CNN Class, ver 0.8.
This project provides matlab class for implementation of convolutional neural networks. This networks was created by Yann LeCun and have sucessfully used in many practical applications, such as handwriten digits recognition, face detection, robot navigation and others (see references for more info). Because of some architectural features of convolutional networks, such as weight sharing it is imposible to implement it using Matlab Neural Network Toolbox without it's source modifications. That's why this class wokrs almost independently from NN toolbox (coming soon full independence).
The significant improovement in this version is a presence of cudacnn mex-file, which speeds up the training up to 44 times using NVidia's CUDA technology.You'll need a CUDA-capable graphic card and CUDA SDK (especially cudart.dll and cublas.dll). The source of cudacnn.mex is not included by now, but I plan to do It in future. Currently only stochastic gradient is supported by CUDA-training, but Hessian approximation is going to be soon also.
This release includes sample of handwriten digits recognition using CNN. If you just want to try it run cnet_tool. You'll see a simple GUI. It loads pretrained convolutional neural net from cnet.mat and recognizes image of gigit either pained in painitg area or downloaded from MNIST database.
If you interested in training you should open train_cnn.m, set all parameters following to comments and start learning by runing it.
The action sequence for creation of arbitrary convolutional neural network is following:
1. Create cnn object.
2. Set archtecture (number of layers, weights, training parameters, etc).
3. Call init method.
4. Define connection matrices for layers if necessary.
5. Load training data.
6. Preprocess training data.
7. Start training.
8. Test neural net.
There're several limitations in current version:
1. Network can have only one input for image (e.g. no stereo images simulateously).
2. You have to set connection matrix after the initialization.
3. MNIST database of handwriten digits not included in this distribution, you can download it from http://yann.lecun.com/exdb/mnist/index.html
Next version expectations:
1. Ability to work with several images simulateously.
2. Image Aquision toolbox integration.
3. Face detection sample.
References:
1. Y. LeCun, L. Bottou, G. Orr and K. Muller: Efficient BackProp, in Orr, G.
and Muller K. (Eds), Neural Networks: Tricks of the trade, Springer, 1998
URL:http://yann.lecun.com/exdb/publis/index.html
2. Y. LeCun, L. Bottou, Y. Bengio and P. Haffner: Gradient-Based Learning
Applied to Document Recognition, Proceedings of the IEEE, 86(11):2278-2324, November 1998
URL:http://yann.lecun.com/exdb/publis/index.html
3. Patrice Y. Simard, Dave Steinkraus, John C. Platt: Best Practices for
Convolutional Neural Networks Applied to Visual Document Analysis
URL:http://research.microsoft.com/apps/pubs/?id=68920
4. Thanks to Mike O'Neill for his great article, wich is summarize and
generalize all the information in 1-3 for better understandig for
programming:
URL: http://www.codeproject.com/KB/library/NeuralNetRecognition.aspx
5. Also thanks to Jake Bouvrie for his "Notes on Convolutional Neural
Networks", particulary for the idea to debug the neural network using
finite differences
URL: http://web.mit.edu/jvb/www/cv.html
==========
(c) Mikhail Sitotenko. This software distributing under BSD licence.
没有合适的资源?快使用搜索试试~ 我知道了~
温馨提示
【达摩老生出品,必属精品,亲测校正,质量保证】 资源名:CNN_matlab 资源类型:matlab项目全套源码 源码说明: 全部项目源码都是经过测试校正后百分百成功运行的,如果您下载后不能运行可联系我进行指导或者更换。 适合人群:新手及有一定经验的开发人员
资源推荐
资源详情
资源评论
收起资源包目录
CNN_matlab.zip (42个子文件)
Matlab实现无约束条件下普列姆(Prim)算法.docx 14KB
license.txt 1KB
ver 0.83
singlestruct2cnn.m 1KB
@cnn
init.m 4KB
cnn.m 7KB
check_finit_dif.m 2KB
subsref.m 2KB
cnn_size.m 973B
adapt_dw.m 4KB
calcje.m 6KB
calchx.m 5KB
cutrain.m 7KB
sim.m 3KB
calcMCR.m 710B
subsasgn.m 9KB
train.m 7KB
back_subsample.m 1KB
changelog.txt~ 1005B
mse.m 819B
subsample.m 1KB
purelin.m 774B
changelog.txt 1KB
cutrain_cnn.m 5KB
cnn_gui.fig 10KB
readMNIST_image.m 935B
tansig_mod.m 985B
fastFilter2.m 128B
license.txt~ 1KB
cnet.mat 557KB
preproc_image.m 412B
cnn_gui.m 12KB
back_conv2.m 716B
rot180.m 57B
cnn2singlestruct.m 1005B
test_dgt.m 433B
train_cnn.m 5KB
rand_std.m 972B
readMNIST.m 3KB
cnet_tool.m 23KB
preproc_data.m 1KB
readme.txt 3KB
cucalcMCR.m 712B
共 42 条
- 1
资源评论
阿里matlab建模师
- 粉丝: 3298
- 资源: 2784
上传资源 快速赚钱
- 我的内容管理 展开
- 我的资源 快来上传第一个资源
- 我的收益 登录查看自己的收益
- 我的积分 登录查看自己的积分
- 我的C币 登录后查看C币余额
- 我的收藏
- 我的下载
- 下载帮助
安全验证
文档复制为VIP权益,开通VIP直接复制
信息提交成功