登录
首页 » matlab » 3dCNN

3dCNN

于 2021-01-28 发布 文件大小:14633KB
0 290
下载积分: 1 下载次数: 32

代码说明:

  3D CNN 网络 用于处理3维的图像, 比如3D 人脸识别这类工作 也可以利用这个架构进行多维的数据处理利用CNN的图像处理思想(3D convolutional nernural network)

文件列表:

3dCNN
3dCNN\CNN.m
3dCNN\DBN.m
3dCNN\DeepLearnToolbox-master
3dCNN\DeepLearnToolbox-master\.travis.yml
3dCNN\DeepLearnToolbox-master\CAE
3dCNN\DeepLearnToolbox-master\CAE\caeapplygrads.m
3dCNN\DeepLearnToolbox-master\CAE\caebbp.m
3dCNN\DeepLearnToolbox-master\CAE\caebp.m
3dCNN\DeepLearnToolbox-master\CAE\caedown.m
3dCNN\DeepLearnToolbox-master\CAE\caeexamples.m
3dCNN\DeepLearnToolbox-master\CAE\caenumgradcheck.m
3dCNN\DeepLearnToolbox-master\CAE\caesdlm.m
3dCNN\DeepLearnToolbox-master\CAE\caetrain.m
3dCNN\DeepLearnToolbox-master\CAE\caeup.m
3dCNN\DeepLearnToolbox-master\CAE\max3d.m
3dCNN\DeepLearnToolbox-master\CAE\scaesetup.m
3dCNN\DeepLearnToolbox-master\CAE\scaetrain.m
3dCNN\DeepLearnToolbox-master\CNN
3dCNN\DeepLearnToolbox-master\CNN\cnnapplygrads.m
3dCNN\DeepLearnToolbox-master\CNN\cnnbp.m
3dCNN\DeepLearnToolbox-master\CNN\cnnff.m
3dCNN\DeepLearnToolbox-master\CNN\cnnnumgradcheck.m
3dCNN\DeepLearnToolbox-master\CNN\cnnsetup.m
3dCNN\DeepLearnToolbox-master\CNN\cnntest.m
3dCNN\DeepLearnToolbox-master\CNN\cnntrain.m
3dCNN\DeepLearnToolbox-master\CONTRIBUTING.md
3dCNN\DeepLearnToolbox-master\DBN
3dCNN\DeepLearnToolbox-master\DBN\dbnsetup.m
3dCNN\DeepLearnToolbox-master\DBN\dbntrain.m
3dCNN\DeepLearnToolbox-master\DBN\dbnunfoldtonn.m
3dCNN\DeepLearnToolbox-master\DBN\rbmdown.m
3dCNN\DeepLearnToolbox-master\DBN\rbmtrain.m
3dCNN\DeepLearnToolbox-master\DBN\rbmup.m
3dCNN\DeepLearnToolbox-master\LICENSE
3dCNN\DeepLearnToolbox-master\NN
3dCNN\DeepLearnToolbox-master\NN\nnapplygrads.m
3dCNN\DeepLearnToolbox-master\NN\nnbp.m
3dCNN\DeepLearnToolbox-master\NN\nnchecknumgrad.m
3dCNN\DeepLearnToolbox-master\NN\nneval.m
3dCNN\DeepLearnToolbox-master\NN\nnff.m
3dCNN\DeepLearnToolbox-master\NN\nnpredict.m
3dCNN\DeepLearnToolbox-master\NN\nnsetup.m
3dCNN\DeepLearnToolbox-master\NN\nntest.m
3dCNN\DeepLearnToolbox-master\NN\nntrain.m
3dCNN\DeepLearnToolbox-master\NN\nnupdatefigures.m
3dCNN\DeepLearnToolbox-master\README.md
3dCNN\DeepLearnToolbox-master\README_header.md
3dCNN\DeepLearnToolbox-master\REFS.md
3dCNN\DeepLearnToolbox-master\SAE
3dCNN\DeepLearnToolbox-master\SAE\saesetup.m
3dCNN\DeepLearnToolbox-master\SAE\saetrain.m
3dCNN\DeepLearnToolbox-master\create_readme.sh
3dCNN\DeepLearnToolbox-master\data
3dCNN\DeepLearnToolbox-master\data\mnist_uint8.mat
3dCNN\DeepLearnToolbox-master\tests
3dCNN\DeepLearnToolbox-master\tests\runalltests.m
3dCNN\DeepLearnToolbox-master\tests\test_cnn_gradients_are_numerically_correct.m
3dCNN\DeepLearnToolbox-master\tests\test_example_CNN.m
3dCNN\DeepLearnToolbox-master\tests\test_example_DBN.m
3dCNN\DeepLearnToolbox-master\tests\test_example_NN.m
3dCNN\DeepLearnToolbox-master\tests\test_example_SAE.m
3dCNN\DeepLearnToolbox-master\tests\test_nn_gradients_are_numerically_correct.m
3dCNN\DeepLearnToolbox-master\util
3dCNN\DeepLearnToolbox-master\util\allcomb.m
3dCNN\DeepLearnToolbox-master\util\expand.m
3dCNN\DeepLearnToolbox-master\util\flicker.m
3dCNN\DeepLearnToolbox-master\util\flipall.m
3dCNN\DeepLearnToolbox-master\util\fliplrf.m
3dCNN\DeepLearnToolbox-master\util\flipudf.m
3dCNN\DeepLearnToolbox-master\util\im2patches.m
3dCNN\DeepLearnToolbox-master\util\isOctave.m
3dCNN\DeepLearnToolbox-master\util\makeLMfilters.m
3dCNN\DeepLearnToolbox-master\util\myOctaveVersion.m
3dCNN\DeepLearnToolbox-master\util\normalize.m
3dCNN\DeepLearnToolbox-master\util\patches2im.m
3dCNN\DeepLearnToolbox-master\util\randcorr.m
3dCNN\DeepLearnToolbox-master\util\randp.m
3dCNN\DeepLearnToolbox-master\util\rnd.m
3dCNN\DeepLearnToolbox-master\util\sigm.m
3dCNN\DeepLearnToolbox-master\util\sigmrnd.m
3dCNN\DeepLearnToolbox-master\util\softmax.m
3dCNN\DeepLearnToolbox-master\util\tanh_opt.m
3dCNN\DeepLearnToolbox-master\util\visualize.m
3dCNN\DeepLearnToolbox-master\util\whiten.m
3dCNN\DeepLearnToolbox-master\util\zscore.m
3dCNN\MexConv3D-master
3dCNN\MexConv3D-master\.build
3dCNN\MexConv3D-master\.build\Timer.obj
3dCNN\MexConv3D-master\.build\_conv3d_blas_cpu.obj
3dCNN\MexConv3D-master\.build\_conv3d_blas_gpu.obj
3dCNN\MexConv3D-master\.build\_conv3d_blas_gpu_fc.obj
3dCNN\MexConv3D-master\.build\_maxpool3d_cpu.obj
3dCNN\MexConv3D-master\.build\_maxpool3d_gpu.obj
3dCNN\MexConv3D-master\.build\_staticMem_cpu.obj
3dCNN\MexConv3D-master\.build\_staticMem_gpu.obj
3dCNN\MexConv3D-master\.build\conv3d.obj
3dCNN\MexConv3D-master\.build\maxpool3d.obj
3dCNN\MexConv3D-master\.build\staticMem.obj
3dCNN\MexConv3D-master\.build\wrapperBlas_cpu.obj

