搜索资源列表
Minist
- 用于对多数据操作的公共类,方便进行多数据库开发使用。-Public class for the operation of multiple data, and facilitate database development use.
CNNWB_05-27-2012
- 这个是我找到的卷积神经网络在minist库上数字识别最好的结果,准确率99.5 ,比C++版本的更好。程序可以直接编译运行,但是因为要下载两个数据库可能非常慢,需要你修改一下代码跳过去。如果你对cnn很感兴趣,可以找我Q:3617 28654-This is what I found convolutional neural network minist library Digital Identification best resul
code
- 基于贝叶斯分类器的minist数据集的识别-Recognition based on Bayesian classifier minist dataset
digit-database-
- perceptron neural network of minist
CNN-MINIST
- 利用卷积神经网络进行MINIST数据集的分类识别,MATLAB源程序。-Convolution neural network classification MNIST dataset, MATLAB source.
xuexi
- 基于VQ构建的手写体数字识别系统,可以用于MINIST数据库训练。-MINIST images can be identified.
number-recognitionP
- 基于matlab利用BP神经网络开发的手写数字识别,正负样本为分别为1000张,手写数字是minist库-Based on BP neural network matlab developed handwritten numeral recognition, positive and negative samples were 1000, handwritten digital library is minist
project-01-Bayes
- 利用直方图的方法以及贝叶斯分类MINIST数据集-Using the Bayesian classification MINIST data set
SVM-Minist-HandWriting-Recognition-master
- 手写字识别,svm算法~~~~~~~~~~~~~~(SVM-Minist-HandWriting-Recognition-master)
WGAN-in-Keras-master
- 基于minist手写数据的最新的WGAN实现方法(The latest method of WGAN implementation)
MINIST_CNN
- 使用卷积神经网络实现手写体识别,有train.m与test.m,里面附有数据集(use CNN to recognize the ministdataset)
数字识别
- python的keras调用theano创建cnn识别minist手写数字(use keras of python to create cnn to recognize digit wrote by hand)
DataLine
- 基于高斯概率模型的分类,这是一个10分类的情况,基于minist数据(pattern classification)
代码
- 手写数字识别,使用神经网络进行minist库的手写数字识别(Minist,I don't want to say,you can see Chinese introduction)
knn
- 首先对minist数据集进行pca降维,然后对降维后的数据进行KNN分类(First, the Minist data set is reduced by PCA, and then the data of the reduced dimension is classified by KNN)
MINIST
- mnist库上 应用DBN网络 DBN使用RBM结构,半监督网络,逐层训练(Application on the DBN network)
Extended Yale B Database
- 这是MNIST数据库(一个手写数字的数据库,它提供了六万的训练集和一万的测试集,它的图片是被规范处理过的,28*28的灰度图) 总共4个文件: train-labels-idx1-ubyte: training set labels t10k-images-idx3-ubyte:? test set images t10k-labels-idx1-ubyte:? test set labels train-images-idx
MNLIST and CNN
- 实现了在Mnist上的分类,使用了卷积神经网络(use convoluntional neural network to implement classificaiton on Minist.)
mnist
- 利用keras实现手写数字识别,使用CNN模型 全连接层+两个卷积层,最后Softmax分类器,识别率超过96%(Using keras to realize handwritten numeral recognition baesd on CNN model. One whole connection layer + two convolution layers, and a Softmax classifier. The re
MINIST
- 对于MINIST数据库手写体数字识别的研究与识别系统的实现。(Research and recognition system of handwritten numeral recognition for MINIST .)