Coder Social home page Coder Social logo

learn-tensorflow-sharp's Introduction

TensorflowSharp教程

Tensorflow是一个人工智能框架。TensorflowSharp是对Tensorflow C语言版接口的封装,便于.net开发人员在项目中使用Tensorflow。

目录

01 HelloWorld:TensorflowSharp入门。

02 UsePlaceholder:占位符的使用。

03 UseVariable:变量的使用。

04 InitVariable:变量的初始化。

05 UseMatrix:矩阵相加、数乘、矩阵相乘。

p06_LinearRegression:线性回归。

p07_MNIST:手写数字识别。

p08_UseTensor:张量的使用。

p09_GenerateData:产生序列、正态分布随机数和随机位置。

p10_CalculateGradient:计算倾斜度(偏导数)。

p11_ReduceMethod:ReduceMean、ReduceSum计算原理和方法。

p12_ClipMatrix:裁剪矩阵(限制矩阵的最小、最大值)。

p13_BitwiseOperation:按位与、按位或、按位异或运算。

p14_UseStack:使用堆栈。

p15_PartialRun:部分运行。

p16_ModelSave:保存模型。(未实现)

p17_TFCoreTest:TFCore测试。

p18_TFBufferTest:TFBuffer测试。

p19_TFDataTypeTest:TFDataType测试。

p20_ComparisonOperators:比较运算符。

p22_ConditionalOperators:条件运算符。

示例

TensorflowSharp的用法还是很简单的

// 创建图
var g = new TFGraph();

// 定义常量
var a = g.Const(2);
var b = g.Const(3);

// 加法和乘法运算
var add = g.Add(a, b);
var mul = g.Mul(a, b);

// 创建会话
var sess = new TFSession(g);

// 计算加法
var result1 = sess.GetRunner().Run(add).GetValue();
Console.WriteLine("a+b={0}", result1);

// 计算乘法
var result2 = sess.GetRunner().Run(mul).GetValue();
Console.WriteLine("a*b={0}", result2);

// 关闭会话
sess.CloseSession();

执行后输出结果

a+b=5
a*b=6

注意事项

  1. 国内目前无法访问Tensorflow官网,但是可以访问谷歌提供的Tensorflow官网镜像

  2. 国内使用NuGet安装TensorflowSharp很容易失败,可以直接从Nuget官网下载,然后改后缀名zip,解压后手工安装。

  3. TensorflowSharp项目使用的.net版本必须高于4.6.1,本教程使用的版本是4.7.0,可以在属性选项卡中设置。

  4. TensorflowSharp项目必须使用64位CPU,需要在属性选项卡生成中,去掉首选32位的勾选

  5. 本教程需要在根目录新建Libs文件夹,请将第二步解压出来的TensorFlowSharp.dll放在该文件夹;另外运行示例还需要把libtensorflow.dll复制到每个项目的bin/Debug目录。如果提示找不到Tensorflow命名空间,请重新添加引用。

  6. 最新版libtensorflow.dll下载:http://ci.tensorflow.org/view/Nightly/job/nightly-libtensorflow-windows/lastSuccessfulBuild/artifact/lib_package/libtensorflow-cpu-windows-x86_64.zip

网站

learn-tensorflow-sharp's People

Contributors

tengge1 avatar

Stargazers

 avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar

Watchers

 avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar

learn-tensorflow-sharp's Issues

konnichiwa

thanks for share
arigato
do you have any contact information data?,,
im so happy if you can mail me [email protected]

or whatsapp +90 507 0 44 3 888

thanks sensei

thanks for lessons

please dont stop

let us learn more tensorflowsharp

for example

how to install run on windows or linux or create an example for picture learn or make learn something for ai
like classafaction and more

谢谢

where is new shares

please start a new tenrsorflowsharp lessons

for example learn how to image process

关于第六课LR回归的教程疑问

你好,首先非常感谢你关于tensorsharp的教程,我上网找了大半圈都没找到任何别的资源,直到来到你这里,受益匪浅!

你设定了一个线性的公式去随机生成训练集,但是我有两个疑问:

  1. 为什么AddGradient里面的参数b并没有根据loss更新?
    2.为什么每次喂数据,都是直接一个xData列表塞进去而不是xData[i]一组组数据塞进去呢?这两者有没有区别?

非常感谢!

In ModelSave

in ModelSave Example, I find a exception:Shape must be rank 1 but is rank 0 for 'Save0' (op: 'Save') with input shapes: [], [], [].
I find nothing solution for it, please give some advices

Recommend Projects

  • React photo React

    A declarative, efficient, and flexible JavaScript library for building user interfaces.

  • Vue.js photo Vue.js

    🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.

  • Typescript photo Typescript

    TypeScript is a superset of JavaScript that compiles to clean JavaScript output.

  • TensorFlow photo TensorFlow

    An Open Source Machine Learning Framework for Everyone

  • Django photo Django

    The Web framework for perfectionists with deadlines.

  • D3 photo D3

    Bring data to life with SVG, Canvas and HTML. 📊📈🎉

Recommend Topics

  • javascript

    JavaScript (JS) is a lightweight interpreted programming language with first-class functions.

  • web

    Some thing interesting about web. New door for the world.

  • server

    A server is a program made to process requests and deliver data to clients.

  • Machine learning

    Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.

  • Game

    Some thing interesting about game, make everyone happy.

Recommend Org

  • Facebook photo Facebook

    We are working to build community through open source technology. NB: members must have two-factor auth.

  • Microsoft photo Microsoft

    Open source projects and samples from Microsoft.

  • Google photo Google

    Google ❤️ Open Source for everyone.

  • D3 photo D3

    Data-Driven Documents codes.