文件名称:CNN-pooling-strategy
介绍说明－－下载内容均来自于网络，请自行研究使用
基于卷积层和池化层的卷积深度网络被执行，该框架可以有效地识别灰度图像，彩色图像和高光谱图像。- Convolution deep network based on convolution layer and pooling layer is performed, the fr a mework can effectively identify grayscale images, color images and hyperspectral images.
(系统自动生成,下载前可以参看下载内容)
下载文件列表
CNN\cnnapplygrads.asv
...\cnnapplygrads.m
...\cnnbp - 副本.m
...\cnnbp.asv
...\cnnbp.m
...\cnnff.asv
...\cnnff.m
...\cnnnumgradcheck.m
...\cnnsetup.m
...\cnntest.m
...\cnntrain.m
...\MaxPooling.cpp
...\MaxPooling.cpp.bak
...\MaxPooling.m
...\MaxPooling.mexw32
...\MaxPooling.mexw64
...\MaxPoolingGPU.cpp
...\MaxPoolingGPU.cpp.bak
...\StochasticPooling.cpp
...\StochasticPooling.mexw64
...\StochaticTest.m
...\test_example_CNN.asv
...\test_example_CNN.m
data\mnist_uint8.mat
util\allcomb.m
....\expand.m
....\flicker.m
....\flipall.m
....\fliplrf.m
....\flipudf.m
....\im2patches.m
....\isOctave.m
....\makeLMfilters.m
....\myOctaveVersion.m
....\normalize.m
....\patches2im.m
....\randcorr.m
....\randp.m
....\rnd.m
....\sigm.m
....\sigmrnd.m
....\softmax.m
....\tanh_opt.m
....\visualize.m
....\whiten.m
....\zscore.m
CNN
data
util
67506287CNN-with-three-pooling-strategy\CNN\cnnapplygrads.asv
.......................................\...\cnnapplygrads.m
.......................................\...\cnnbp - 副本.m
.......................................\...\cnnbp.asv
.......................................\...\cnnbp.m
.......................................\...\cnnff.asv
.......................................\...\cnnff.m
.......................................\...\cnnnumgradcheck.m
.......................................\...\cnnsetup.m
.......................................\...\cnntest.m
.......................................\...\cnntrain.m
.......................................\...\MaxPooling.cpp
.......................................\...\MaxPooling.cpp.bak
.......................................\...\MaxPooling.m
.......................................\...\MaxPooling.mexw32
.......................................\...\MaxPooling.mexw64
.......................................\...\MaxPoolingGPU.cpp
.......................................\...\MaxPoolingGPU.cpp.bak
.......................................\...\StochasticPooling.cpp
.......................................\...\StochasticPooling.mexw64
.......................................\...\StochaticTest.m
.......................................\...\test_example_CNN.asv
.......................................\...\test_example_CNN.m
.......................................\data\mnist_uint8.mat
.......................................\util\allcomb.m
.......................................\....\expand.m
.......................................\....\flicker.m
.......................................\....\flipall.m
.......................................\....\fliplrf.m
.......................................\....\flipudf.m
.......................................\....\im2patches.m
.......................................\....\isOctave.m
.......................................\....\makeLMfilters.m
.......................................\....\myOctaveVersion.m
.......................................\....\normalize.m
.......................................\....\patches2im.m
.......................................\....\randcorr.m
.......................................\....\randp.m
.......................................\....\rnd.m
.......................................\....\sigm.m
.......................................\....\sigmrnd.m
.......................................\....\softmax.m
.......................................\....\tanh_opt.m
.......................................\....\visualize.m
.......................................\....\whiten.m
.......................................\....\zscore.m
.......................................\CNN
.......................................\data
.......................................\util
67506287CNN-with-three-pooling-strategy