7월, 2017의 게시물 표시

[Deep learning] Gradient Descent Optimizer

이미지
https://icim.nims.re.kr/post/easyMath/70 알기 쉬운 산업수학 알기 쉬운 산업수학 Gradient Descent Optimizer 2017년 12월 13일(수) | 김민중 URL  (1) 주어진 목적함수  f f 의 최솟값(minimum)을 찾아가는 알고리즘으로 다음과 같은 방식으로 최솟값을 찾아간다. 초기값  x 0 x 0 을 임의로 설정, 적당한 Learning rate  α α  설정 n ≥ 0 n ≥ 0 인 정수에 대해서  x n + 1 x n + 1 은 다음과 같이 정의한다. x n + 1 : = x n − α ⋅ ∇ f ( x n ) x n + 1 := x n − α ⋅ ∇ f ( x n ) 주의사항 함수 f f 의 모양이 convex가 아닌 경우 global minimum이 아닌 local minimum으로  x n x n 이 수렴할 가능성이 있다. Learning rate  α α  값이 큰 경우 최솟값으로  x n x n 이 수렴하는 것이 아니라 발산할 수 있다. Learning rate  α α  값이 작은 경우 수렴하는 속도가 지나치게 느릴 수 있다. 방정식  2 ⋅ x = 10 2 ⋅ x = 10  의 근을 Gradient Descent를 이용해서 찾아보자. 목적함수  f ( x ) : = ( 10 − 2 x ) 2 f ( x ) := ( 10 − 2 x ) 2 으로 설정하겠다( f f 의 최솟값인 0이 되게 하는  x x 값이 우리가 원하는 방정식의 근이다). 초기값  x 0 = 0 x 0 = 0 , Learning rate  α = 0.05 α = 0.05 으로 설정 f ′ ( x ) = 4 ( 2 x − 10 ) f ′ ( x ) = 4 ( 2 x − 10 ) 이므로  x 1 x 1 은 다음과 같이 구할 수 있다. x 1 = x 0 − α ⋅ f ′ ( x 0 ) = 0 − 0.05 ⋅ ( − 40 ) = 2 x

[Xcode][IOS][Swift] Twitter api

< About requestAccessToAccounts function > 1. Environment: Xcode 8.3.3 , swift3 , IOS 10.3 2. Not work   account. requestAccessToAccounts (with: accountType, options: [:]) {             (success: Bool , error: Error ?) -> Void in             if success {                 print ( "success" )             } else {                 print ( "not success" )                              }                       } 3. Work well         account. requestAccessToAccounts (with: accountType, options: nil , completion:                          {(success, error) in                 if success {                                              }                  }) 4. From IOS 11 , we should use Twitter Kit 3 ( from dev.twitter.com ) <Reference> https://dev.twitter.com/twitterkit/ios/migrate-social-framework <Example> let account = ACAccountStore () let accountTy

[Anaconda][Python][Visual Studio] How to add virtual environment to visual studio python project.

이미지
<How to add virtual environment to visual studio python project> 1. Create virtual env There are several way to make python virtual environment. 1-1. anaconda UI 1-2. anaconda command ( conda create -n 'name of virtualevn' python=x.x  ) $> conda create -n CNTK python=3.5 1-3. With pip, virtuanenv and virtualenvwrapper https://www.blogger.com/blogger.g?blogID=8309050393695147092#editor/target=post;postID=1046788766165476929;onPublishedMenu=allposts;onClosedMenu=allposts;postNum=0;src=postname 2. After creating a python project, View -> Other windows -> python environments 3. Apply a virtual environment from already exist ( in this example from anaconda ) 3-2. Follow like the sequence number on picture. ( 1 -> 2 -> 3 -> 4 -> 5 ) <For example in my case> -> + Custom...  -> fill in description -> click ... line of prefix path -> se

[Python][Virtualenv][virtualenvwrapper] Create virtual envrionment ( pip , virtualenv, virtalenvwrapper )

1. Install pip, virtualenv , virtualenvwrapper for separate python environments $ wget https://bootstrap.pypa.io/get-pip.py $ sudo python get-pip.py $ sudo pip install virtualenv virtualenvwrapper $ sudo rm -rf get-pip.py ~/.cache/pip 2. Update .bashrc file # virtualenv and virtualenvwrapper export WORKON_HOME=$HOME/.virtualenvs source /usr/local/bin/virtualenvwrapper.sh 3. Make workplace with virtual environment $ source ~/.bashrc $ mkvirtualenv deepLab ( deepLab is name , it means you can name it , after this command run prompt of terminal will change. )

[Xcode][IOS] CoreData -> Code Generate -> Error : ,,,,used twice......

이미지
< Problem > Working with coredata in XCode. After generate relation code there is an error message. <unknown>:0: error: filename "Pattern+CoreDataProperties.swift" used twice: '/Volumes/Seagate Backup Plus Drive/Data/Projects/IPhone/Project/Patterns/Pattern+CoreDataProperties.swift' and '/Users/sunggukim/Library/Developer/Xcode/DerivedData/Patterns-bshesfmiyvjjlvegoiunmaydhdfq/Build/Intermediates/Patterns.build/Debug-iphoneos/Patterns.build/DerivedSources/CoreDataGenerated/Patterns/Pattern+CoreDataProperties.swift' <unknown>:0: note: filenames are used to distinguish private declarations with the same name Command /Applications/Xcode.app/Contents/Developer/Toolchains/XcodeDefault.xctoolchain/usr/bin/swiftc failed with exit code 1 <Solution> 1. Delete already generated files. 2. Set *.xcdatamodeld class option     Model : Current Product Module    Codegen : Manual / None 3. Generate code.

[Anaconda][spyder] Working for setup environent

이미지
This post is written to memory that how can I setup working environment with Spyder in anaconda. 1. Working with UI. Create a new environment 2. Working with command. Activate an environment 2-1. open command prompt. 2-2. Type in  activate 'VIRTUAL-ENVIRONMENT-NAME' Ex> activate tensorflow_lab After that we can see prompt changed as (tensorflow) /user/home$ 2-3.  Install some modules. conda install  xyz ex> conda install -c menpo dlib=19.4 3. Tip> conda info --envs with this command you can check available virtual environments.

[Anaconda][Opencv][Spyder] How to install opencv to anaconda (spyder).

< Install opencv to anaconda : Method 1> 1. Download opencv from  http://opencv.org/releases.html 2. Extract module to a folder. 3. Copy cv2.pyd from "\opencv\build\python\2.7\x64"                       to    "anaconda install folder\Lib\site-packages" 4. Close anaconda and spyder. 5. Re-run spyder from anaconda. 6. Test it ( from command prompt :  import cv2 ) < Install opencv to anaconda : Method 2> 1. Run spyder 2. Run command window in spyder. 3. activate some environment. ( This is optional ) 4. install opencv with below command. 5. conda install -c menpo opencv36. Test it ( from command prompt : import cv2 ) <Reference> Method 1> https://www.youtube.com/watch?v=9hb0gYCv3YI Method 2> https://github.com/conda/conda/issues/2448 https://www.blogger.com/blogger.g?blogID=8309050393695147092#editor/target=post;postID=335116236004254132;onPublishedMenu=allposts;onClosedMenu=allposts;postNum=0;src=postname