Code Monkey home page Code Monkey logo

deeplearning-notes's Introduction

记录DeepLearning学习过程

目录

1. Learning

(1) Basic

科普文章:

机器学习:

深度学习:

深度学习系列文章:

其他文章:

(2) 常见模型讲解及实现

Paper讲解

ResNet

(1) 讲解

(2) 实践

关于残差连接:resnet中的残差连接,你确定真的看懂了?

更多内容请看我单独写的一个文档:ResNet(残差网络).md

(3) Images segmentation(图像分割: 语义/实例/场景分割)

semseg-Aticles

①什么是图像分割?

  • 图像分割 传统方法 整理

    图片分割根据灰度、颜色、纹理、和形状等特征将图像进行划分区域,让区域间显差异性,区域内呈相似性。主要分割方法有:

    基于阈值的分割
    基于边缘的分割
    基于区域的分割
    基于图论的分割
    基于能量泛函的分割
  • 十分钟看懂图像语义分割技术

②综述类/总结类:

③深度学习语义分割模型的介绍:

④图像分割的衡量指标:

语义分割其实就是对图片的每个像素都做分类。其中,较为重要的语义分割数据集有:VOC2012 以及 MSCOCO。

semseg-Repositories

semseg-Papers

论文汇集:

semseg-Videos

(4) Object Detection(目标检测)

(待更……)

(5) Reinforce Learning(强化学习/增强学习)

RL-Articles

2. Questions

3. Competition

(1) Kaggle

Kaggle官网:https://www.kaggle.com/

(2) 天池

天池AI开发者社区:https://tianchi.aliyun.com/home/

4. Papers-Links

(1) Basics

  • 《A guide to convolution arithmetic for deep》{Paper}
  • 《Bag of Tricks for Image Classification with Convolutional Neural Networks》{Paper}

(2) Models

  • [1989]LeNet:《Gradient-Based Learning Applied to document Recognition》{Paper}

  • [2012]AlexNet:《ImageNet Classification with Deep Convolutional Neural Networks》{Paper}

  • [2014]Inception v1:《Going deeper with convolutions》{Paper}

    注:先前叫 GoogLeNet,现在简单地被称为 Inception vN,其中 N 指的是由 Google 定的版本号。

  • [2014]VGGNet:《Very Deep Convolutional Networks for Large-Scale Image Recognition》{Paper}

  • [2015]Inception v2:《Batch Normalization Accelerating Deep Network Training by Reducing Internal Covariate Shift》{Paper}

  • [2015]Inception v3:《Rethinking the Inception Architecture for Computer Vision》{Paper}

  • [2015]ResNet:《Deep Residual Learning for Image Recognition》{Paper}

  • [2016]Inception v4:《Inception-v4, Inception-ResNet and the Impact of Residual Connections on Learning》{Paper}

(3) Images segmentation

  • FCN:《Fully Convolutional Networks for Semantic Segmentation》 [Paper-v1] [Paper-v2](最新提交时间:2015.03.08)
  • U-Net:《U-Net: Convolutional Networks for Biomedical Image Segmentation》[Paper](最新提交时间:2015.05.18)
  • SegNet:《SegNet: A Deep Convolutional Encoder-Decoder Architecture for Image Segmentation》[Paper-v1] [Paper-v2] [Paper-v3](最新提交时间:2016.11.10)
  • Dilated Convolutions:《Multi-Scale Context Aggregation by Dilated Convolutions》[Paper-v1] [Paper-v2] [Paper-v3](最新提交时间:2016.04.30)
  • DeconvNet:《Learning Deconvolution Network for Semantic Segmentation》[Paper](最新提交时间:2015.05.17)
  • RefineNet:《RefineNet: Multi-Path Refinement Networks for High-Resolution Semantic Segmentation》[Paper-v1] [Paper-v2] [Paper-v3](最新提交时间:2016.11.25)
  • PSPNet:《Pyramid Scene Parsing Network》[Paper-v1] [Paper-v2](最新提交时间:2017.04.27)
  • Large Kernel Matters:《Large Kernel Matters -- Improve Semantic Segmentation by Global Convolutional Network》[Paper](最新提交时间:2017.03.08)
  • DeepLab 系列:
    • DeepLab v1:《Semantic Image Segmentation with Deep Convolutional Nets and Fully Connected CRFs》Paper-v1 [Paper-v2] [Paper-v3] [Paper-v4](最新提交时间 :2016.06.07)
    • DeepLab v2:《DeepLab: Semantic Image Segmentation with Deep Convolutional Nets, Atrous Convolution, and Fully Connected CRFs》[Paper-v1] [Paper-v2](最新提交时间:2017.05.12)
    • DeepLab v3:《Rethinking Atrous Convolution for Semantic Image Segmentation》[Paper-v1] [Paper-v2] [Paper-v3](最新提交时间:2017.12.05)
    • DeepLab v3+:《Encoder-Decoder with Atrous Separable Convolution for Semantic Image Segmentation》[Paper-v1] [Paper-v2] [Paper-v3](最新提交时间:2018.08.22)
  • NAS:《Searching for Efficient Multi-Scale Architectures for Dense Image Prediction》Paper-v1(提交时间:2018.09.11)

