images.idx3-ubyte <span style='color:#111;'> 44.86MB </span>","children":null,"spread":false},{"title":"t10k-labels.idx1-ubyte <span style='color:#111;'> 9.77KB </span>","children":null,"spread":false},{"title":"t10k-images.idx3-ubyte <span style='color:#111;'> 7.48MB </span>","children":null,"spread":false},{"title":"tiny_cnn.vcxproj <span style='color:#111;'> 5.72KB </span>","children":null,"spread":false},{"title":"test.vcxproj.filters <span style='color:#111;'> 1.89KB </span>","children":null,"spread":false},{"title":"tiny_cnn.sln <span style='color:#111;'> 1.29KB </span>","children":null,"spread":false},{"title":"tiny_cnn_test.vcxproj <span style='color:#111;'> 4.34KB </span>","children":null,"spread":false},{"title":"train-labels.idx1-ubyte <span style='color:#111;'> 58.60KB </span>","children":null,"spread":false},{"title":"cnn.vcxproj.filters <span style='color:#111;'> 1.99KB </span>","children":null,"spread":false}],"spread":true},{"title":"waf <span style='color:#111;'> 88.35KB </span>","children":null,"spread":false},{"title":"wscript <span style='color:#111;'> 1.47KB </span>","children":null,"spread":false},{"title":"include","children":[{"title":"fully_connected_layer.h <span style='color:#111;'> 4.92KB </span>","children":null,"spread":false},{"title":"config.h <span style='color:#111;'> 1.88KB </span>","children":null,"spread":false},{"title":"convolutional_layer.h <span style='color:#111;'> 6.12KB </span>","children":null,"spread":false},{"title":"picotest.h <span style='color:#111;'> 22.82KB </span>","children":null,"spread":false},{"title":"mnist_parser.h <span style='color:#111;'> 4.50KB </span>","children":null,"spread":false},{"title":"fixed_point.h <span style='color:#111;'> 5.66KB </span>","children":null,"spread":false},{"title":"util.h <span style='color:#111;'> 5.32KB </span>","children":null,"spread":false},{"title":"network.h <span style='color:#111;'> 13.11KB </span>","children":null,"spread":false},{"title":"product.h <span style='color:#111;'> 12.23KB </span>","children":null,"spread":false},{"title":"optimizer.h <span style='color:#111;'> 2.67KB </span>","children":null,"spread":false},{"title":"deform.h <span style='color:#111;'> 1.92KB </span>","children":null,"spread":false},{"title":"loss_function.h <span style='color:#111;'> 2.05KB </span>","children":null,"spread":false},{"title":"image.h <span style='color:#111;'> 4.53KB </span>","children":null,"spread":false},{"title":"layer.h <span style='color:#111;'> 9.99KB </span>","children":null,"spread":false},{"title":"average_pooling_layer.h <span style='color:#111;'> 3.42KB </span>","children":null,"spread":false},{"title":"activation_function.h <span style='color:#111;'> 3.54KB </span>","children":null,"spread":false},{"title":"tiny_cnn.h <span style='color:#111;'> 1.87KB </span>","children":null,"spread":false},{"title":"partial_connected_layer.h <span style='color:#111;'> 8.50KB </span>","children":null,"spread":false}],"spread":false},{"title":"src","children":[{"title":"test.cpp <span style='color:#111;'> 14.81KB </span>","children":null,"spread":false},{"title":"wscript <span style='color:#111;'> 352B </span>","children":null,"spread":false},{"title":"main.cpp <span style='color:#111;'> 6.60KB </span>","children":null,"spread":false}],"spread":true},{"title":".gitignore <span style='color:#111;'> 2.06KB </span>","children":null,"spread":false},{"title":"README.md <span style='color:#111;'> 2.00KB </span>","children":null,"spread":false},{"title":".gitattributes <span style='color:#111;'> 483B </span>","children":null,"spread":false}],"spread":true}],"spread":true}]
评论信息
-
-
-
anruo12138 :觉得很实用，非常希望都能传些高质量的东西2019-11-04 -
-
ll79444326 :不过 有借鉴价值 谢谢分享2018-07-21
-
-
ghxx2010 :代码一般，可读性不强2018-04-09
-
-
worldy :真是晕，我都按取消了还没有下载，就要我CSDN还没看内容就要打分，我也是醉了2018-01-12
-
-
hongyi6814 :我用迅雷下的，怎么说找不到网页2018-01-05
-
其他资源
- ARCPY使用手册V1.2
- 2017的qsdk.rar
- 获取文件编码格式(纯JAVA代码，绝对对你有用)
- Omnia_Music_Player_Premium_v1.4.5_build_67.apk
- Linux云计算架构师完美教材
- Synergy1_10_2 Pro安装包.7z
- CityEngine 城市三维建模
- KLT Algorithm人脸追踪
- GB∕T 25058-2019 信息安全技术 网络安全等级保护实施指南.pdf
- 华为培训5G-上下行解耦.pptx
- 《英语单词图像记忆法(小学单词)》.pdf
- 苏教版译林牛津初中英语语法总结(初一初二).docx
- 网络营销-网络推广0.《解密：网络营销推广实战和流量变现公式》.pdf
- MyApp.rar - Dojo - Creating a custom widget创建自定义小部件
- AP_standards.zip
- 论文生成器 js、Python源码
- VFP企业管理
- nodejs+ajax用js实现前端后台demo
- FTP服务器CLIENT端C语言源文件
- 《C+++GUI+Qt+4+编程（第二版）》
- 人工智能 水壶问题的求解.rar
- C#写的桌面倒计时器，可用于各种竞赛，抢答，演讲倒计时
- drupal7专业开发指南 中文版 word版
免责申明
【只为小站】的资源来自网友分享，仅供学习研究，请务必在下载后24小时内给予删除，不得用于其他任何用途，否则后果自负。基于互联网的特殊性，【只为小站】 无法对用户传输的作品、信息、内容的权属或合法性、合规性、真实性、科学性、完整权、有效性等进行实质审查；无论 【只为小站】 经营者是否已进行审查，用户均应自行承担因其传输的作品、信息、内容而可能或已经产生的侵权或权属纠纷等法律责任。
本站所有资源不代表本站的观点或立场，基于网友分享，根据中国法律《信息网络传播权保护条例》第二十二条之规定，若资源存在侵权或相关问题请联系本站客服人员，zhiweidada#qq.com，请把#换成@，本站将给予最大的支持与配合，做到及时反馈和处理。关于更多版权及免责申明参见 版权及免责申明
本站所有资源不代表本站的观点或立场，基于网友分享，根据中国法律《信息网络传播权保护条例》第二十二条之规定，若资源存在侵权或相关问题请联系本站客服人员，zhiweidada#qq.com，请把#换成@，本站将给予最大的支持与配合，做到及时反馈和处理。关于更多版权及免责申明参见 版权及免责申明