# mdCNN
mdCNN is a MATLAB toolbox implementing Convolutional Neural Networks (CNN) for 2D and 3D inputs.
Network is Multidimensional, kernels are in 3D and convolution is done in 3D. It is suitable for volumetric inputs such as CT / MRI, but can also support 1D/2D image inputs.
The framework supports all the major features such as droput, padding, stride, max pooling, L2 regularization, momentum, cross entropy/ MSE , softmax, regression, classification and batch normalization layer.
Framework is completely written in matlab and is heavily optimized. While training or testing, all of the CPU cores are participating by using Matlab Built-in Multi-threading.
There are several examples for networks pre-configured to run MNIST, CIFAR10 ,1D CNN, autoencoder for MNIST images, and 3dMNIST - a special enhancement of MNIST dataset to 3D volumes.
MNIST Demo reach 99.2% in several minutes, and CIFAR10 demo reaches about 80%
I have used this framework in a project for classifying Vertebra in a 3D CT images.
=~=~=~=~=~=~=~=~=~=~=~=~=~=~=~=~=~=~=~=~
To run MNIST demo:
Go into the folder 'Demo/MNIST' , Run 'demoMnist.m' file.
The file will download MNIST dataset and start training the network.
After 15 iterations (several minutes) it will open a GUI where you can test the network performance.
In addition layer 1 filters will be shown.
=~=~=~=~=~=~=~=~=~=~=~=~=~=~=~=~=~=~=~=~
Check the 'mdCNN documentation.docx' file for more specification on how to configure a network for classification/regression
For general questions regarding network design and training , please use the [forum](https://groups.google.com/forum/#!forum/mdcnn-multidimensional-cnn-library-in-matlab).
Any other issues feel free to contact me at [email protected]
Hagay
没有合适的资源?快使用搜索试试~ 我知道了~
minist 输入实现卷积神经网络 (CNN) 的 MATLAB 工具箱.zip
共52个文件
m:42个
conf:8个
md:1个
1.该资源内容由用户上传,如若侵权请联系客服进行举报
2.虚拟产品一经售出概不退款(资源遇到问题,请及时私信上传者)
2.虚拟产品一经售出概不退款(资源遇到问题,请及时私信上传者)
版权申诉
0 下载量 63 浏览量
2023-02-08
22:58:57
上传
评论
收藏 105KB ZIP 举报
温馨提示
minist 输入实现卷积神经网络 (CNN) 的 MATLAB 工具箱.zip
资源推荐
资源详情
资源评论
收起资源包目录
minist 输入实现卷积神经网络 (CNN) 的 MATLAB 工具箱.zip (52个子文件)
minist 输入实现卷积神经网络 (CNN) 的 MATLAB 工具箱
Training
MSE.m 90B
manipulateImage.m 1KB
empty_script.m 102B
dRelu.m 62B
imresize3d.m 581B
Unit.m 46B
MSE_Cost.m 102B
CrossEnt_Cost.m 162B
centerOfMass.m 402B
Sigmoid.m 57B
CrossEnt.m 512B
Train.m 17KB
dTanh.m 71B
dSigmoid.m 79B
dUnit.m 47B
Relu.m 57B
Tanh.m 77B
GetNetworkInputs.m 4KB
imrotate3d.m 237B
loadBackroundImages.m 418B
utilCode
printNetwork.m 914B
showIso.m 1KB
checkNetwork.m 5KB
displayFilters.m 2KB
Configs
mnist99.24.conf 1KB
1d.conf 1KB
mnist.conf 2KB
autoEnc.conf 2KB
1d_conv.conf 1KB
cifar10_fast.conf 1KB
cifar10.conf 2KB
mnist3d.conf 2KB
Demo
MNIST
getMNISTdata.m 4KB
displayMNIST.m 23KB
demoMnist.m 1KB
CIFAR10
demoCIFAR10.m 535B
getCIFAR10data.m 2KB
displayCIFAR10.m 22KB
1d
demoBinEncoding_1d.m 1KB
MNIST3d
getMNIST3Ddata.m 6KB
demoMnist3D.m 669B
AutoEnc
getMNISTdata.m 4KB
demoAutoEnc.m 3KB
README.md 2KB
mdCNN documentation.docx 48KB
mdCNN
feedForward.m 7KB
backPropagate.m 8KB
updateWeights.m 3KB
verifyBackProp.m 8KB
sumDim.m 108B
CreateNet.m 5KB
initNetWeight.m 19KB
共 52 条
- 1
资源评论
天天Matlab科研工作室
- 粉丝: 3w+
- 资源: 7258
下载权益
C知道特权
VIP文章
课程特权
开通VIP
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