Giter Site home page Giter Site logo

nn-implemantation's Introduction

神经网络的学习与实践

基础学习

MNIST DATASET

code for a 3-layer neural network using numpy

  • code
  • Test accuracy: 97.3%

code for a Softmax Regression using Tensorflow

  • code
  • Test accuracy: 92.5%

CNN

Based on Tensorflow framework
  • code
  • Layers: conv1+pool1+conv2+pool2+fc1+softmax
  • Test accuracy: 99.2%
Based on Keras
  • code
  • Test accuracy: 99.2%

learning PyTorch

一维信号分类任务

主要目标是识别分布式光纤系统上不同的扰动信号,参见详情

任务一

从分布式光纤同一位置依次制造三种不同扰动,进行识别。

  1. 原始数据:四种扰动信号 --> 构建数据集: code
  2. 搭建一维CNN进行分类: code
  3. 训练集准确率为99.7%, 测试集准确率为100%

任务二

扩大数据集,使用任务一的网络识别三种不同扰动。

  1. 三种扰动信号构建数据集:code
  2. 一维CNN分类:code
  3. 训练集准确率为99.9%, 测试集准确率为96.4%

任务三

将每条数据长度局限在一个传感器范围内,即50个数据点。

  • 构建数据集:code
  • 模型的训练与测试:code

以下均采用同一个一维CNN模型

基于联合采集数据集

  1. 一维信号分类结果

    • 4995条训练数据,501条验证数据,501条测试数据
    • 训练集准确率为94.5%, 测试集准确率为90.6%
  2. 二维信号分类结果

    • 4869条训练数据,489条验证数据,489条测试数据
    • 训练集准确率为100%, 测试集准确率为100%

基于混合数据集

  1. 一维混合信号分类结果
    • 19992条训练数据,1998条验证数据,1998条测试数据
    • 训练集准确率为76.8%, 测试集准确率为70.7%
  2. 二维混合信号分类结果
    • 19866条训练数据,1986条验证数据,1986条测试数据
    • 训练集准确率为100%, 测试集准确率为100%

基于剔除无效信号的混合数据集

  1. 一维有效信号分类结果
    • 7329条训练数据,732条验证数据,732条测试数据
    • 训练集准确率为91.2%, 测试集准确率为72.4%
  2. 二维有效信号分类结果
    • 12198条训练数据,1219条验证数据,1219条测试数据
    • 训练集准确率为99.9%, 测试集准确率为100%

GPR信号识别

nn-implemantation's People

Contributors

lllssf avatar

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.