Keras实现的卷积神经网络

如下内容来自个人github仓库，具体框架的代码也能够在仓库中找到，更加欢迎各位一块儿帮助我修改。

[法师传送门]https://github.com/AngularLock/DeepLearningFramework

A Deep Learning Framework based on Keras

Keras搭建的深度学习包 类比于MatConvNet

Tutorial

Keras is a high-level neural networks library, written in Python and capable of running on top of either TensorFlow or Theano.Below,I'll show my framework which is to solve cifar10.With the framework,you can focus on the parameters of the neurn network

Keras是一个简单好用的python深度学习框架，后端能够选择Tensorflow和Theano.如下用cifar10分类来介绍这个已经搭建好的包，以此，你只须要更加关注CNN参数的调整

implementation function 实现功能

• load data, buid model, train model

• save better model_weights,you can continue training after a pause

• at the end of every epoch will show loss&error curve

• 读取数据，生成模型，训练模型

• 网络能够实时保存权值，在终端以后依旧能够继续运算。

• 在训练时，每个epoch结束后会显示 loss 和 error曲线

1. The structure 网络结构

• data_generator
• model_setup
• callbackfn
• main

1.1 data_generator

to load and normalize raw data,this module returns 4 variable: x_train,t_train(label),x_test,t_test(label).

这个模块用于加载和规范化原始数据文件，有4个返回值：x_train,t_train(类标),x_test,t_test(类标)

1.2 model_setup

you can build your model in this module.Return the model as the returned vlue.

在此模块 你能够自由搭建CNN网络。 此模块返回值为model

1.3 callbackfn

this module is built to show the loss & error curve while training.

此模块能够实如今网络训练时 实时画出loss & error曲线

1.4 main

this file like the main function in c or other program language.all the modules above will be called in this file.

主文件，调用以上全部模块，完成主要流程：load data--build model--train model

##2. what to do next 后续版本

###2.1 Bug Fix 错误修改

• sometimes crashed when ploting loss&error curve

• sometimes warnings shows when building or training model

• 在画loss&error曲线时会无响应

• 在搭建和训练模型时会弹出某些警告

2.2 to be done 后续功能

• prediction module

• 预测 测试 模块