搜索资源列表
main.py
- 人工神经网络入门 artificial neural network 使用sklearn 包实现分类图片，可用于手写数字识别(artificial neural network Using sklearn packet to achieve classification, can be used for handwritten numeral recognition)
数字识别系统v2
- 可以手写输入数字 但是要2014b以前的MATLAB才能运行(You can write the numbers by hand, but you can run them with the MATLAB 2014b)
手写体数字识别界面程序
- 模糊模式识别，贝叶斯，手写识别。用于识别手写的数字。有样本图片。(Fuzzy pattern recognition, Bayes, handwriting recognition. Used to recognize handwritten numbers.)
DBN的matlab代码
- 这是一个关于用数字识别训练一个手写数字识别的深度神经网络事例(This is a deep neural network example that uses digital recognition to train a handwritten numeral recognition)
VC++数字、英文字符、汉字及手写识别实例
- 简单的字符识别程序，能实现手写字符、英文、符号的识别，采用了位图以及预处理(character recognition)
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)
5-4 tensorboard visualization
- tensorflow手写数字识别学习，根据样本进行计算(learn TensorFlow with mnist)
figure_recognition
- 基于python3的利用神经网络进行的手写数字识别程序。(A handwritten numeric recognition program based on python3 based on Neural Network.)
stacking
- kaggle digitrecognizer MNIST by stacking some machine learning method, such like GBM(Gradient Boosting Method), LR, Extra Randomized Trees, Random Forest,KNN,etc.用stacking的方法实现手写数字识别MNIST。(kaggle digitrecognizer MNIST by stacking some machine learnin
mnist.pkl
- mnist数据集，用于手写数字识别的数据集，机器学习入门必备(mnist data,original data in http://yann.lecun.com/exdb/mnist/)
mnist
- 手写数字识别。通过各种数字图片进行机器识别，属于机器学习入门级别编程。(Handwritten digit recognition. The machine is recognized by various digital pictures, which belongs to the introduction level programming of machine learning.)
纯C-CNN
- 纯C深度学习库，里面包含MNIST手写数字识别数据集，编译就能训练和预测(Pure C depth learning library, which contains MNIST handwritten digital recognition data sets, compiling can be trained and predicted.)
mnistA
- 手写识别，基于tensorflow的代码，包含数据源等，供学习，代码为官方源代码(Handwriting recognition, tensorflow based code, including data sources, etc. for learning, the code is official source code)
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 recognition accuracy is over 96%
MNIST_CNN 代码及测试结果
- 只含一层卷积层的CNN也可以将手写数字识别的正确率达到99%(The CNN with only one convolutional layer can also get the correct rate of handwritten digit recognition up to 99%.)
input_data
- mnist数据集的导入文件，官网上有可能进不去(def maybe_download(filename, work_directory): """Download the data from Yann's website, unless it's already here.""")
deep_autoencoder_or_classifier@MNISTdigits
- SAE手写数字识别 MATLAB代码 deep learning(SAE deep learning MATLAB)
张哲_017034910051_03
- 基于tensorflow的手写数字识别，MLP和CNN对比(the compare between MLP and CNN in Handwriting recognition.)
MNIST数据集
- 手写数字识别数据集的训练集和测试集，关于BP神经网络(Handwritten digit recognition data set)
mnist手写数字识别
- 本代码运行良好，代码包括全连接网络和卷积网络，同时附有数据集，非常方便初学者使用。