(4) Object Detection

  • R-CNN:《Rich feature hierarchies for accurate object detection and semantic segmentation》Paper
  • Fast R-CNN:《Fast R-CNN》 Paper
  • Faster R-CNN:《Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks》 Paper
  • Mask R-CNN :《Mask R-CNN》 Paper

(5) Others

5. Interview

6. Resources

(1) Books

这两年关于人工智能特别是深度学习的书如雨后春笋很多。下面列举一些被大家普遍评价较高以及我有大概浏览过觉得不错的书,当个参考和记录:

1.机器学习

  • 《写给人类的机器学习》译者:飞龙(等);原书:Machine Learning for Humans
  • 周志华《机器学习》,2016年1月
  • Peter Harrington 《机器学习实战》,中文版译者:李锐/李鹏/曲亚东/王斌 ,2013年6月 [GitHub代码仓库]

2.深度学习

  • Michael Nielsen《Neural Networks and Deep Learning》,中文版《神经网络与深度学习》
  • 弗朗索瓦•肖莱 《Python深度学习》,中文版译者:张亮,2018年8月
  • 张玉宏《深度学习之美:AI时代的数据处理与最佳实践》,2018年6月
  • 张平《图解深度学习与神经网络:从张量到TensorFlow实现》,2018年09月
  • 李沐、Aston Zhang 等人《动手学深度学习》预览版:《动手学深度学习》
  • 邱锡鹏《神经网络与深度学习》:在线阅读

3.深度学习框架

  • 泽宇/顾思宇 《Tensorflow:实战Google深度学习框架》
  • 黄文坚/唐源《TensorFlow实战》
  • 廖星宇《深度学习入门之PyTorch》 [代码仓库]
  • 陈云《深度学习框架PyTorch:入门与实践》 [代码仓库]

(2) Videos

(3) GitHub

  • apachecn/AiLearning

  • DeepLearning-500-questions

    深度学习500问,以问答形式对常用的概率知识、线性代数、机器学习、深度学习、计算机视觉等热点问题进行阐述,以帮助自己及有需要的读者。 全书分为15个章节,近20万字。由于水平有限,书中不妥之处恳请广大读者批评指正。 未完待续...

  • AI初学者--(机器学习爱好者)

    本网站是一个公益性网站,致力于人工智能(AI)方面的课程的翻译、笔记分享等。

    本人2014年下半年开始翻译吴恩达老师的机器学习课程字幕,并写了课程的中文笔记。笔记被下载了几万次,应该帮助了不少人,也有很多人一直在帮助我,现在我把笔记的word原稿和markdown原稿分享给大家。

    …… ——By 黄海广

  • daily-paper-computer-vision

    记录每天整理的计算机视觉/深度学习/机器学习相关方向的论文。

7. Thinking

deeplearning-notes's People

Contributors

jayboxyz avatar

Watchers

James Cloos avatar

Forkers

peiwang27

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.