下载说明:请别用迅雷下载,失败请重下,重下不扣分!

发表评论

0 个回复

  • statcom6
    statcom matlab sumulink
    2019-05-29 06:10:54下载
    积分:1
  • wrote it myself, do not know is not appropriate, it may be wrong! Java Calculato...
    这些是自己写的,不知道合适不,也有可能会有错!java计算器的-wrote it myself, do not know is not appropriate, it may be wrong! Java Calculator
    2022-03-10 15:46:26下载
    积分:1
  • zhouzhihua
    zhouzhihua machine learning book
    2019-07-01 13:49:24下载
    积分:1
  • demo联合雨检测和去除_JORDER_release
    用深度学习做单幅图像去雨 有效的解决了去雨后雨纹残留 去雨背景模糊(through using deep learning to do single image rain removal.)
    2020-12-28 11:59:02下载
    积分:1
  • 除尘风机
    通过远程控制四套除尘风机一次启动,通过保护器反馈信号控制风机保护,并且反馈运行状态,通过延时躲开信号反馈冲击等(Through remote control, the four sets of dedusting fan start once, control the fan protection through the feedback signal of the protector, and feedback the running state, avoid the signal feedback, impact and so on through the time delay)
    2017-06-19 11:17:45下载
    积分:1
  • MATLAB生成.exe总结
    说明:  MATLAB生成.exe总结(Summary of MATLAB Generation.exe)
    2020-06-15 22:23:56下载
    积分:1
  • OpenHackSrc
    Open-Hack WoW tool, edit memory and objects, teleport
    2013-09-21 18:30:55下载
    积分:1
  • ruby
    ruby中文文档.chm 日文原版由Ruby作者matz提供;最初的英文版由GOTO Kentaro和Julian Fondren翻译;Mark Slagell进行了深入的英文翻译和整理排版;中文版由oasis_me(cai@pardan.org)翻译,由huzheng(huzheng_001@163.com)整理,校对,并于2003年1月22日发布。(ruby Chinese documents. chm)
    2010-09-03 19:49:54下载
    积分:1
  • upload
    说明:  这些文件将在两用户非正交多址(NOMA)系统中实现用于信号检测的深度学习方法[1]。三个主要脚本分别是生成训练数据、训练神经网络和生成测试结果。该神经网络用于相位衰落的静态标量信道,用于NOMA系统中同时检测2个用户的单个子载波上的传输符号。考虑并测试了两种情况:一种是导频符号数目较少,另一种是循环前缀长度较短。在这两种情况下,深度学习方法都比传统的信道估计方法具有更强的鲁棒性。(These files are to implement the deep learning method for signal detection in a two-user non-orthogonal multiple access (NOMA) system [1]. The 3 main scripts are to generate training data, to train the neural network and to produce testing results, respectively. The neural network is trained for a static scalar channel with phase fading and is used to detect transmitted symbols on a single subcarrier for 2 users simultaneously in a NOMA system. Two scenarios are considered and tested: one is with fewer number of pilot symbols and the other is with shorter length of cyclic prefix. The deep learning method is shown to be more robust than conventional channel estimation methods in both cases.)
    2020-11-16 17:49:40下载
    积分:1
  • yuyin
    对于单个高斯概率密度函数的输出整理,仅供参考(Output Finishing of Single Gauss Probability Density Function)
    2020-06-22 06:00:01下载
    积分:1
  • 696516资源总数
  • 106658会员总数
  • 16今日下载