乱七八糟_杂乱知识点

临时学习的知识点有点乱,保存起来。

 

用这个漂亮的工具将方程式截图迅速转换为 LaTeX

https://zhuanlan.zhihu.com/p/48077774

 

乱七八糟_杂乱知识点_第1张图片


乱七八糟_杂乱知识点_第2张图片

 

乱七八糟_杂乱知识点_第3张图片

乱七八糟_杂乱知识点_第4张图片

 

乱七八糟_杂乱知识点_第5张图片

 

 

 

SENet学习笔记

https://blog.csdn.net/xjz18298268521/article/details/79078551

http://www.sohu.com/a/161633191_465975

 

 

 

机器学习中特征的处理及选择

https://www.cnblogs.com/wkslearner/p/8933685.html

 

 

scorecardpy

https://github.com/ShichenXie/scorecardpy

 

 

attention机制

论文阅读: 图像分类中的注意力机制(attention)

https://blog.csdn.net/Wayne2019/article/details/78488142

目前主流的attention方法都有哪些?

https://www.zhihu.com/question/68482809/answer/595692566

 

 

Kudu Administration

https://www.oreilly.com/library/view/getting-started-with/9781491980248/ch04.html

 

美团机器学习实践》—— 读后总结

https://www.cnblogs.com/xing901022/p/9692348.html

 

 

FM

github

https://github.com/ibayer/fastFM

Factorization Machines 学习笔记(四)学习算法

https://blog.csdn.net/itplus/article/details/40536025

推荐系统学习笔记之四 Factorization Machines 因子分解机 + Field-aware Factorization Machine(FFM) 场感知分解机

https://blog.csdn.net/asd136912/article/details/78318563

Introductory Guide – Factorization Machines & their application on huge datasets (with codes in Python)

https://www.analyticsvidhya.com/blog/2018/01/factorization-machines/

FM算法(Factorization Machine)

https://blog.csdn.net/g11d111/article/details/77430095

 

python3 拼接字符串的7种方法

https://www.cnblogs.com/Jimc/p/9634427.html

 

ython-argparse-命令行与参数解析

https://zhuanlan.zhihu.com/p/34395749

 

乱七八糟_杂乱知识点_第6张图片

解析Python中的yield关键字

https://www.cnblogs.com/zhenlingcn/p/8337788.html

 

 

 

Python绘图问题:Matplotlib中指定图片大小和像素

https://blog.csdn.net/weixin_34613450/article/details/80678522

乱七八糟_杂乱知识点_第7张图片

乱七八糟_杂乱知识点_第8张图片

乱七八糟_杂乱知识点_第9张图片

乱七八糟_杂乱知识点_第10张图片

乱七八糟_杂乱知识点_第11张图片乱七八糟_杂乱知识点_第12张图片

matplotlib(二):画布(figure)与坐标轴(axes)的布局

https://blog.csdn.net/xiaoxu2050/article/details/82253828

乱七八糟_杂乱知识点_第13张图片

 

 

 

 

 

 

Python代码中的捕捉性能-内存分析

https://blog.csdn.net/chenvast/article/details/78803911

 

 

解决Python memory error的问题(四种解决方案)

一、逐行读取

二、巧用pandas中read_csv的块读取功能

三、扩充虚拟内存

四、更新Pandas和Numpy库为64位

 

 

多进程异常处理

【python】多进程异常处理【multiprocessing】

https://blog.csdn.net/lixiaowang_327/article/details/81319923

 

 

 

https://blog.csdn.net/qq_34857250/article/details/79673698

乱七八糟_杂乱知识点_第14张图片

 

python3 - Queue队列

https://blog.csdn.net/GeekLeee/article/details/77883252

 

The magic behind Attribute Access in Python

https://codesachin.wordpress.com/2016/06/09/the-magic-behind-attribute-access-in-python/

