Skip to content

중앙대학교 [공학교육혁신센터] 딥러닝 IoT 과정

Notifications You must be signed in to change notification settings

Broco98/cau_2022_summer

 
 

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

14 Commits
 
 
 
 
 
 
 
 
 
 

Repository files navigation

딥러닝 IoT 과정


일자별 계획

0일차

딥러닝을 위한 라이브러리(최소) : library_for_deep_learning_shortly.ipynb Open In Colab


1일차


2일차

  • 환경

    • colab 사용법
    • python 아주 살짝
    • 기본 linux 명령어 : linux.md
  • Keras로 구현한 딥러닝 #1 : dnn_in_keras.ipynb Open In Colab

    • 표준 Keras 딥러닝 코드
    • 로스 보기
    • 은닉층과 노드 수
    • trian, test 데이터 분리
    • batch size와 학습
    • 데이터 수와 학습

3일차


4일차


5일차


6일차


7일차


8일차

  • 웹 카메라를 사용한 영상 분류

9일차

  • 웹 카메라를 사용한 물체 탐지

10일차

  • 웹 카메라를 사용한 포즈 추출

기타


Template


GAN

기타 활용

성능 개선


기타 실습


How-To


환경


기타 자료


교육에 사용된 외부 자료


딥러닝 활용을 위한 지식 구조

Environment
    jupyter
	colab
	usage
		!, %, run
    GCP virtual machine
linux
	ENV
	command
		cd, pwd, ls
		mkdir, rm, cp
		head, more, tail, cat
	util
		apt
		git, wget
		grep, wc, tree
		tar, unrar, unzip
	gpu
		nvidia-smi

python
	env
		python
			interactive
			execute file
		pip
	syntax
        variable
        data
            tuple
            list
            dict
            set
        loop
        if
        comprehensive list
        function
        class
	module
		import

libray
    numpy
        load
        operation
        shape
        slicing
        reshape
        axis + sum, mean
    pandas
        load
        view
	    operation
        to numpy
    seaborn
        charts
    matplot
        plot
        scatter
        hist
        multi draw
        show image

Deep Learning
    DNN
        concept
            layer, node, weight, bias, activation
            cost function
            GD, BP
        data
            x, y
            train, validate, test
            shuffle
        learning curve : accuracy, loss
        tuning
            overfitting, underfitting
            dropout, batch normalization, regularization
            data augmentation
        Transfer Learning
    type
        supervised
        unsupervised
        reinforcement
    model
        CNN
            vanilla, named CNN
        RNN
        GAN
    task
        Classification
        Object Detection
        Generation
	Segmentation
	Pose Extraction
	Noise Removing
	Super Resolution
	Question answering
	Auto Captioning
    data type
    	attribute data
	image data
	natural language data
	time series data

TensorFlow/Keras
    basic frame
        data preparing
            x, y
            train, valid, test
            normalization
            ImageDataGenerator
        fit
        evaluate
        predict
    model
        activation function
        initializer
    tuning
        learning rate
        regularizer
        dropout
        batch normalization
    save/load
    compile
        optimizer
        loss
        metric

About

중앙대학교 [공학교육혁신센터] 딥러닝 IoT 과정

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Languages

  • Jupyter Notebook 99.3%
  • Other 0.7%