深度学习之卷积神经网络CNN模式识别VS代码

【文件属性】：

文件名称：深度学习之卷积神经网络CNN模式识别VS代码

文件大小：10.29MB

文件格式：RAR

更新时间：2017-03-10 12:07:02

深度学习 卷积神经网络 CNN VS

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/config.h to customize default behavior. ### vc(2012~) open vc/tiny_cnn.sln and build in release mode.

【文件预览】：
cnn_vs2012
----vc()
--------train-images.idx3-ubyte(44.86MB)
--------t10k-labels.idx1-ubyte(10KB)
--------t10k-images.idx3-ubyte(7.48MB)
--------tiny_cnn.vcxproj(6KB)
--------test.vcxproj.filters(2KB)
--------tiny_cnn.sln(1KB)
--------tiny_cnn_test.vcxproj(4KB)
--------train-labels.idx1-ubyte(59KB)
--------cnn.vcxproj.filters(2KB)
----waf(88KB)
----wscript(1KB)
----include()
--------fully_connected_layer.h(5KB)
--------config.h(2KB)
--------convolutional_layer.h(6KB)
--------picotest.h(23KB)
--------mnist_parser.h(5KB)
--------fixed_point.h(6KB)
--------util.h(5KB)
--------network.h(13KB)
--------product.h(12KB)
--------optimizer.h(3KB)
--------deform.h(2KB)
--------loss_function.h(2KB)
--------image.h(5KB)
--------layer.h(10KB)
--------average_pooling_layer.h(3KB)
--------activation_function.h(4KB)
--------tiny_cnn.h(2KB)
--------partial_connected_layer.h(8KB)
----src()
--------test.cpp(15KB)
--------wscript(352B)
--------main.cpp(7KB)
----.gitignore(2KB)
----README.md(2KB)
----.gitattributes(483B)