 Python __dict__与dir()区别

https://blog.csdn.net/lis_12/article/details/53521554

1、无处不在的__dict__

https://www.cnblogs.com/alvin2010/p/9102344.html

 

 

 

 

 

 

A-深度学习基础.md

https://github.com/imhuay/Algorithm_Interview_Notes-Chinese/blob/master/A-%E6%B7%B1%E5%BA%A6%E5%AD%A6%E4%B9%A0/A-%E6%B7%B1%E5%BA%A6%E5%AD%A6%E4%B9%A0%E5%9F%BA%E7%A1%80.md

算法/深度学习/NLP面试笔记

https://github.com/imhuay/Algorithm_Interview_Notes-Chinese

第五章 卷积神经网络(CNN)

https://github.com/scutan90/DeepLearning-500-questions/blob/master/ch05_%E5%8D%B7%E7%A7%AF%E7%A5%9E%E7%BB%8F%E7%BD%91%E7%BB%9C(CNN)/%E7%AC%AC%E4%BA%94%E7%AB%A0%20%E5%8D%B7%E7%A7%AF%E7%A5%9E%E7%BB%8F%E7%BD%91%E7%BB%9C%EF%BC%88CNN%EF%BC%89.md

Topic Modeling and Latent Dirichlet Allocation (LDA) in Python

https://towardsdatascience.com/topic-modeling-and-latent-dirichlet-allocation-in-python-9bf156893c24

通俗理解LDA主题模型

https://blog.csdn.net/yhao2014/article/details/51098037

LDA---隐狄利克雷分布(TODO

https://www.jianshu.com/p/8ed5cb24ca0e

 

 

 

 

 

 

 

乱七八糟_杂乱知识点_第15张图片

 

 

图网络

谱图(Spectral Graph Theory)理解(2)

https://blog.csdn.net/StreamRock/article/details/82769865

谱图(Spectral Graph Theory)理解(1)

https://blog.csdn.net/StreamRock/article/details/82754539

Spectral Graph Theory 谱图论简谈 图的特征值和拉普拉斯型

http://www.lunarnai.cn/2018/02/04/spectral-graph/

图卷积Graph Convolutional Networks

https://blog.csdn.net/lemon759597/article/details/81104891

论文笔记之Spectral Networks and Deep Locally Connected Networks on Graphs

https://blog.csdn.net/BVL10101111/article/details/53426226

谱聚类(spectral clustering)原理总结

https://www.cnblogs.com/pinard/p/6221564.html

从CNN到GCN的联系与区别——GCN从入门到精(fang)通(qi)

https://blog.csdn.net/weixin_40013463/article/details/81089223

GRAPH CONVOLUTIONAL NETWORKS

http://tkipf.github.io/graph-convolutional-networks/#the-issue-with-regular-graphs

GraphSage: Representation Learning on Large Graphs

https://github.com/williamleif/GraphSAGE

Convolutional Neural Networks on Graphs with Fast Localized Spectral Filtering

https://github.com/mdeff/cnn_graph

图谱论(Spectral Graph Theory)基础

https://www.cnblogs.com/huangshiyu13/p/6237166.html

How powerful are Graph Convolutions? (review of Kipf & Welling, 2016)

https://www.inference.vc/how-powerful-are-graph-convolutions-review-of-kipf-welling-2016-2/

Spectral graph theory

https://en.wikipedia.org/wiki/Spectral_graph_theory

Laplacian_matrix

https://en.wikipedia.org/wiki/Laplacian_matrix

如何理解 Graph Convolutional Network(GCN)?

https://www.zhihu.com/question/54504471

浅析图卷积神经网络

https://www.jianshu.com/p/89fbed65cd04?winzoom=1

 

 

Variational Autoencoder: Intuition and Implementation

https://wiseodd.github.io/techblog/2016/12/10/variational-autoencoder/

从变分编码、信息瓶颈到正态分布:论遗忘的重要性

https://spaces.ac.cn/archives/6181

 

 

 

 

 

 

去雾算法

https://www.cnblogs.com/molakejin/p/5708883.html

 

 

宽度学习

DeepLearning | Broad Learning System 宽度学习系统 : 高效增量式浅层神经网络

https://blog.csdn.net/Liangjun_Feng/article/details/80541689

Broad-Learning-System

https://github.com/LiangjunFeng/Broad-Learning-System

 

 

浅谈对JIT编译器的理解。

https://www.cnblogs.com/insistence/p/5901457.html

 

CUDA编程之快速入门

https://www.cnblogs.com/skyfsm/p/9673960.html

CUDA编程(一): 老黄和他的核弹们

https://www.jianshu.com/p/6c4ec3490559

CUDA编程(三): GPU架构了解一下!

https://www.jianshu.com/p/87cf95b1faa0

 

 

Faster R-CNN - 目标检测详解

https://blog.csdn.net/zziahgf/article/details/79311275

一文读懂Faster RCNN

https://zhuanlan.zhihu.com/p/31426458

 

(Mask RCNN)——论文详解(真的很详细)

https://blog.csdn.net/wangdongwei0/article/details/83110305

Mask RCNN 源代码解析 (1) - 整体思路

https://blog.csdn.net/hnshahao/article/details/81231211

 

Mask R-CNN详解

https://blog.csdn.net/WZZ18191171661/article/details/79453780

MASK RCNN 源码阅读(UPDATE)

https://www.cnblogs.com/YouXiangLiThon/p/9178861.html

mask_rcnn keras源码跟读1)模型搭建

https://blog.csdn.net/jiangpeng59/article/details/80351423

MaskRCNN源码解读

https://blog.csdn.net/horizonheart/article/details/81188161

 

 

Faster R-CNN (object detection) implemented by Keras for custom data from Google’s Open Images Dataset V4

https://towardsdatascience.com/faster-r-cnn-object-detection-implemented-by-keras-for-custom-data-from-googles-open-images-125f62b9141a

 

聊聊目标检测中的多尺度检测(Multi-Scale),从YOLO,ssd到FPN,SNIPER,SSD填坑贴和极大极小目标识别

http://nooverfit.com/wp/%E8%81%8A%E8%81%8A%E7%9B%AE%E6%A0%87%E6%A3%80%E6%B5%8B%E4%B8%AD%E7%9A%84%E5%A4%9A%E5%B0%BA%E5%BA%A6%E6%A3%80%E6%B5%8B%EF%BC%88multi-scale%EF%BC%89%EF%BC%8C%E4%BB%8Eyolo%EF%BC%8Cssd%E5%88%B0fpn/

 

从RCNN到SSD,这应该是最全的一份目标检测算法盘点

https://www.jiqizhixin.com/articles/2018-04-27

 

图像目标检测一——RCNN

https://www.jianshu.com/p/11df675c9699

 

神经网络优化(初始化权重)

https://blog.csdn.net/qq_29133371/article/details/51868103

 

Convolutional Neural Networks from the ground up

https://towardsdatascience.com/convolutional-neural-networks-from-the-ground-up-c67bb41454e1

 

卷积神经网络CNN(1)——图像卷积与反卷积(后卷积,转置卷积)

https://blog.csdn.net/fate_fjh/article/details/52882134

乱七八糟_杂乱知识点_第16张图片

 

densenet与resneXt的巧妙结合-DPN网络

https://blog.csdn.net/Chunfengyanyulove/article/details/80509739

乱七八糟_杂乱知识点_第17张图片

ResNext与Xception——对模型的新思考

https://zhuanlan.zhihu.com/p/28839889

乱七八糟_杂乱知识点_第18张图片

 

论文阅读理解 - ResNeXt - Aggregated Residual Transformations for DNN

https://blog.csdn.net/zziahgf/article/details/78854456

乱七八糟_杂乱知识点_第19张图片

 

想入门设计卷积神经网络?这是一份综合设计指南

https://zhuanlan.zhihu.com/p/36791720

卷积神经网络(CNN)的结构设计都有哪些思想?

https://www.zhihu.com/question/312556066

 

 

 

 

 

 

双线性插值及其在图像中的应用

https://blog.csdn.net/hzhj2007/article/details/79449659

双线性插值的实现方法:filter+deconv

https://zhuanlan.zhihu.com/p/38964806

图像上采样:双线性插值,Deconv,Spatial transform

https://blog.csdn.net/qq_42277222/article/details/82726864

 

反卷积 转置卷积的理解

https://www.cnblogs.com/wmr95/p/9551490.html

乱七八糟_杂乱知识点_第20张图片

 

对深度可分离卷积、分组卷积、空洞卷积、转置卷积的理解

https://blog.csdn.net/yqmind/article/details/82977172

乱七八糟_杂乱知识点_第21张图片

乱七八糟_杂乱知识点_第22张图片

乱七八糟_杂乱知识点_第23张图片

 

[转载]对深度可分离卷积、分组卷积、扩张卷积、转置卷积(反卷积)的理解

 

https://www.cnblogs.com/marsggbo/p/9737991.html

 

对深度可分离卷积、分组卷积、扩张卷积、转置卷积(反卷积)的理解

https://blog.csdn.net/Chaolei3/article/details/79374563?utm_source=blogkpcl7

 

我读Faster R-CNN

https://blog.csdn.net/xuanwu_yan/article/details/52426862

乱七八糟_杂乱知识点_第24张图片

深度学习中的Normalization模型

https://zhuanlan.zhihu.com/p/43200897

 

既然cnn对图像具有平移不变性,那么利用 图像平移(shift)进行数据增强来训练cnn会有效果吗?

https://www.zhihu.com/question/301522740/answer/531606623

 

通俗理解卷积神经网络(cs231n与5月dl班课程笔记)

https://blog.csdn.net/v_JULY_v/article/details/51812459

 

 

 

全卷积网络 FCN 详解

https://www.cnblogs.com/gujianhan/p/6030639.html

FCN 全卷积网络

https://blog.csdn.net/it_lxg123/article/details/80680821

FCN于反卷积(Deconvolution)、上采样(UpSampling)

https://blog.csdn.net/nijiayan123/article/details/79416764

 

GAN

https://www.cnblogs.com/noahzhixiao/p/10171410.html

Wasserstein GAN and the Kantorovich-Rubinstein Duality

https://vincentherrmann.github.io/blog/wasserstein/

mnist_gangp.py

https://github.com/bojone/gan/blob/master/mnist_gangp.py

 

FPN

FPN(feature pyramid networks)算法讲解

https://blog.csdn.net/u014380165/article/details/72890275/

FPN详解

https://blog.csdn.net/WZZ18191171661/article/details/79494534

FPN(feature pyramid networks)算法讲解

https://blog.csdn.net/u014380165/article/details/72890275

 

 

 

Review: MSDNet — Multi-Scale Dense Networks (Image Classification)

https://towardsdatascience.com/review-msdnet-multi-scale-dense-networks-image-classification-4d949955f6d5

 

 

conv_arithmetic

https://github.com/lujingqiao/conv_arithmetic

 

纵览轻量化卷积神经网络:SqueezeNet、MobileNet、ShuffleNet、Xception

https://zhuanlan.zhihu.com/p/32746221?utm_source=wechat_session&utm_medium=social

 

深度学习之基础模型-Xception

https://blog.csdn.net/whz1861/article/details/78395684

 

深度可分离卷积(Xception 与 MobileNet 的点滴)

https://www.jianshu.com/p/38dc74d12fcf

Xception算法详解

https://blog.csdn.net/u014380165/article/details/75142710

 

Deep Learning-TensorFlow (13) CNN卷积神经网络_ GoogLeNet 之 Inception(V1-V4)

https://blog.csdn.net/diamonjoy_zone/article/details/70576775

 

大话CNN经典模型:GoogLeNet(从Inception v1到v4的演进

https://my.oschina.net/u/876354/blog/1637819

 

CVPR 2018 | 使用CNN生成图像先验,实现更广泛场景的盲图像去模糊

https://cloud.tencent.com/developer/article/1101224

 

 

 

 

 

 

ResNet介绍

https://blog.csdn.net/u013181595/article/details/80990930

https://blog.csdn.net/lanran2/article/details/79057994

 

深度学习VGG模型核心拆解

https://blog.csdn.net/qq_40027052/article/details/79015827

深度学习之基础模型-VGG

https://blog.csdn.net/whz1861/article/details/78111606

 

VGG-16、VGG-19(论文阅读《Very Deep Convolutional NetWorks for Large-Scale Image Recognition》)

https://blog.csdn.net/u011440696/article/details/77756776

一文读懂VGG网络

https://zhuanlan.zhihu.com/p/41423739

 

 

 

 

 

深度学习(二十三)Maxout网络学习

https://blog.csdn.net/hjimce/article/details/50414467

 

 

EM算法及其应用: K-means 与 高斯混合模型

https://www.cnblogs.com/massquantity/p/9416109.html

第十二、十三课 K-means算法 高斯混合模型

 

https://www.jianshu.com/p/5d546dab15f2

 

 

“Understanding Dynamic Routing between Capsules (Capsule Networks)”

https://jhui.github.io/2017/11/03/Dynamic-Routing-Between-Capsules/

Code for Capsule model used in the following paper:

https://github.com/Sarasra/models/tree/master/research/capsules

 

Unet 论文解读 代码解读

https://www.jianshu.com/p/f9b0c2c74488

深入理解深度学习分割网络Unet——U-Net: Convolutional Networks for Biomedical Image Segmentation

https://blog.csdn.net/Formlsl/article/details/80373200

 

BERT的理解

https://blog.csdn.net/yangfengling1023/article/details/84025313

 

斯坦福cs231n学习笔记(11)------神经网络训练细节(梯度下降算法大总结/SGD/Momentum/AdaGrad/RMSProp/Adam/牛顿法)

https://blog.csdn.net/huplion/article/details/79184338

 

 

 

 

 

 

 

找出无向图中所有的环的算法

https://blog.csdn.net/robin_xu_shuai/article/details/51898847

深度优先遍历找出一个无向图中的环

乱七八糟_杂乱知识点_第25张图片

https://blog.csdn.net/dfq12345/article/details/78004876

乱七八糟_杂乱知识点_第26张图片

判断一个图是否有环

http://www.cnblogs.com/TenosDoIt/p/3644225.html

 

 

Spark动态分配资源

https://blog.csdn.net/terrorblade1235/article/details/78322389

Spark动态资源分配-Dynamic Resource Allocation

http://lxw1234.com/archives/2015/12/593.htm

 

Spark 以及 spark streaming 核心原理及实践

https://www.cnblogs.com/liuliliuli2017/p/6809094.html

Spark入门实战系列--7.Spark Streaming(上)--实时流计算Spark Streaming原理介绍

https://www.cnblogs.com/shishanyuan/p/4747735.html

Spark Streaming基础与实践

https://blog.csdn.net/ForgetThatNight/article/details/79766015#

 

 

 

 

 

hive

乱七八糟_杂乱知识点_第27张图片

 

 

 

 

乱七八糟_杂乱知识点_第28张图片

linux nc命令使用详解(转)

https://www.cnblogs.com/boluoboluo/p/6437787.html

 

 

 

 

 

正交矩阵

https://zh.wikipedia.org/wiki/%E6%AD%A3%E4%BA%A4%E7%9F%A9%E9%98%B5

 

 

-- 未完待续 --

你可能感兴趣的:(deep,learning)