CUDA-CNN-master
所属分类:matlab编程
开发工具:matlab
文件大小:1450KB
下载次数:30
上传日期:2015-04-02 14:52:16
上 传 者:
lihuayuluo0621
说明: CNN(卷积神经网络) cuda的加速。
start-of-art结果的流行的数据集
1。测试mnist库并获得99.76 ,投票后(99.82 )(最好的99.79 )
2。测试cifar-10并获得81.42 最好(90 )
3。测试cifar - 100和51.13 (最好的65 )
(CNN accelerated by cuda.
The start-of-art result s of popular datasets
1. Test on mnist and get 99.76 , after voting(99.82 ) (best 99.79 )
2. Test on cifar-10 and get 81.42 (best 90 )
3. Test on cifar-100 and get 51.13 (best 65 ))
文件列表:
.cproject (13175, 2015-03-19)
.project (809, 2015-03-19)
Config (0, 2015-03-19)
Config\ChineseConfig.txt (1093, 2015-03-19)
Config\Cifar100Config.txt (1906, 2015-03-19)
Config\Cifar10Config.txt (1987, 2015-03-19)
Config\Cifar10Config1.txt (1813, 2015-03-19)
Config\Cifar10Config2.txt (2065, 2015-03-19)
Config\Cifar10Config80.39.txt (1849, 2015-03-19)
Config\Cifar10Config81.42.txt (1890, 2015-03-19)
Config\MnistConfig.txt (1822, 2015-03-19)
Config\whiteNoise_80 (0, 2015-03-19)
Config\whiteNoise_80\Cifar10Config80.39.txt (1849, 2015-03-19)
Config\whiteNoise_80\log.txt (45376, 2015-03-19)
Debug (0, 2015-03-19)
Debug\common (0, 2015-03-19)
Debug\common\subdir.mk (1180, 2015-03-19)
Debug\dataAugmentation (0, 2015-03-19)
Debug\dataAugmentation\subdir.mk (1196, 2015-03-19)
Debug\layers (0, 2015-03-19)
Debug\layers\subdir.mk (1511, 2015-03-19)
Debug\makefile (1647, 2015-03-19)
Debug\nsightbuilddata (13, 2015-03-19)
Debug\objects.mk (316, 2015-03-19)
Debug\readData (0, 2015-03-19)
Debug\readData\subdir.mk (1207, 2015-03-19)
Debug\sources.mk (598, 2015-03-19)
Debug\subdir.mk (1402, 2015-03-19)
Release (0, 2015-03-19)
Release\DataAugmentation (0, 2015-03-19)
Release\DataAugmentation\subdir.mk (1184, 2015-03-19)
Release\common (0, 2015-03-19)
Release\common\subdir.mk (1787, 2015-03-19)
Release\dataAugmentation (0, 2015-03-19)
Release\dataAugmentation\subdir.mk (1191, 2015-03-19)
Release\layers (0, 2015-03-19)
Release\layers\subdir.mk (1913, 2015-03-19)
... ...
>CUDA-CNN
>========
>Document
>1. The simple c version author is
Eric
>2.
Overlap Data Transfers in CUDA
>
>Results
>--------
>CNN accelerated by cuda.
>The
start-of-art result's of popular datasets
>1. Test on
mnist and get 99.76%, after voting(99.82%) (best 99.79%)
>2. Test on cifar-10 and get 81.42% (best 90%)
>3. Test on cifar-100 and get 51.13% (best 65%)
***
>Feature
>--------
>1. Use ***
DropConnect*** to train the NetWork
>2. Support checkpoint, the program will save the best test result and save the network weight in the file "Result/checkPoint.txt", If the program exit accidentally, you can continue the program form this checkpoint.
>3. Translate the data set of mnist, including scale, rotate, ***distortion***,
accordding to
Best Practices for Convolutional Neural Networks Applied to Visual Document Analysis.
>4. The log will be saved in the file "Result/log.txt".
>5. In the convolutional layers, you can chose ***combine feature maps***, according to
notes on Convolutional Neural NetWorks.
>6. Support
local connection layers.
The demo Configure file
Cifar10 is very small but can get 79.9%.
>7. If you want the program run fast, you can set the "TEST_EPOCH" to be large.
***
>Compile
>-------
>Depend on opencv and cuda
>You can compile the code on windows or linux.
###SDK include path(-I)
>* linux: /usr/local/cuda/samples/common/inc/ (For include file "helper_cuda"); /usr/local/include/opencv/ (Depend on situation)
>* windows: X:/Program Files (x86) /NVIDIA Corporation/CUDA Samples/v6.5/common/inc (For include file "helper_cuda"); X:/Program Files/opencv/vs2010/install/include (Depend on situation)
>
###Library search path(-L)
>* linux: /usr/local/lib/
>* windows: X:/Program Files/opencv/vs2010/install/x86/cv10/lib (Depend on situation)
>
###libraries(-l)
>* opencv_core
>* opencv_highgui
>* opencv_imgproc
>* opencv_imgcodecs (need for opencv3.0)
>* ***cublas***
>* ***curand***
>* ***cudadevrt***
>
###GPU compute
>* capability 2.0
###Windows
>1. Install vs2010.
>2. Download and install
opencv-2.4 or other higher versions
>3. Download and install
cuda-5.0 or other higher versions
>4. When you create a new project using VS2010, You can find NVIDIA-CUDA project template, create a cuda-project.
>5. View-> Property Pages-> Configuration Properties-> CUDA C/C++ -> Device-> Code Generation-> compute_20,sm_20
>6. View-> Property Pages-> Configuration Properties-> CUDA C/C++ -> Common-> Generate Relocatable Device Code-> Yes(-rdc=true)
>7. View-> Property Pages-> Configuration Properties-> Linker-> Input-> Additional Dependencies-> libraries(-l)
>8. View-> Property Pages-> Configuration Properties-> VC++ Directories-> General-> Library search path(-L)
>9. View-> Property Pages-> Configuration Properties-> VC++ Directories-> General-> Include Directories(-I)
###Linux
>1. Install opencv and cuda
>2. Start the ***nsight*** from cuda
>3. Create an 'empty cuda' project and import the clone code
>4. Project->Proerties for add-> Build-> Settings->CUDA->Device linker mode: separate compilation
>5. Project->Proerties for add-> Build-> Settings->CUDA->Generate PTX code 2.0
>6. Project->Proerties for add-> Build-> Settings->CUDA->Generate GPU code 2.0
>7. Project->Proerties for add-> Build-> Settings->Tool Settings->NVCC Compiler->includes: +/usr/local/cuda/samples/common/inc/; + opencv sdk include path ;
>8. Project->Proerties for add-> Build-> Settings->Tool Settings->NVCC Linkers->Libraries: libraries(-l)
>9. Project->Proerties for add-> Build-> Settings->Tool Settings->NVCC Linkers->Libraries search path(-L): /usr/local/lib/
***
>Config
>1.
CIFAR10
>2.
MNIST
>3.
CIFAR100
***
>Informations
>------------
>* Author :zhxfl
>* Mail :zhxfl@mail.ustc.edu.cn
>* 单位 :中国科学技术大学苏州研究院多核系统实验室
>* Welcome for any suggest!!
>*
近期下载者:
相关文件:
收藏者: