profile-img
The merit of an action lies in finishing it to the end.
slide-image
์ „์ฒด ๊ธ€ + 28
list_img
์นด์ด์ŠคํŠธ ๋ฐ์ดํ„ฐ์‚ฌ์ด์–ธ์Šค๋Œ€ํ•™์› ํ•ฉ๊ฒฉ ํ›„๊ธฐ (2025 ํ›„๊ธฐ/์„œ๋ฅ˜, ๋ฉด์ ‘)
user-img iamnotwhale
2025.07.04
์ด๋ฒˆ ํ•™๊ธฐ์— ์„œ์šธ๋Œ€, ์นด์ด์ŠคํŠธ ๋ฐ์ดํ„ฐ์‚ฌ์ด์–ธ์Šค๋Œ€ํ•™์›์— ๋„์ „ํ•˜์˜€๋Š”๋ฐ์„œ์šธ๋Œ€๋Š” 1์ฐจ ๋ฉด์ ‘์—์„œ ๋ถˆํ•ฉ๊ฒฉํ•˜์˜€์ง€๋งŒ ์นด์ด์ŠคํŠธ์— ์ตœ์ข… ํ•ฉ๊ฒฉํ•˜๊ฒŒ ๋˜์—ˆ์Šต๋‹ˆ๋‹ค. ์นด์ด ๋ฐ์‹ธ ํ•ฉ๊ฒฉ ํ›„๊ธฐ ๋ธ”๋กœ๊ทธ ์˜ฌ๋ ค ์ฃผ์‹  ๋ถ„ ๋„์›€์„ ๋งŽ์ด ๋ฐ›์•„์„œ์ €๋„ ์ด ๋Œ€ํ•™์›์„ ์ค€๋น„ํ•˜๋Š” ๋ถ„๋“ค์—๊ฒŒ ๋„์›€์ด ๋ ๊นŒ ์‹ถ์–ด์„œ ๊ธ€์„ ์ž‘์„ฑํ•˜๊ฒŒ ๋์Šต๋‹ˆ๋‹ค. ๋ณธ๊ฒฉ์ ์ธ ์ž…์‹œ ์ง„ํ–‰ ์ „ ์ž…์‹œ์„ค๋ช…ํšŒ๋ฅผ ์ง„ํ–‰ํ•˜๋Š” ๊ฒƒ์œผ๋กœ ์•Œ๊ณ  ์žˆ์Šต๋‹ˆ๋‹ค.์ €์˜ ๊ฒฝ์šฐ๋Š” ์ž…์‹œ ๊ธฐ๊ฐ„์— ๊ฐ‘์ž๊ธฐ ์›์„œ๋ฅผ ์“ฐ๊ฒŒ ๋˜์–ด์„œ ์ž…์‹œ์„ค๋ช…ํšŒ๋Š” ์ฐธ์—ฌํ•˜์ง€ ๋ชปํ•˜์˜€์œผ๋‚˜,๊ธฐํšŒ๊ฐ€ ๋œ๋‹ค๋ฉด ์ž…์‹œ์„ค๋ช…ํšŒ๋Š” ๊ผญ ์ฐธ์„ํ•˜์‹œ๊ธธ ๋ฐ”๋ž๋‹ˆ๋‹ค. 1) ์ŠคํŽ™ํ•™๊ต: ๊ณ ๋ ค๋Œ€์ „๊ณต: ์ƒ๋ช…๊ณ„์—ด (์ปดํ“จํ„ฐํ•™๊ณผ ์ด์ค‘์ „๊ณต)ํ•™์ : ์ „์ฒด 3.81/4.5, ์ „๊ณต 3.56/4.5์ „๊ณต ๊ด€๋ จ ํ™œ๋™: ๊ต๋‚ด ๋”ฅ๋Ÿฌ๋‹ ํ•™ํšŒ 1๋…„, ์—ฐํ•ฉ ์ธ๊ณต์ง€๋Šฅ/๋ฐ์ดํ„ฐ๋ถ„์„ ๋™์•„๋ฆฌ 2๋…„, ๋ฐ์ดํ„ฐ๋ถ„์„ ๊ณต๋ชจ์ „ ์ž…์ƒ 1ํšŒ์—ฐ๊ตฌ ๊ด€๋ จ..
[git] fatal: the remote end hung up unexpectedly everything up-to-date ์˜ค๋ฅ˜ ํ•ด๊ฒฐ
user-img iamnotwhale
2024.12.10
vscode๋ฅผ ์ด์šฉํ•ด์„œ git ๊ด€๋ฆฌ๋ฅผ ํ•˜๊ณ  ์žˆ๋Š”๋ฐ (์ฝ”๋“œ๋ฅผ ๋”ฐ๋กœ ์ž‘์„ฑํ•˜์ง€๋Š” ์•Š๊ณ  ํ™•์žฅ ํ”„๋กœ๊ทธ๋žจ์„ ์ด์šฉํ•œ๋‹ค) ๋‚œ์ƒ ์ฒ˜์Œ ๋ณด๋Š” ์˜ค๋ฅ˜๋ฅผ ๋งž๋‹ฅ๋œจ๋ ธ๋‹ค."unexpected disconnect while reading sideband packet fatal: the remote end hung up unexpectedly everything up-to-date"์ด๋ผ๋Š” ์ฐฝ์ด ๋œจ๋ฉด์„œ ํ‘ธ์‹œ๊ฐ€ ๋˜์ง€ ์•Š๋Š” ํ˜„์ƒ์ด ๋ฐœ์ƒํ–ˆ๋‹ค.์ธํ„ฐ๋„ท ์˜ค๋ฅ˜์ธ๊ฐ€ ์‹ถ์–ด์„œ ๋‹ค๋ฅธ ์™€์ดํŒŒ์ด๋ฅผ ์ด์šฉํ•˜์˜€์ง€๋งŒ ์ด ๋ฌธ์ œ๋Š” ์•„๋‹ˆ์—ˆ๋‹ค. ๊ตฌ๊ธ€๋ง์„ ํ†ตํ•ด ์˜ค๋ฅ˜์˜ ์›์ธ์„ ํŒŒ์•…ํ–ˆ๋‹ค. ๊ธฐ๋ณธ์ ์œผ๋กœ ํ‘ธ์‹œํ•  ์ˆ˜ ์žˆ๋Š” ํ•œ ๊ฐœ ํŒŒ์ผ์˜ ์ตœ๋Œ€ ์šฉ๋Ÿ‰์ด 1MB์—ฌ์„œ, ์šฉ๋Ÿ‰ ์ดˆ๊ณผํ•œ ํŒŒ์ผ์„ pushํ•  ๋•Œ ์˜ค๋ฅ˜๊ฐ€ ๋ฐœ์ƒํ•œ๋‹ค๊ณ  ํ•œ๋‹ค. ์ด๋ฒˆ์— ์ฒ˜์Œ์œผ๋กœ 1MB๊ฐ€ ๋„˜๋Š” ํŒŒ์ผ์„ ์—…๋กœ๋“œํ•ด์„œ ๊ทธ๋Ÿฐ ๊ฒƒ์ด์—ˆ๋‹ค.์ด๋ฅผ ..
[Ensemble Learning] Bagging vs. Boosting
user-img iamnotwhale
2024.12.05
Ensemble Learning์ด๋ž€?์—ฌ๋Ÿฌ ๊ฐœ์˜ base-learner(base-model)๋ฅผ ์กฐํ•ฉํ•˜๋Š” ๋ชจ๋ธ Bagging- ๋‹ค๋ฅธ ์ด๋ฆ„: Bootstrap Aggregating- Bootstrap: Random Sampling ๋ฐฉ๋ฒ•๋ก  ์ค‘ ํ•˜๋‚˜. ๋ณต์› ์ถ”์ถœ์„ ์‹œํ–‰ํ•œ๋‹ค.- ๋ณต์› ์ถ”์ถœ์„ ํ†ตํ•ด ๋™์ผํ•œ ํฌ๊ธฐ์˜ ๋ฐ์ดํ„ฐ์…‹์„ ์—ฌ๋Ÿฌ ๊ฐœ ์ƒ์„ฑํ•œ ํ›„, ์•™์ƒ๋ธ”์„ ๊ตฌ์„ฑํ•˜๋Š” ํ•™์Šต ๋ฐฉ์‹- ๋‹จ์ : ๋žœ๋ค ์ƒ˜ํ”Œ๋ง์€ ์šด์— ์˜์กดํ•œ๋‹ค.๋งŒ์•ฝ, decision tree๋ฅผ ํ•™์Šต์‹œํ‚จ๋‹ค๊ณ  ๊ฐ€์ •ํ•ด๋ณด์ž.boostrap์œผ๋กœ ๋ฐ์ดํ„ฐ๋ฅผ ์ถ”์ถœํ•  ๊ฒฝ์šฐ, ๋ณต์› ์ถ”์ถœ์ด๊ธฐ ๋•Œ๋ฌธ์— ๊ฐ™์€ ๋ฐ์ดํ„ฐ๊ฐ€ ์—ฌ๋Ÿฌ ๋ฒˆ ๋ฝ‘ํž ์ˆ˜ ์žˆ๊ณ , ๊ทธ๋ ‡๊ธฐ ๋•Œ๋ฌธ์— ๋ฐ์ดํ„ฐ์…‹๋ผ๋ฆฌ ์œ ์‚ฌํ•˜๋‹ค. ๊ทธ๋Ÿฌ๋ฏ€๋กœ ์ด๋Ÿฐ ๊ฒฝ์šฐ decision tree์˜ root node๋Š” ๋ชจ๋ธ ๊ฐ„์— ํ•ญ์ƒ ๋น„์Šทํ•ด์งˆ ์ˆ˜๋ฐ–์— ์—†๋‹ค.  Boos..
[Selenium] ๋ฌดํ•œ์Šคํฌ๋กค ํŽ˜์ด์ง€ ์Šคํฌ๋กค ๋๊นŒ์ง€ ๋‚ด๋ฆฌ๋Š” ๋ฐฉ๋ฒ•
user-img iamnotwhale
2024.11.28
๋ฌดํ•œ์Šคํฌ๋กค ํŽ˜์ด์ง€์—์„œ ํฌ๋กค๋ง์„ ํ•  ์ผ์ด ์ƒ๊ฒผ๋‹ค.๋ฌดํ•œ์Šคํฌ๋กค ํŽ˜์ด์ง€์—์„œ ํ•ญ๋ชฉ์˜ ๋ชฉ๋ก์„ ๋ชจ๋‘ ์ˆ˜์ง‘ํ•˜๊ธฐ ์œ„ํ•ด์„œ๋Š” ์Šคํฌ๋กค ๋ฐ”๋ฅผ ๋งจ ๋๊นŒ์ง€ ๋‚ด๋ ค์•ผํ•œ๋‹ค.๋”ฐ๋ผ์„œ ํŽ˜์ด์ง€๋ฅผ ๋‚ด๋ ค๋„ ๊ณ„์†ํ•ด์„œ ์ƒˆ๋กœ์šด ๋‚ด์šฉ์ด ๋กœ๋”ฉ๋˜๋Š” ๋ฌดํ•œ์Šคํฌ๋กค ์›นํŽ˜์ด์ง€์—์„œ ์Šคํฌ๋กค ๋ฐ”๋ฅผ ๊ณ„์†ํ•ด์„œ ๋‚ด๋ฆฌ๋Š” ๋ฐฉ๋ฒ•์„ ์•Œ์•„๋ณด์ž. ์—ฌ๋Ÿฌ ๊ฐ€์ง€ ๋ฐฉ๋ฒ•์ด ์žˆ๋Š”๋ฐ, Keys.PAGE_DOWN๋ฅผ ์‚ฌ์šฉํ•  ์ˆ˜ ์žˆ๋‹ค. 1. ํ•„์š” ๋ผ์ด๋ธŒ๋Ÿฌ๋ฆฌ๋ฅผ ๋ถˆ๋Ÿฌ์˜จ๋‹ค.from selenium import webdriverfrom selenium.webdriver.common.keys import Keysfrom selenium.webdriver.chrome.options import Optionsfrom selenium.webdriver.common.by import By 2. Keys.PAGE_DOWN..
list_img
[LLM] SQuAD / KorQuAD
user-img iamnotwhale
2024.11.21
ํ•™ํšŒ์—์„œ ์ฃผ์–ด์ง„ ์ง€๋ฌธ์— ๋Œ€ํ•œ ๊ฐ๊ด€์‹ ์งˆ๋ฌธ์„ ์ƒ์„ฑํ•˜๋Š” Question Generation NLP ํ”„๋กœ์ ํŠธ๋ฅผ ์ง„ํ–‰ ์ค‘์ด๋‹ค.QG ํ”„๋กœ์ ํŠธ์— ์‚ฌ์šฉํ•  ์ˆ˜ ์žˆ๋Š” ๋Œ€ํ‘œ์ ์ธ ๋ฐ์ดํ„ฐ์…‹์„ ์†Œ๊ฐœํ•˜๊ณ ์ž ํ•œ๋‹ค. 1. SQuAD https://rajpurkar.github.io/SQuAD-explorer/ The Stanford Question Answering DatasetWhat is SQuAD? Stanford Question Answering Dataset (SQuAD) is a reading comprehension dataset, consisting of questions posed by crowdworkers on a set of Wikipedia articles, where the answer to every qu..
list_img
CNN์„ ์ด์šฉํ•œ ์˜ค๋””์˜ค ๋ถ„๋ฅ˜ ๋ชจ๋ธ ๋งŒ๋“ค๊ธฐ
user-img iamnotwhale
2023.11.21
๋‹ค์ด๋ธŒ ๊ฐ€์„ ๊ธฐ์ˆ˜ 2์ฃผ์ฐจ ๊ณผ์ œ - Audio Classification Model (์˜ค๋””์˜ค ๋ถ„๋ฅ˜ ๋ชจ๋ธ) ๋งŒ๋“ค๊ธฐ ๊ณผ์ œ ํ•˜๋Š” ๊ณผ์ • ๊ฐ„๋žตํ•˜๊ฒŒ ์ •๋ฆฌํ•ด๋ณด๋„๋ก ํ•˜๊ฒ ๋‹ค. ์šฐ์„ , ๋‚˜๋Š” ๋”ฅ๋Ÿฌ๋‹์„ ๊ทธ๋ ‡๊ฒŒ ์ž˜ ์•„๋Š” ํŽธ์€ ์•„๋‹ˆ๋ผ์„œ ๊ฐ€์žฅ ์‰ฌ์šด ๋ฐฉ๋ฒ•์œผ๋กœ ๊ณผ์ œ๋ฅผ ํ•ด๊ฒฐํ•˜๊ธฐ๋กœ ํ•˜์˜€๊ณ  ๊ทธ ๊ณผ์ •์—์„œ ์ฑ„ํƒ๋œ ๊ฒƒ์ด ๋ฐ”๋กœ CNN ๋ชจ๋ธ์ด๋‹ค. Tensorflow๋ฅผ ์ด์šฉํ•˜์˜€๋‹ค. (ํ•™๊ต์—์„œ ์‹œํ‚ค๋Š” ๊ณผ์ œ๋Š” ํŒŒ์ดํ† ์น˜๋ฅผ ์“ฐ๊ธฐ ๋•Œ๋ฌธ์—,, ํ…์„œํ”Œ๋กœ์šฐ๋Š” ์ฒ˜์Œ์ด๋‹ค) 1) ์˜ค๋””์˜ค ๋ฐ์ดํ„ฐ ๋ถˆ๋Ÿฌ์˜ค๊ธฐ ์‚ฌ์šฉํ•œ ๋ฐ์ดํ„ฐ ์„ค๋ช…์€ ๋‹ค์Œ๊ณผ ๊ฐ™๋‹ค. 14๊ฐœ์˜ ์•…๊ธฐ๋“ค๋ณ„ ์†Œ๋ฆฌ๊ฐ€ ์ €์žฅ๋˜์–ด ์žˆ๋Š” ๋ฐ์ดํ„ฐ์…‹์ž…๋‹ˆ๋‹ค. ์˜ค๋””์˜ค๋ฅผ MFCC ๊ณ„์ˆ˜์˜ ๊ฐœ์ˆ˜๋ฅผ 13๊ฐœ๋กœ ์„ค์ •ํ•œ MFCC ํ˜•ํƒœ๋กœ ์ „์ฒ˜๋ฆฌํ–ˆ์œผ๋ฉฐ ์ „์ฒ˜๋ฆฌ ๋ฐฉ์‹์€ ์•„๋ž˜์™€ ๊ฐ™์Šต๋‹ˆ๋‹ค. ์ „์ฒด ๋ฐ์ดํ„ฐ์…‹์—์„œ ๋ฌด์ž‘์œ„๋กœ ํ•˜๋‚˜์˜ ์•…๊ธฐ๋ฅผ ๊ณ ๋ฅด๊ณ , ํ•ด๋‹น ์•…๊ธฐ ๋ ˆ์ด๋ธ”์˜ ๋ฐ..
list_img
Microaveraging vs. Macroaveraging
user-img iamnotwhale
2023.11.14
์ด์ง„ ๋ถ„๋ฅ˜๊ธฐ์˜ ์„ฑ๋Šฅ์„ ๊ณ„์‚ฐํ•  ๋•Œ ์šฐ๋ฆฌ๋Š” confusion matrix (ํ˜ผ๋™ํ–‰๋ ฌ) ์„ ๊ทธ๋ ค True positive, True negative, False positive, False negative๋ฅผ ํ™•์ธํ•˜๊ณ  ์ด๋ฅผ ํ†ตํ•ด precision, recall, accuracy๋“ฑ์„ ํ™•์ธํ•  ์ˆ˜ ์žˆ๋‹ค. ๊ทธ๋Ÿฐ๋ฐ ๋งŒ์•ฝ ๋ถ„๋ฅ˜ํ•ด์•ผ ํ•  ํด๋ž˜์Šค๊ฐ€ 3๊ฐœ ์ด์ƒ์ด๋ผ๋ฉด ์–ด๋–ป๊ฒŒ ํ•ด์•ผํ• ๊นŒ? ๋‘ ๊ฐ€์ง€ ๋ฐฉ์‹์ด ์žˆ๋Š”๋ฐ ๋ฐ”๋กœ Microaveraging ๊ณผ Macroaveraging์ด๋‹ค. ๋‘˜์˜ ์ฐจ์ด๋ฅผ ํ™•์ธํ•ด๋ณด์ž. Macroaveraging ๊ตฌํ•˜๊ณ  ์‹ถ์€ ๊ฐ๊ฐ์˜ ํด๋ž˜์Šค์— ๋Œ€ํ•ด์„œ ์„ฑ๋Šฅ์„ ๊ณ„์‚ฐํ•œ๋‹ค. ๊ทธ ์ดํ›„ ๊ฐ ํด๋ž˜์Šค์— ๋Œ€ํ•œ ํ‰๊ท ๊ฐ’์ด ์ตœ์ข… ์„ฑ๋Šฅ์ด ๋œ๋‹ค. ๋งŒ์•ฝ ํด๋ž˜์Šค๊ฐ€ 4๊ฐœ๋ผ๋ฉด, ์ž‘์€ confusion matrix 4๊ฐœ๋ฅผ ๊ทธ๋ฆฌ๊ณ , ์ด 4๊ฐœ์— ๋Œ€ํ•œ ํ‰๊ท ๊ฐ’..
list_img
Ch01. Speaking Mathematically
user-img iamnotwhale
2023.09.08
Statement = Proposition : ๋ช…์ œ - ์ •์˜: ์ฐธ์ด๋‚˜ ๊ฑฐ์ง“์œผ๋กœ ํŒ๋‹จํ•  ์ˆ˜ ์žˆ๋Š” ๋ฌธ์žฅ - ์ข…๋ฅ˜ 1) Universal Statement: ํ•œ ์ง‘ํ•ฉ์˜ ๋ชจ๋“  ์š”์†Œ์— ๋Œ€ํ•ด์„œ ์ฐธ 2) Conditional Statement: ํŠน์ • ์กฐ๊ฑด๋งŒ ํฌํ•จ 3) Existential Statement: ์กฐ๊ฑด์„ ๋งŒ์กฑํ•˜๋Š” ์š”์†Œ๊ฐ€ 1๊ฐœ ์ด์ƒ ์žˆ๋‹ค. 4) Universal Conditional Statement: universal & conditional 5) Universal Existential Statement: ์ฒซ ๋ถ€๋ถ„์€ universal, ๋‘ ๋ฒˆ์งธ ๋ถ€๋ถ„์€ existential 6) Existential Universal Statement: ์ฒซ ๋ถ€๋ถ„์€ existential, ๋‘ ๋ฒˆ์งธ ๋ถ€๋ถ„์€ universal S..

์ด๋ฒˆ ํ•™๊ธฐ์— ์„œ์šธ๋Œ€, ์นด์ด์ŠคํŠธ ๋ฐ์ดํ„ฐ์‚ฌ์ด์–ธ์Šค๋Œ€ํ•™์›์— ๋„์ „ํ•˜์˜€๋Š”๋ฐ
์„œ์šธ๋Œ€๋Š” 1์ฐจ ๋ฉด์ ‘์—์„œ ๋ถˆํ•ฉ๊ฒฉํ•˜์˜€์ง€๋งŒ ์นด์ด์ŠคํŠธ์— ์ตœ์ข… ํ•ฉ๊ฒฉํ•˜๊ฒŒ ๋˜์—ˆ์Šต๋‹ˆ๋‹ค. 
 
์นด์ด ๋ฐ์‹ธ ํ•ฉ๊ฒฉ ํ›„๊ธฐ ๋ธ”๋กœ๊ทธ ์˜ฌ๋ ค ์ฃผ์‹  ๋ถ„ ๋„์›€์„ ๋งŽ์ด ๋ฐ›์•„์„œ
์ €๋„ ์ด ๋Œ€ํ•™์›์„ ์ค€๋น„ํ•˜๋Š” ๋ถ„๋“ค์—๊ฒŒ ๋„์›€์ด ๋ ๊นŒ ์‹ถ์–ด์„œ ๊ธ€์„ ์ž‘์„ฑํ•˜๊ฒŒ ๋์Šต๋‹ˆ๋‹ค.
 

 
๋ณธ๊ฒฉ์ ์ธ ์ž…์‹œ ์ง„ํ–‰ ์ „ ์ž…์‹œ์„ค๋ช…ํšŒ๋ฅผ ์ง„ํ–‰ํ•˜๋Š” ๊ฒƒ์œผ๋กœ ์•Œ๊ณ  ์žˆ์Šต๋‹ˆ๋‹ค.
์ €์˜ ๊ฒฝ์šฐ๋Š” ์ž…์‹œ ๊ธฐ๊ฐ„์— ๊ฐ‘์ž๊ธฐ ์›์„œ๋ฅผ ์“ฐ๊ฒŒ ๋˜์–ด์„œ ์ž…์‹œ์„ค๋ช…ํšŒ๋Š” ์ฐธ์—ฌํ•˜์ง€ ๋ชปํ•˜์˜€์œผ๋‚˜,
๊ธฐํšŒ๊ฐ€ ๋œ๋‹ค๋ฉด ์ž…์‹œ์„ค๋ช…ํšŒ๋Š” ๊ผญ ์ฐธ์„ํ•˜์‹œ๊ธธ ๋ฐ”๋ž๋‹ˆ๋‹ค.
 
1) ์ŠคํŽ™

  • ํ•™๊ต: ๊ณ ๋ ค๋Œ€
  • ์ „๊ณต: ์ƒ๋ช…๊ณ„์—ด (์ปดํ“จํ„ฐํ•™๊ณผ ์ด์ค‘์ „๊ณต)
  • ํ•™์ : ์ „์ฒด 3.81/4.5, ์ „๊ณต 3.56/4.5
  • ์ „๊ณต ๊ด€๋ จ ํ™œ๋™: ๊ต๋‚ด ๋”ฅ๋Ÿฌ๋‹ ํ•™ํšŒ 1๋…„, ์—ฐํ•ฉ ์ธ๊ณต์ง€๋Šฅ/๋ฐ์ดํ„ฐ๋ถ„์„ ๋™์•„๋ฆฌ 2๋…„, ๋ฐ์ดํ„ฐ๋ถ„์„ ๊ณต๋ชจ์ „ ์ž…์ƒ 1ํšŒ
  • ์—ฐ๊ตฌ ๊ด€๋ จ ํ™œ๋™: ํ•™๋ถ€์—ฐ๊ตฌ์ƒ ํ”„๋กœ๊ทธ๋žจ 2ํšŒ (์ž๋Œ€ ์ƒ๊ณผ๋Œ€, ์„œ์šธ๋Œ€ ์˜๋Œ€ ๊ฐ 2๊ฐœ์›”์”ฉ), ๊ตญ๋‚ด ํ•™์ˆ ๋Œ€ํšŒ ๋…ผ๋ฌธ ์ฐธ์—ฌ 1ํšŒ 
  • ๊ธฐํƒ€: ํ•™๊ณผ ํ•™์ƒํšŒ์žฅ
  • ์–ดํ•™ ๋ฐ ์ž๊ฒฉ์ฆ: ํ† ์ต 985, SQLD 

์ €๋Š” ์„œ์šธ๋Œ€ ์ž…์‹œ ๋•Œ๋ฌธ์— ํ…์Šค 449์ ์„ ๋ณด์œ  ์ค‘์ธ ์ƒํƒœ์˜€์Šต๋‹ˆ๋‹ค.
์ด ์ ์ˆ˜๋„ ์ œ์ถœ ๊ฐ€๋Šฅํ•˜์ง€๋งŒ, ํ…์Šค 449๋ณด๋‹ค ํ† ์ต 985๊ฐ€ ๋” ๋†’์•„๋ณด์ผ ๊ฒƒ ๊ฐ™์•„์„œ ํ† ์ต ์ ์ˆ˜๋งŒ ์ž‘์„ฑํ•˜์—ฌ ์ œ์ถœํ•˜์˜€์Šต๋‹ˆ๋‹ค.
ํ•™๋ถ€๋ฅผ ๊ฐ์•ˆํ•˜๋”๋ผ๋„ ํ•™์ , ํŠนํžˆ ์ „๊ณตํ•™์ ์ด ์ƒ๋‹นํžˆ ๋‚ฎ์€ ํŽธ์ด๋ผ๊ณ  ์ƒ๊ฐํ•˜๋Š”๋ฐ(ใ… ใ… ..)
'๋ฐ์ดํ„ฐ์‚ฌ์ด์–ธ์Šค'๋ผ๋Š” ๋ถ„์•ผ์— ์ ํ•ฉํ•œ ์ˆ˜์—…์„ ๋งŽ์ด ์ˆ˜๊ฐ•ํ•˜์˜€๊ณ , ํ™œ๋™ ์ŠคํŽ™์œผ๋กœ ์ปค๋ฒ„๊ฐ€ ๋œ ๊ฒŒ ์•„๋‹๊นŒ ์ƒ๊ฐํ•ฉ๋‹ˆ๋‹ค.
 
2) ์„œ๋ฅ˜ ์ค€๋น„
1์ง€๋ง์ด ์„œ์šธ๋Œ€์˜€๊ธฐ ๋•Œ๋ฌธ์— ์ƒ๋Œ€์ ์œผ๋กœ ์นด์ด์ŠคํŠธ๋Š” ์„œ๋ฅ˜๋ฅผ ์ƒ๋Œ€์ ์œผ๋กœ ๋œ ์—ด์‹ฌํžˆ ์“ฐ๊ธด ํ–ˆ์Šต๋‹ˆ๋‹ค. 
ํฌ๊ฒŒ ์ค€๋น„ํ•  ๊ฒƒ์€ ์ž์†Œ์„œ์™€ ์šฐ์ˆ˜์„ฑ ์ž…์ฆ ์ž๋ฃŒ์ž…๋‹ˆ๋‹ค.
 
์ž์†Œ์„œ์—๋Š” ํ‚ค์›Œ๋“œ ๊ธฐ๋ฐ˜ ๋ฌธํ•ญ๊ณผ ์ž๊ธฐ์†Œ๊ฐœ/๋ฉดํ•™๊ณ„ํš ์ž‘์„ฑ ๋ฌธํ•ญ์ด ์žˆ๋Š”๋ฐ,
์ž๊ธฐ์†Œ๊ฐœ/๋ฉดํ•™๊ณ„ํš ์ž‘์„ฑํ•  ๋•Œ ๋‚ด๊ฐ€ ๋ฐ์ดํ„ฐ์‚ฌ์ด์–ธ์Šค ์ „๊ณต์„ ์™œ ํ•ด์•ผํ•˜๋Š”์ง€ ๊ทธ ์Šคํ† ๋ฆฌ๊ฐ€ ์ž˜ ๋“œ๋Ÿฌ๋‚˜๊ฒŒ ์ž‘์„ฑํ•˜๋Š” ๊ฒƒ์ด ์ข‹์„ ๊ฒƒ ๊ฐ™์Šต๋‹ˆ๋‹ค. 
ํ‚ค์›Œ๋“œ ๊ธฐ๋ฐ˜์€ ๊ธ€์ž์ˆ˜๊ฐ€ ๋งŽ์ง€ ์•Š์œผ๋‹ˆ ์ ๋‹นํžˆ๋งŒ ์ž‘์„ฑํ•˜๋ฉด ๋  ๊ฒƒ ๊ฐ™์•„์š”.
 
์šฐ์ˆ˜์„ฑ ์ž…์ฆ ์ž๋ฃŒ์˜ ๊ฒฝ์šฐ์—๋Š” ๊ฐœ์ˆ˜ ์ œํ•œ์ด ์—†๋‹ค ๋ณด๋‹ˆ ๋„์›€๋  ๋งŒํ•œ ๊ฒƒ์€ ์ „๋ถ€ ์ œ์ถœํ–ˆ์Šต๋‹ˆ๋‹ค.
(ํ•™์ˆ ๋Œ€ํšŒ ๋…ผ๋ฌธ ์‚ฌ๋ณธ, ๊ณต๋ชจ์ „ ์ƒ์žฅ, ๋™์•„๋ฆฌ ์ˆ˜๋ฃŒ์ฆ, ํ•™ํšŒ ์ˆ˜๋ฃŒ์ฆ, ํ•™๋ถ€์—ฐ๊ตฌ์ƒ ํ”„๋กœ๊ทธ๋žจ ์ˆ˜๋ฃŒ์ฆ, SQLD ์ฆ๋ช…์„œ, ํ•™์ƒํšŒ ํ™œ๋™์ฆ๋ช…์„œ)
์šฐ์ˆ˜์„ฑ ์ž…์ฆ ์ž๋ฃŒ ์„ค๋ช…๋ž€์— ๋…ผ๋ฌธ ๋‚ด์šฉ, ๋™์•„๋ฆฌ/ํ•™ํšŒ/ํ•™๋ถ€์—ฐ๊ตฌ์ƒ ํ”„๋กœ์ ํŠธ ๋‚ด์šฉ์„ ๊ฐ„๋‹จํ•˜๊ฒŒ ์ž‘์„ฑํ•˜์—ฌ ์ œ์ถœํ•˜์˜€์Šต๋‹ˆ๋‹ค.
 
์ง€์›ํ•  ๋•Œ ์‚ฐ์—…๋ฐ์‹œ์Šคํ…œ๊ณตํ•™๊ณผ๋ฅผ 2์ง€๋ง์œผ๋กœ ์„ ํƒํ•˜์—ฌ ์ง€์›ํ•  ์ˆ˜ ์žˆ๋Š”๋ฐ ์ €๋Š” ์ž์†Œ์„œ 2์ง€๋ง ๋ฌธํ•ญ ์“ฐ๊ธฐ ๊ท€์ฐฎ์•„์„œ ์•ˆ ํ–ˆ์Šต๋‹ˆ๋‹ค.
 
3) ๋ฉด์ ‘
ํฌ๊ฒŒ ๋ฌธ์ œํ’€์ด ๋ฉด์ ‘, ์—ฐ๊ตฌ์ฃผ์ œ ๋ฐœํ‘œ ๋ฉด์ ‘์œผ๋กœ ์ง„ํ–‰๋ฉ๋‹ˆ๋‹ค.
๋ฌธ์ œํ’€์ด 1์‹œ๊ฐ„ > ํ’€์ด ๋ฉด์ ‘ 15๋ถ„ > 15๋ถ„ ํœด์‹ > ์—ฐ๊ตฌ์ฃผ์ œ๋ฐœํ‘œ 5๋ถ„ > ์งˆ์˜์‘๋‹ต 10๋ถ„
 
๋ฌธ์ œํ’€์ด ๋ฉด์ ‘๊ณผ ์—ฐ๊ตฌ์ฃผ์ œ๋ฐœํ‘œ ๋ฉด์ ‘ ์ค‘ ๋” ๋†’์€ ์ ์ˆ˜๋ฅผ ๋ฐ›์€ ๋ฉด์ ‘๋งŒ ์ตœ์ข… ์ ์ˆ˜์— ๋ฐ˜์˜๋ฉ๋‹ˆ๋‹ค.
์ €๋Š” ๋ฌธ์ œํ’€์ด ๋ฉด์ ‘์— ์ž์‹ ์ด ์—†๋‹ค๋ณด๋‹ˆ ์—ฐ๊ตฌ์ฃผ์ œ ๋ฐœํ‘œ์— ํž˜์„ ์ผ์Šต๋‹ˆ๋‹ค. 
 
๋ฌธ์ œ๋Š” ํ†ต๊ณ„ํ•™, ํ”„๋กœ๊ทธ๋ž˜๋ฐ ๋ฌธ์ œ๊ฐ€ ์ถœ์ œ๋˜๋ฉฐ, ๋ฐ์ดํ„ฐ์‚ฌ์ด์–ธ์Šค๋Œ€ํ•™์› ํ™ˆํŽ˜์ด์ง€์— ์ƒ˜ํ”Œ ๋ฌธ์ œ๊ฐ€ ์˜ฌ๋ผ์™€์žˆ์œผ๋‹ˆ ์ฐธ๊ณ ํ•˜๋ฉด ์ข‹์„ ๊ฒƒ ๊ฐ™์Šต๋‹ˆ๋‹ค.
ํ†ต๊ณ„๋Š” ์ˆ˜๋ฆฌํ†ต๊ณ„ํ•™์„ ๊ณต๋ถ€ํ•˜์…”์•ผ ํ•˜๊ณ  ํ”„๋กœ๊ทธ๋ž˜๋ฐ์€ ์•Œ๊ณ ๋ฆฌ์ฆ˜ ์œ„์ฃผ๋กœ ๊ณต๋ถ€ํ•˜์‹œ๋ฉด ๋ฉ๋‹ˆ๋‹ค.
ํ”„๋กœ๊ทธ๋ž˜๋ฐ ๋ฉด์ ‘์€ ์–ด๋–ค ๋ฌธ์ œ ์ƒํ™ฉ์ด ์ฃผ์–ด์ ธ์žˆ์„ ๋•Œ ์–ด๋–ค ์•Œ๊ณ ๋ฆฌ์ฆ˜์„ ์‚ฌ์šฉํ•  ๊ฒƒ์ธ์ง€, ์–ด๋–ค ๋ฐฉ์‹์œผ๋กœ ์ˆ˜๋„์ฝ”๋“œ๋ฅผ ์งค์ง€, ์ง  ์ฝ”๋“œ๋ฅผ ์–ด๋–ป๊ฒŒ ์„ค๋ช…ํ•  ๊ฒƒ์ธ์ง€๋ฅผ ์—ฐ์Šตํ•˜๋ฉด ์ข‹์„ ๊ฒƒ ๊ฐ™์•„์š”.
์ €์ฒ˜๋Ÿผ ๋ฒผ๋ฝ์น˜๊ธฐ ํ•˜์‹œ๋ฉด ๋ฉด์ ‘์žฅ ๊ฐ€์„œ ์ฉ”์ฉ”๋งต๋‹ˆ๋‹ค(ใ… ใ… )
๋ฌธ์ œ ํ’€์ด ๋ฉด์ ‘์žฅ์— ๋“ค์–ด๊ฐ€๊ฒŒ ๋˜๋ฉด ๋ฉด์ ‘๊ด€๋“ค์—๊ฒŒ ๋ฌธ์ œ ํ’€์ด๋ฅผ ์ œ์ถœํ•ด์•ผ ํ•˜๋‹ˆ ๊ธ€์”จ๋Š” ์ตœ๋Œ€ํ•œ ์ •๊ฐˆํ•˜๊ฒŒ ์“ฐ์‹œ๊ธธ ๋ฐ”๋ž๋‹ˆ๋‹ค!
์ œ๊ฐ€ ๋„ˆ๋ฌด ๋ฌธ์ œ๋ฅผ ๋ชป ํ’€์–ด์„œ ๊ทธ๋Ÿฐ์ง€ ๋ชจ๋ฅด๊ฒ ์œผ๋‚˜... ์‚ด์ง ์••๋ฐ•๋ฉด์ ‘์ด๋ผ๊ณ  ๋А๊ปด์กŒ์Šต๋‹ˆ๋‹ค.
๋ฌธ์ œํ’€์ด ๋ฉด์ ‘์„ ์ž˜ ๋ณด๊ณ  ์‹ถ๋‹ค๋ฉด ์›์„œ ์ ‘์ˆ˜ ์ดํ›„ ๋ฐ”๋กœ ๊ณต๋ถ€ ์‹œ์ž‘ํ•˜์‹œ๋Š” ๊ฒŒ ์ข‹์„ ๊ฒƒ ๊ฐ™์Šต๋‹ˆ๋‹ค.
 
์—ฐ๊ตฌ์ฃผ์ œ๋ฐœํ‘œ ๋ฉด์ ‘์€ ๊ธธ์ด๊ฐ€ 5๋ถ„์ด๊ธฐ ๋•Œ๋ฌธ์— ๋ชจ๋“  ๊ฒƒ์„ ๋‹ด์„ ํ•„์š”๊ฐ€ ์—†๋‹ค๊ณ  ํŒ๋‹จํ–ˆ๊ณ ,
์—ฐ๊ตฌ ํ•„์š”์„ฑ > ๋‚ด๊ฐ€ ์ƒ๊ฐํ•œ ์—ฐ๊ตฌ ๋ฐฉ๋ฒ•๋ก  > ์ง€๊ธˆ๊นŒ์ง€์˜ ๋‚˜์˜ ๋…ธ๋ ฅ
์ด ์ •๋„๋งŒ ์ •๋ฆฌํ•ด์„œ ๋ฐœํ‘œํ•˜์˜€์Šต๋‹ˆ๋‹ค. (์ƒ˜ํ”Œ์ด ๋ฐ์ดํ„ฐ์‚ฌ์ด์–ธ์Šค๋Œ€ํ•™์› ํ™ˆํŽ˜์ด์ง€์— ์˜ฌ๋ผ๊ฐ€์žˆ์Šต๋‹ˆ๋‹ค.)
๋ฉด์ ‘๊ด€๋ถ„๋“ค์ด ์ž˜ ์•„๋Š” ๋ถ„์•ผ๊ฐ€ ์•„๋‹ˆ๋ผ๋ฉด ์งˆ๋ฌธ์˜ ๊นŠ์ด๋„ ๋งŽ์ด ๊นŠ์ง€๋Š” ์•Š์Šต๋‹ˆ๋‹ค.
๋Œ€์‹  ์ด ์งˆ์˜์‘๋‹ต ์‹œ๊ฐ„์—๋Š” ์—ฐ๊ตฌ์ฃผ์ œ ๋ฐœํ‘œ๋ฟ๋งŒ ์•„๋‹ˆ๋ผ ์ œ์ถœํ•œ ์„œ๋ฅ˜์— ๋Œ€ํ•œ ์งˆ๋ฌธ๋„ ํ•˜๋‹ˆ ์˜ˆ์ƒ ์งˆ๋ฌธ๊ณผ ๋‹ต๋ณ€์„ ์—ผ๋‘์— ๋‘๊ณ  ๋ฉด์ ‘์žฅ ๋“ค์–ด๊ฐ€์‹œ๋ฉด ์ข‹์„ ๊ฒƒ ๊ฐ™์Šต๋‹ˆ๋‹ค.
 
๋ฐœํ‘œ์ž๋ฃŒ๋Š” USB๋ž‘ ์ด๋ฉ”์ผ ๋‘˜ ๋‹ค ์ €์žฅํ•ด๋‘์‹œ๋ฉด ์ข‹์Šต๋‹ˆ๋‹ค. USB ์ธ์‹์ด ์•ˆ๋˜์–ด์„œ ๋‹นํ™ฉํ–ˆ๋˜ ๊ธฐ์–ต์ด ์žˆ๋„ค์š”...
 
4) ์ปจํƒ
๋‹ค๋“ค ์•„์‹œ๋‹ค์‹œํ”ผ ์นด์ด์ŠคํŠธ๋Š” ์ปจํƒ์ด ์ž…์‹œ์— ์œ ์˜๋ฏธํ•œ ์˜ํ–ฅ์„ ๋ฏธ์น˜์ง€๋Š” ์•Š์Šต๋‹ˆ๋‹ค.
์ € ์—ญ์‹œ๋„ ์ž…์‹œ ์ „์—” ๋”ฐ๋กœ ์ปจํƒํ•˜์ง€ ์•Š๊ณ  ์ž…์‹œ๋ถ€ํ„ฐ ์น˜๋ฅธ ๋‹ค์Œ ํ•ฉ๊ฒฉ์ž ๋ฐœํ‘œ ๋ณด๊ณ  ๋‚˜์„œ ์ปจํƒํ–ˆ์Šต๋‹ˆ๋‹ค.
ํ•˜์ง€๋งŒ ์›ํ•˜๋Š” ์—ฐ๊ตฌ์‹ค์ด ์žˆ๋‹ค๋ฉด ์ž…์‹œ ๊ธฐ๊ฐ„ ์ „์— ์ปจํƒ์„ ํ•ด๋ณด์‹œ๋Š” ๊ฑธ ์ถ”์ฒœ๋“œ๋ฆฝ๋‹ˆ๋‹ค.
 
ํ•ฉ๊ฒฉ์ž ๋ฐœํ‘œ ํ›„ ํ–‰์ •์‹ค์—์„œ 1์ฐจ ์ง€๋„๊ต์ˆ˜ ์‹ ์ฒญ ๊ธฐ๊ฐ„์„ ์•Œ๋ ค์ค๋‹ˆ๋‹ค.
๋งŒ์•ฝ ์ปจํƒ์„ ๋ชปํ•œ ์ƒํƒœ์—์„œ ํ•ฉ๊ฒฉํ•˜์…จ๋‹ค๋ฉด ๋ฐ”๋กœ ์ปจํƒํ•˜์‹œ๊ธธ ๋ฐ”๋ž๋‹ˆ๋‹ค.
๋ฐ์‚ฌ ๊ต์ˆ˜๋‹˜ ๋‹ค์ˆ˜๊ฐ€ ๊ฒธ์ž„๊ต์ˆ˜๋กœ ๊ณ„์‹œ๊ธฐ ๋•Œ๋ฌธ์— ์—ฐ๊ตฌ์‹ค ๋‚ด ๋ฐ์‚ฌ TO๊ฐ€ ๋งค์šฐ ์ ์„ ๊ฐ€๋Šฅ์„ฑ์ด ํฌ๊ธฐ ๋•Œ๋ฌธ์ž…๋‹ˆ๋‹ค.
์ด 1์ฐจ ์ง€๋„๊ต์ˆ˜ ์‹ ์ฒญ ๊ธฐ๊ฐ„ ๋‚ด์— ์ง€๋„๊ต์ˆ˜๋ฅผ ์ •ํ•˜์ง€ ๋ชปํ•˜์—ฌ๋„ 2์ฐจ ๋ฐฐ์ •์ด ์žˆ๊ธด ํ•ฉ๋‹ˆ๋‹ค.
 
๊ถ๊ธˆํ•œ ์  ์žˆ์œผ์‹œ๋ฉด ๊ณต๊ฐœ๋Œ“๊ธ€ (๋น„๊ณต๊ฐœ ๋Œ“๊ธ€์€ ๋‹ต๋ณ€๋“œ๋ฆฌ์ง€ ์•Š์Šต๋‹ˆ๋‹ค!) ๋˜๋Š” ์ด๋ฉ”์ผ๋กœ ์—ฐ๋ฝ์ฃผ์‹œ๋ฉด ๋‹ต์žฅ๋“œ๋ฆฌ๊ฒ ์Šต๋‹ˆ๋‹ค!
> kby150103@gmail.com 
 
๋ถ€์กฑํ•œ ๊ธ€ ์ฝ์–ด์ฃผ์…”์„œ ๊ฐ์‚ฌ๋“œ๋ฆฌ๊ณ 
๋ชจ๋‘ ์›ํ•˜์‹œ๋Š” ๋Œ€ํ•™์› ํ•ฉ๊ฒฉํ•˜์‹œ๊ธฐ๋ฅผ ๊ธฐ์›ํ•ฉ๋‹ˆ๋‹ค!

vscode๋ฅผ ์ด์šฉํ•ด์„œ git ๊ด€๋ฆฌ๋ฅผ ํ•˜๊ณ  ์žˆ๋Š”๋ฐ (์ฝ”๋“œ๋ฅผ ๋”ฐ๋กœ ์ž‘์„ฑํ•˜์ง€๋Š” ์•Š๊ณ  ํ™•์žฅ ํ”„๋กœ๊ทธ๋žจ์„ ์ด์šฉํ•œ๋‹ค) ๋‚œ์ƒ ์ฒ˜์Œ ๋ณด๋Š” ์˜ค๋ฅ˜๋ฅผ ๋งž๋‹ฅ๋œจ๋ ธ๋‹ค.

"unexpected disconnect while reading sideband packet fatal: the remote end hung up unexpectedly everything up-to-date"

์ด๋ผ๋Š” ์ฐฝ์ด ๋œจ๋ฉด์„œ ํ‘ธ์‹œ๊ฐ€ ๋˜์ง€ ์•Š๋Š” ํ˜„์ƒ์ด ๋ฐœ์ƒํ–ˆ๋‹ค.

์ธํ„ฐ๋„ท ์˜ค๋ฅ˜์ธ๊ฐ€ ์‹ถ์–ด์„œ ๋‹ค๋ฅธ ์™€์ดํŒŒ์ด๋ฅผ ์ด์šฉํ•˜์˜€์ง€๋งŒ ์ด ๋ฌธ์ œ๋Š” ์•„๋‹ˆ์—ˆ๋‹ค.

 

๊ตฌ๊ธ€๋ง์„ ํ†ตํ•ด ์˜ค๋ฅ˜์˜ ์›์ธ์„ ํŒŒ์•…ํ–ˆ๋‹ค. 

๊ธฐ๋ณธ์ ์œผ๋กœ ํ‘ธ์‹œํ•  ์ˆ˜ ์žˆ๋Š” ํ•œ ๊ฐœ ํŒŒ์ผ์˜ ์ตœ๋Œ€ ์šฉ๋Ÿ‰์ด 1MB์—ฌ์„œ, ์šฉ๋Ÿ‰ ์ดˆ๊ณผํ•œ ํŒŒ์ผ์„ pushํ•  ๋•Œ ์˜ค๋ฅ˜๊ฐ€ ๋ฐœ์ƒํ•œ๋‹ค๊ณ  ํ•œ๋‹ค. ์ด๋ฒˆ์— ์ฒ˜์Œ์œผ๋กœ 1MB๊ฐ€ ๋„˜๋Š” ํŒŒ์ผ์„ ์—…๋กœ๋“œํ•ด์„œ ๊ทธ๋Ÿฐ ๊ฒƒ์ด์—ˆ๋‹ค.

์ด๋ฅผ ํ•ด๊ฒฐํ•˜๊ธฐ ์œ„ํ•ด์„œ ์ตœ๋Œ€ ์šฉ๋Ÿ‰์„ ๋Š˜๋ ค์ฃผ๋ฉด ๋œ๋‹ค.

ํ„ฐ๋ฏธ๋„์„ ์—ด๊ณ  

git config --local http.postBuffer 2048M

 

ํ•ด๋‹น ๋ช…๋ น์–ด๋ฅผ ์ž…๋ ฅํ•ด์ฃผ๋‹ˆ ํ•ด๊ฒฐ๋˜์—ˆ๋‹ค.

์ด๊ฒŒ ๋จนํžˆ์ง€ ์•Š์œผ๋ฉด ssh์—์„œ๋„ ๋ณ€๊ฒฝํ•ด์ฃผ๋ฉด ๋œ๋‹ค๊ณ  ํ•œ๋‹ค. 

git config --local ssh.postBuffer 2048M

 

์ถœ์ฒ˜: https://happy-jjang-a.tistory.com/222

'CS study/๊ธฐํƒ€' Related Articles +

Ensemble Learning์ด๋ž€?

์—ฌ๋Ÿฌ ๊ฐœ์˜ base-learner(base-model)๋ฅผ ์กฐํ•ฉํ•˜๋Š” ๋ชจ๋ธ

 

Bagging

- ๋‹ค๋ฅธ ์ด๋ฆ„: Bootstrap Aggregating

- Bootstrap: Random Sampling ๋ฐฉ๋ฒ•๋ก  ์ค‘ ํ•˜๋‚˜. ๋ณต์› ์ถ”์ถœ์„ ์‹œํ–‰ํ•œ๋‹ค.

- ๋ณต์› ์ถ”์ถœ์„ ํ†ตํ•ด ๋™์ผํ•œ ํฌ๊ธฐ์˜ ๋ฐ์ดํ„ฐ์…‹์„ ์—ฌ๋Ÿฌ ๊ฐœ ์ƒ์„ฑํ•œ ํ›„, ์•™์ƒ๋ธ”์„ ๊ตฌ์„ฑํ•˜๋Š” ํ•™์Šต ๋ฐฉ์‹

- ๋‹จ์ : ๋žœ๋ค ์ƒ˜ํ”Œ๋ง์€ ์šด์— ์˜์กดํ•œ๋‹ค.

๋งŒ์•ฝ, decision tree๋ฅผ ํ•™์Šต์‹œํ‚จ๋‹ค๊ณ  ๊ฐ€์ •ํ•ด๋ณด์ž.

boostrap์œผ๋กœ ๋ฐ์ดํ„ฐ๋ฅผ ์ถ”์ถœํ•  ๊ฒฝ์šฐ, ๋ณต์› ์ถ”์ถœ์ด๊ธฐ ๋•Œ๋ฌธ์— ๊ฐ™์€ ๋ฐ์ดํ„ฐ๊ฐ€ ์—ฌ๋Ÿฌ ๋ฒˆ ๋ฝ‘ํž ์ˆ˜ ์žˆ๊ณ , ๊ทธ๋ ‡๊ธฐ ๋•Œ๋ฌธ์— ๋ฐ์ดํ„ฐ์…‹๋ผ๋ฆฌ ์œ ์‚ฌํ•˜๋‹ค. ๊ทธ๋Ÿฌ๋ฏ€๋กœ ์ด๋Ÿฐ ๊ฒฝ์šฐ decision tree์˜ root node๋Š” ๋ชจ๋ธ ๊ฐ„์— ํ•ญ์ƒ ๋น„์Šทํ•ด์งˆ ์ˆ˜๋ฐ–์— ์—†๋‹ค. 

 

Boosting

- Bagging๊ณผ ๊ฐ™์€ ๋ฐฉ๋ฒ•์ด randomness์— ์˜์กดํ•œ๋‹ค๋Š” ๋‹จ์ ์„ ๋ณด์™„ํ•˜๊ธฐ ์œ„ํ•ด ๊ณ ์•ˆ๋œ ๋ฐฉ์‹

- ์ „์ฒด ๋ฐ์ดํ„ฐ์…‹์„ 3๊ฐœ๋กœ ๋ถ„ํ• ํ•œ๋‹ค. (D1, D2, D3)

- ํ•™์Šต ๋ฐฉ์‹

base-learner๋ฅผ 3๊ฐœ ํ•™์Šต์‹œํ‚จ๋‹ค.

1. h1์„ D1์œผ๋กœ ํ•™์Šต์‹œํ‚จ๋‹ค.

2. h2๋ฅผ D2 ์ค‘ h1์ด ํ‹€๋ ธ๋˜ ๋ฌธ์ œ + ๋งž์•˜๋˜ ๋ฌธ์ œ ๊ฐ™์€ ๋น„์œจ๋กœ ๊ตฌ์„ฑ๋œ ๋ฐ์ดํ„ฐ์…‹์œผ๋กœ ํ•™์Šต์‹œํ‚จ๋‹ค.

3. h3์„ h2๊ฐ€ ํ‹€๋ ธ๋˜ ๋ฌธ์ œ ๋ฐ์ดํ„ฐ์…‹์œผ๋กœ ํ•™์Šต์‹œํ‚จ๋‹ค.

- ์˜ˆ์ธก ๋ฐฉ์‹

h1(x)=h2(x)๋ผ๋ฉด, h1(x)๋ฅผ ๋ฐ˜ํ™˜.

์•„๋‹ˆ๋ผ๋ฉด h3(x)์„ ๋ฐ˜ํ™˜. => ํ‹€๋ ธ๋˜ ๋ฌธ์ œ๋งŒ์œผ๋กœ ํ•™์Šต๋œ ๋ชจ๋ธ์ด๋ฏ€๋กœ ๊ฐ€์žฅ ๋งž์„ ํ™•๋ฅ ์ด ๋†’๋‹ค.

๋ฌดํ•œ์Šคํฌ๋กค ํŽ˜์ด์ง€์—์„œ ํฌ๋กค๋ง์„ ํ•  ์ผ์ด ์ƒ๊ฒผ๋‹ค.

๋ฌดํ•œ์Šคํฌ๋กค ํŽ˜์ด์ง€์—์„œ ํ•ญ๋ชฉ์˜ ๋ชฉ๋ก์„ ๋ชจ๋‘ ์ˆ˜์ง‘ํ•˜๊ธฐ ์œ„ํ•ด์„œ๋Š” ์Šคํฌ๋กค ๋ฐ”๋ฅผ ๋งจ ๋๊นŒ์ง€ ๋‚ด๋ ค์•ผํ•œ๋‹ค.

๋”ฐ๋ผ์„œ ํŽ˜์ด์ง€๋ฅผ ๋‚ด๋ ค๋„ ๊ณ„์†ํ•ด์„œ ์ƒˆ๋กœ์šด ๋‚ด์šฉ์ด ๋กœ๋”ฉ๋˜๋Š” ๋ฌดํ•œ์Šคํฌ๋กค ์›นํŽ˜์ด์ง€์—์„œ ์Šคํฌ๋กค ๋ฐ”๋ฅผ ๊ณ„์†ํ•ด์„œ ๋‚ด๋ฆฌ๋Š” ๋ฐฉ๋ฒ•์„ ์•Œ์•„๋ณด์ž.

 

์—ฌ๋Ÿฌ ๊ฐ€์ง€ ๋ฐฉ๋ฒ•์ด ์žˆ๋Š”๋ฐ, Keys.PAGE_DOWN๋ฅผ ์‚ฌ์šฉํ•  ์ˆ˜ ์žˆ๋‹ค.

 

1. ํ•„์š” ๋ผ์ด๋ธŒ๋Ÿฌ๋ฆฌ๋ฅผ ๋ถˆ๋Ÿฌ์˜จ๋‹ค.

from selenium import webdriver
from selenium.webdriver.common.keys import Keys
from selenium.webdriver.chrome.options import Options
from selenium.webdriver.common.by import By

 

2. Keys.PAGE_DOWN์„ ์‚ฌ์šฉํ•˜์—ฌ ํŽ˜์ด์ง€ ๋งจ ๋์— ๋„๋‹ฌํ•  ๋•Œ๊นŒ์ง€ ์Šคํฌ๋กค ๋ฐ”๋ฅผ ๋‚ด๋ฆฐ๋‹ค.

last_count = len(driver.find_elements(By.CSS_SELECTOR, 'a.contents__title'))  # ํ˜„์žฌ ํŽ˜์ด์ง€์— ๋กœ๋“œ๋œ ๋ฆฌ๋ทฐ ๋งํฌ ์ˆ˜

while True:
    body = driver.find_element(By.TAG_NAME, 'body')
    body.send_keys(Keys.PAGE_DOWN)
    time.sleep(1)

    new_count = len(driver.find_elements(By.CSS_SELECTOR, 'a.contents__title'))
        
    # ๋งŒ์•ฝ ์ƒˆ๋กœ์šด ๋งํฌ๊ฐ€ ๋” ์ด์ƒ ๋กœ๋“œ๋˜์ง€ ์•Š๋Š”๋‹ค๋ฉด ์ข…๋ฃŒ
    if new_count == last_count:
        print("๋” ์ด์ƒ ์Šคํฌ๋กคํ•  ์ˆ˜ ์—†์Šต๋‹ˆ๋‹ค.")
        break
    
    last_count = new_count  # ๊ฐœ์ˆ˜ ์—…๋ฐ์ดํŠธ

 

body = driver.find_element(By.TAG_NAME, 'body')๋ฅผ ์‚ฌ์šฉํ•˜์—ฌ body๋ฅผ ์„ ํƒํ•œ ์ดํ›„, send_keys ํ•จ์ˆ˜๋ฅผ ํ†ตํ•ด์„œ page down ํ‚ค๋ฅผ ๋ˆ„๋ฅด๋Š” ๊ฒƒ๊ณผ ๋™์ผํ•œ ํšจ๊ณผ๋ฅผ ์ค€๋‹ค.

์ด๋•Œ, ๋ฌดํ•œ๋ฃจํ”„๋ฅผ ์‚ฌ์šฉํ•ด์„œ ๊ณ„์†ํ•ด์„œ ์Šคํฌ๋กค์„ ๋‚ด๋ฆฌ๊ธฐ ๋•Œ๋ฌธ์— ๋ฌดํ•œ๋ฃจํ”„ ํƒˆ์ถœ ์กฐ๊ฑด์„ ์„ค์ •ํ•ด์•ผ ํ•œ๋‹ค.

๋‚˜๋Š” ์Šคํฌ๋กค์„ ๋‚ด๋ ค๋„ content์˜ ๊ฐœ์ˆ˜๊ฐ€ ๋ฐ”๋€Œ์ง€ ์•Š์„ ๋•Œ ๋ฌดํ•œ๋ฃจํ”„๋ฅผ ํƒˆ์ถœํ•  ์ˆ˜ ์žˆ๋„๋ก ์กฐ๊ฑด์„ ์„ค์ •ํ•˜์˜€๋‹ค.

time.sleep(1)์€ ํŽ˜์ด์ง€ ๋กœ๋”ฉ์— ๋”œ๋ ˆ์ด๊ฐ€ ๊ฑธ๋ฆด ์ˆ˜ ์žˆ๊ธฐ ๋•Œ๋ฌธ์— ์„ค์ •ํ•œ ๊ฐ’์ด๋‹ค.

 

'CS study/ํŒŒ์ด์ฌ ๊ธฐ์ดˆ' Related Articles +

ํ•™ํšŒ์—์„œ ์ฃผ์–ด์ง„ ์ง€๋ฌธ์— ๋Œ€ํ•œ ๊ฐ๊ด€์‹ ์งˆ๋ฌธ์„ ์ƒ์„ฑํ•˜๋Š” Question Generation NLP ํ”„๋กœ์ ํŠธ๋ฅผ ์ง„ํ–‰ ์ค‘์ด๋‹ค.

QG ํ”„๋กœ์ ํŠธ์— ์‚ฌ์šฉํ•  ์ˆ˜ ์žˆ๋Š” ๋Œ€ํ‘œ์ ์ธ ๋ฐ์ดํ„ฐ์…‹์„ ์†Œ๊ฐœํ•˜๊ณ ์ž ํ•œ๋‹ค.

 

1. SQuAD 

https://rajpurkar.github.io/SQuAD-explorer/

 

The Stanford Question Answering Dataset

What is SQuAD? Stanford Question Answering Dataset (SQuAD) is a reading comprehension dataset, consisting of questions posed by crowdworkers on a set of Wikipedia articles, where the answer to every question is a segment of text, or span, from the correspo

rajpurkar.github.io

- ์˜์–ด ๋จธ์‹ ๋Ÿฌ๋‹ Reading Comprehension ๋ฐ์ดํ„ฐ์…‹ 

- ๋ฒ„์ „: v1.1, v2.0

Stanford Question Answering Dataset (SQuAD)์˜ ์•ฝ์ž๋‹ค. ์šฐ๋ฆฌ๋Š” QG ํ”„๋กœ์ ํŠธ์— ์‚ฌ์šฉํ–ˆ์ง€๋งŒ, ์›๋ž˜๋Š” QA๋ฅผ ์œ„ํ•œ ๋ฐ์ดํ„ฐ์…‹์ด๋‹ค.

๋ฒ„์ „ v1.1์˜ ๊ฒฝ์šฐ์—๋Š” 500+๊ฐœ์˜ ์•„ํ‹ฐํด๋กœ ๋งŒ๋“ค์–ด์ง„ 100,000+๊ฐœ์˜ QA ์Œ์ด ์กด์žฌํ•œ๋‹ค.

์‚ฌ์ดํŠธ์— ๋“ค์–ด๊ฐ€์„œ ํ™•์ธํ•ด๋ณด๋ฉด, ์˜ˆ์‹œ ์ง€๋ฌธ๊ณผ ground truth ๋ฐ์ดํ„ฐ, ๊ทธ๋ฆฌ๊ณ  ์˜ˆ์ธกํ•œ ๋‹ต ์ผ๋ถ€๋ฅผ ํ™•์ธํ•ด๋ณผ ์ˆ˜ ์žˆ๋‹ค.

์•„๋ฌด๋ž˜๋„ ๋Œ€ํšŒ ํ˜•์‹์ด๋‹ค ๋ณด๋‹ˆ๊นŒ ๋‹ค๋ฅธ ์‚ฌ์šฉ์ž๋“ค์ด ์–ผ๋งˆ๋‚˜ ๋‹ต๋ณ€์„ ์ž˜ ์ฐพ์•˜๋Š”์ง€ (๋†’์€ ์ ์ˆ˜๋ฅผ ์–ป์—ˆ๋Š”์ง€) ์Šค์ฝ”์–ด๋ณด๋“œ๋ฅผ ํ™•์ธํ•  ์ˆ˜ ์žˆ๋‹ค.

v1.1์—๋Š” ๋‹ต๋ณ€ํ•  ์ˆ˜ ์žˆ๋Š” ์งˆ๋ฌธ ๋ฐ์ดํ„ฐ๋งŒ ํฌํ•จ๋˜์–ด์žˆ๋‹ค๊ณ  ํ•œ๋‹ค๋ฉด, v2.0์—๋Š” ์ผ๋ถ€๋Ÿฌ ๋‹ต์„ ์ฐพ์„ ์ˆ˜ ์—†๋Š” ๋ฌธ์ œ๊นŒ์ง€ ํฌํ•จ์ด ๋˜์–ด์žˆ๋‹ค. ์ด๋Ÿด ๊ฒฝ์šฐ์— ๋ชจ๋ธ์€ ๋‹ต์„ ์ฐพ์„ ์ˆ˜ ์—†๋Š” ๋ฌธ์ œ์ž„์„ ์ธ์‹ํ•  ์ˆ˜ ์žˆ์–ด์•ผ ํ•œ๋‹ค๊ณ  ํ•œ๋‹ค.

QG ํ”„๋กœ์ ํŠธ์—์„œ๋Š” ์ง€๋ฌธ๊ณผ ์งˆ๋ฌธ๋งŒ ์‚ฌ์šฉํ•˜๋ฉด ๋˜๋‹ˆ๊นŒ ํฌ๊ฒŒ ์ƒ๊ด€์€ ์—†๋‹ค.

 

2. KorQuAD

https://korquad.github.io/

 

KorQuAD

What is KorQuAD 2.0? KorQuAD 2.0์€ KorQuAD 1.0์—์„œ ์งˆ๋ฌธ๋‹ต๋ณ€ 20,000+ ์Œ์„ ํฌํ•จํ•˜์—ฌ ์ด 100,000+ ์Œ์œผ๋กœ ๊ตฌ์„ฑ๋œ ํ•œ๊ตญ์–ด Machine Reading Comprehension ๋ฐ์ดํ„ฐ์…‹ ์ž…๋‹ˆ๋‹ค. KorQuAD 1.0๊ณผ๋Š” ๋‹ค๋ฅด๊ฒŒ 1~2 ๋ฌธ๋‹จ์ด ์•„๋‹Œ Wikipedia artic

korquad.github.io

- ํ•œ๊ตญ์–ด ๋จธ์‹ ๋Ÿฌ๋‹ Reading Comprehension ๋ฐ์ดํ„ฐ์…‹

- ๋ฒ„์ „: v1.0, v2.0

SQuAD์™€ ๋™์ผํ•œ ๋ฐฉ์‹์œผ๋กœ ๋งŒ๋“ค์–ด์ง„ ๋ฐ์ดํ„ฐ์…‹์ด๋‹ค. ๋Œ€์‹  ํ•œ๊ตญ์–ด๋กœ ๋˜์–ด์žˆ๋‹ค๋Š” ์ฐจ์ด๊ฐ€ ์žˆ์Šต๋‹ˆ๋‹ค. ์œ„ํ‚คํ”ผ๋””์•„์˜ ๋ฐ์ดํ„ฐ๋ฅผ ํ™œ์šฉํ•˜์—ฌ ์ œ์ž‘๋˜์—ˆ๋‹ค๊ณ  ํ•œ๋‹ค. SQuAD v2.0์€ v1.0๊ณผ ๋‹ค๋ฅด๊ฒŒ 1~2๋ฌธ๋‹จ์ด ์•„๋‹Œ ์œ„ํ‚คํ”ผ๋””์•„ ์ „์ฒด์—์„œ ๋‹ต์„ ์ฐพ๋Š”๋‹ค๋Š” ์ฐจ์ด๊ฐ€ ์žˆ๋‹ค.

 

SQuAD์™€ KorQuAD๋Š” ๋™์ผํ•œ ์–ด๋…ธํ…Œ์ด์…˜ ๊ตฌ์กฐ๋ฅผ ๊ฐ€์ง„ ๋ฐ์ดํ„ฐ์…‹์ด๋ฏ€๋กœ, ํ”„๋กœ์ ํŠธ๋ฅผ ์ง„ํ–‰ํ•  ๋•Œ ์›ํ•˜๋Š” ์–ธ์–ด๊ฐ€ ์˜์–ด์ธ์ง€ ํ•œ๊ตญ์–ด์ธ์ง€์— ๋”ฐ๋ผ์„œ ์ ์ ˆํ•˜๊ฒŒ ์„ ํƒํ•˜์—ฌ ํ”„๋กœ์ ํŠธ๋ฅผ ์ˆ˜ํ–‰ํ•˜๋ฉด ๋œ๋‹ค.

'CS study/๋จธ์‹ ๋Ÿฌ๋‹' Related Articles +

๋‹ค์ด๋ธŒ ๊ฐ€์„ ๊ธฐ์ˆ˜ 2์ฃผ์ฐจ ๊ณผ์ œ - Audio Classification Model (์˜ค๋””์˜ค ๋ถ„๋ฅ˜ ๋ชจ๋ธ) ๋งŒ๋“ค๊ธฐ ๊ณผ์ œ ํ•˜๋Š” ๊ณผ์ •

๊ฐ„๋žตํ•˜๊ฒŒ ์ •๋ฆฌํ•ด๋ณด๋„๋ก ํ•˜๊ฒ ๋‹ค.

 

์šฐ์„ , ๋‚˜๋Š” ๋”ฅ๋Ÿฌ๋‹์„ ๊ทธ๋ ‡๊ฒŒ ์ž˜ ์•„๋Š” ํŽธ์€ ์•„๋‹ˆ๋ผ์„œ ๊ฐ€์žฅ ์‰ฌ์šด ๋ฐฉ๋ฒ•์œผ๋กœ ๊ณผ์ œ๋ฅผ ํ•ด๊ฒฐํ•˜๊ธฐ๋กœ ํ•˜์˜€๊ณ 

๊ทธ ๊ณผ์ •์—์„œ ์ฑ„ํƒ๋œ ๊ฒƒ์ด ๋ฐ”๋กœ CNN ๋ชจ๋ธ์ด๋‹ค.

Tensorflow๋ฅผ ์ด์šฉํ•˜์˜€๋‹ค. (ํ•™๊ต์—์„œ ์‹œํ‚ค๋Š” ๊ณผ์ œ๋Š” ํŒŒ์ดํ† ์น˜๋ฅผ ์“ฐ๊ธฐ ๋•Œ๋ฌธ์—,, ํ…์„œํ”Œ๋กœ์šฐ๋Š” ์ฒ˜์Œ์ด๋‹ค)

 

1) ์˜ค๋””์˜ค ๋ฐ์ดํ„ฐ ๋ถˆ๋Ÿฌ์˜ค๊ธฐ

์‚ฌ์šฉํ•œ ๋ฐ์ดํ„ฐ ์„ค๋ช…์€ ๋‹ค์Œ๊ณผ ๊ฐ™๋‹ค.

14๊ฐœ์˜ ์•…๊ธฐ๋“ค๋ณ„ ์†Œ๋ฆฌ๊ฐ€ ์ €์žฅ๋˜์–ด ์žˆ๋Š” ๋ฐ์ดํ„ฐ์…‹์ž…๋‹ˆ๋‹ค. ์˜ค๋””์˜ค๋ฅผ MFCC ๊ณ„์ˆ˜์˜ ๊ฐœ์ˆ˜๋ฅผ 13๊ฐœ๋กœ ์„ค์ •ํ•œ MFCC ํ˜•ํƒœ๋กœ ์ „์ฒ˜๋ฆฌํ–ˆ์œผ๋ฉฐ ์ „์ฒ˜๋ฆฌ ๋ฐฉ์‹์€ ์•„๋ž˜์™€ ๊ฐ™์Šต๋‹ˆ๋‹ค. ์ „์ฒด ๋ฐ์ดํ„ฐ์…‹์—์„œ ๋ฌด์ž‘์œ„๋กœ ํ•˜๋‚˜์˜ ์•…๊ธฐ๋ฅผ ๊ณ ๋ฅด๊ณ , ํ•ด๋‹น ์•…๊ธฐ ๋ ˆ์ด๋ธ”์˜ ๋ฐ์ดํ„ฐ ์ค‘ ๋žœ๋คํ•˜๊ฒŒ ํŒŒ์ผ์„ ๊ณจ๋ผ ๊ทธ ์Œ์„ฑ ํŒŒ์ผ ๋‚ด์—์„œ ๊ณต๋ฐฑ ๋ถ€๋ถ„์„ ์ œ์™ธํ•˜๊ณ  0.5์ดˆ๋ฅผ ์ƒ˜ํ”Œ๋งํ•˜๋Š” ๊ณผ์ •์„ ์ „์ฒด ๋ฐ์ดํ„ฐ์…‹์— ๋Œ€ํ•ด 56789๋ฒˆ ๋ฐ˜๋ณตํ–ˆ์Šต๋‹ˆ๋‹ค. ๋ฐ์ดํ„ฐ์˜ ํ˜•ํƒœ๋Š” ๋‹ค์Œ๊ณผ ๊ฐ™์Šต๋‹ˆ๋‹ค. ๋ฐ์ดํ„ฐ๋Š” ์–ด๋–ค ์ •๊ทœํ™”๋‚˜ ํ‘œ์ค€ํ™”๋„ ๊ฑฐ์น˜์ง€ ์•Š์•˜์Šต๋‹ˆ๋‹ค.

๋ฐ์ดํ„ฐ์˜ ํ˜•ํƒœ๋Š” ๋„˜ํŒŒ์ด๋กœ ์ €์žฅ๋˜์–ด ์žˆ์—ˆ๊ธฐ ๋•Œ๋ฌธ์— ๋„˜ํŒŒ์ด๋ฅผ ์ด์šฉํ•ด ๋ถˆ๋Ÿฌ์™€์ค€๋‹ค.

 

import numpy as np
Xdata = np.load("Xdata.npy")
ydata = np.load("ydata.npy")

 

๊ทธ ํ›„, ํ•„์š”ํ•œ ๋ชจ๋“ˆ๋“ค์„ ์ž„ํฌํŠธ ํ•ด์˜จ๋‹ค.

import tensorflow as tf
from tensorflow import keras
from tensorflow.keras import layers
from sklearn.model_selection import train_test_split

 

2) ์ •๊ทœํ™” ์ง„ํ–‰ ๋ฐ ๋ฐ์ดํ„ฐ ๋ถ„ํ• 

๋„˜ํŒŒ์ด ๋ฐฐ์—ด ํ˜•ํƒœ์ด๊ธฐ ๋•Œ๋ฌธ์— ์ „์ฒ˜๋ฆฌ๋กœ ๊ฐ„๋‹จํ•˜๊ฒŒ ์ •๊ทœํ™”๋ฅผ ์ง„ํ–‰ํ•ด ๋ณด์•˜๋‹ค.

Xdata_normalized = (Xdata - np.mean(Xdata)) / np.std(Xdata)

 

๋˜ํ•œ ํ•™์Šต๊ณผ ํ…Œ์ŠคํŠธ ๋ฐ์ดํ„ฐ์…‹ ๋ถ„๋ฆฌ๋ฅผ ์œ„ํ•ด train_test_split์„ ์ด์šฉํ•˜์˜€๋‹ค.

X_train, X_test, y_train, y_test = train_test_split(Xdata_normalized, ydata, test_size = 0.2, random_state = 42)

 

3) ๋ชจ๋ธ ์ƒ์„ฑ ๋ฐ ํ•™์Šต 

model = tf.keras.Sequential([
    tf.keras.layers.Conv1D(64, kernel_size=3, activation='relu', input_shape=X_train.shape[1:]),
    tf.keras.layers.MaxPooling1D(pool_size=2),
    tf.keras.layers.Conv1D(128, kernel_size=3, activation='relu'),
    tf.keras.layers.MaxPooling1D(pool_size=2),
    tf.keras.layers.Flatten(),
    tf.keras.layers.Dense(512, activation='relu'),
    tf.keras.layers.Dropout(0.2),
    tf.keras.layers.Dense(256, activation='relu'),
    tf.keras.layers.Dropout(0.5),
    tf.keras.layers.Dense(y_train.shape[1], activation='softmax')
])

์ผ€๋ผ์Šค๋ฅผ ์ด์šฉํ•˜์—ฌ CNN ์ธต์„ ์Œ“์•„์ค€๋‹ค. ๊ณผ์ ํ•ฉ ๋ฐฉ์ง€์šฉ์œผ๋กœ Dropout์„ ์ด์šฉํ•œ๋‹ค.

์ธต์„ ์Œ“๋Š” ๊ธฐ์ค€์ด๋ผ ํ•œ๋‹ค๋ฉด ์‚ฌ์‹ค ์ž˜ ๋ชจ๋ฅด๊ฒ ๊ณ  ์ด๊ฒƒ์ €๊ฒƒ ์กฐํ•ฉํ•ด๋ณด์•˜๋‹ค.

# ๋ชจ๋ธ ์ปดํŒŒ์ผ
model.compile(optimizer='adam', loss='categorical_crossentropy', metrics=['accuracy'])

# ๋ชจ๋ธ ํ•™์Šต
history = model.fit(X_train, y_train, epochs=50, batch_size=64)

๋ชจ๋ธ ํ•™์Šต์„ ์œ„์™€ ๊ฐ™์ด ์ง„ํ–‰ํ•œ๋‹ค. ์—ํฌํฌ ์ˆ˜๋Š” ์ฒ˜์Œ์— 20์œผ๋กœ ํ–ˆ๋‹ค๊ฐ€ ์ˆ˜๋ ด์ด ์•ˆ๋๊ธธ๋ž˜ ๋” ํฌ๊ฒŒ ํ•ด์คฌ๋‹ค.

 

4) ์„ฑ๋Šฅ ํ…Œ์ŠคํŠธ

Epoch 50/50 688/688 [==============================] - 7s 11ms/step - loss: 0.2341 - accuracy: 0.9247

ํ•™์Šต ๊ฒฐ๊ณผ ์ •ํ™•๋„๊ฐ€ 0.9247์ด์—ˆ๋‹ค.

๋” ํ•™์Šต์‹œํ‚ค๋ฉด ์™„์ „ ์ˆ˜๋ ดํ•  ๊ฒƒ ๊ฐ™์ง€๋งŒ ์‹œ๊ฐ„๊ด€๊ณ„์ƒ..

 

Test ๋ฐ์ดํ„ฐ์…‹์œผ๋กœ ๋‹ค์‹œ ํ‰๊ฐ€ํ–ˆ์„ ๋•Œ ๊ฒฐ๊ณผ๋Š” accuracy: 0.8739 ์ด์—ˆ๋‹ค. ์•ฝ๊ฐ„ ๊ณผ์ ํ•ฉ์ด ๋œ ๊ฑธ๊นŒ?.? ์‹ถ๊ธฐ๋„...

 

๋‹ค๋ฅธ ํŒ€์›์€ LSTM์œผ๋กœ ํ•˜๊ณ  ๋‚˜๋„ ์‹œ๊ณ„์—ด ๋ฐ์ดํ„ฐ๋Š” LSTM์ด ๋” ์„ฑ๋Šฅ์ด ์ข‹๋‹ค๊ณ  ์•Œ๊ณ  ์žˆ๋Š”๋ฐ ์ด๋ฏธ CNN์œผ๋กœ ๋„ˆ๋ฌด ์ข‹์€ ์„ฑ๋Šฅ์„ ๋‚ด์„œ ๋” ์ข‹์•„์งˆ ์ˆ˜ ์žˆ์„์ง€ ๊ถ๊ธˆํ•ด์กŒ๋‹ค!

 

++ ๋”ฅ๋Ÿฌ๋‹ ๊ณต๋ถ€ ์ข€ ํ•ด์•ผ๊ฒ ..๋‹ค

'CS study/๊ธฐํƒ€' Related Articles +

์ด์ง„ ๋ถ„๋ฅ˜๊ธฐ์˜ ์„ฑ๋Šฅ์„ ๊ณ„์‚ฐํ•  ๋•Œ ์šฐ๋ฆฌ๋Š” confusion matrix (ํ˜ผ๋™ํ–‰๋ ฌ) ์„ ๊ทธ๋ ค True positive, True negative, False positive, False negative๋ฅผ ํ™•์ธํ•˜๊ณ  ์ด๋ฅผ ํ†ตํ•ด precision, recall, accuracy๋“ฑ์„ ํ™•์ธํ•  ์ˆ˜ ์žˆ๋‹ค.

๊ทธ๋Ÿฐ๋ฐ ๋งŒ์•ฝ ๋ถ„๋ฅ˜ํ•ด์•ผ ํ•  ํด๋ž˜์Šค๊ฐ€ 3๊ฐœ ์ด์ƒ์ด๋ผ๋ฉด ์–ด๋–ป๊ฒŒ ํ•ด์•ผํ• ๊นŒ?

๋‘ ๊ฐ€์ง€ ๋ฐฉ์‹์ด ์žˆ๋Š”๋ฐ ๋ฐ”๋กœ Microaveraging ๊ณผ Macroaveraging์ด๋‹ค. ๋‘˜์˜ ์ฐจ์ด๋ฅผ ํ™•์ธํ•ด๋ณด์ž. 

 

Macroaveraging

๊ตฌํ•˜๊ณ  ์‹ถ์€ ๊ฐ๊ฐ์˜ ํด๋ž˜์Šค์— ๋Œ€ํ•ด์„œ ์„ฑ๋Šฅ์„ ๊ณ„์‚ฐํ•œ๋‹ค. ๊ทธ ์ดํ›„ ๊ฐ ํด๋ž˜์Šค์— ๋Œ€ํ•œ ํ‰๊ท ๊ฐ’์ด ์ตœ์ข… ์„ฑ๋Šฅ์ด ๋œ๋‹ค.

๋งŒ์•ฝ ํด๋ž˜์Šค๊ฐ€ 4๊ฐœ๋ผ๋ฉด, ์ž‘์€ confusion matrix 4๊ฐœ๋ฅผ ๊ทธ๋ฆฌ๊ณ , ์ด 4๊ฐœ์— ๋Œ€ํ•œ ํ‰๊ท ๊ฐ’์œผ๋กœ ์„ฑ๋Šฅ์„ ๊ตฌํ•  ์ˆ˜ ์žˆ๋Š” ๊ฒƒ์ด๋‹ค.

 

Microaveraging

๋ชจ๋“  ํด๋ž˜์Šค์˜ ๊ฒฐ๊ณผ๋ฅผ ํ•˜๋‚˜์˜ confusion matrix๋กœ ๋‚˜ํƒ€๋‚ด์–ด ๊ฐ ์„ฑ๋Šฅ์„ ๊ตฌํ•  ์ˆ˜ ์žˆ๋Š” ๋ฐฉ์‹์ด๋‹ค.

 

Microaveraging ๋ฐฉ์‹์œผ๋กœ ๊ณ„์‚ฐ๋œ score๋Š” ํ”ํ•˜๊ฒŒ ๋‚˜ํƒ€๋‚˜๋Š” ํด๋ž˜์Šค์— ๋Œ€ํ•œ ์ ์ˆ˜๋กœ ๊ฒฐ์ •๋œ๋‹ค.

'CS study/๊ธฐํƒ€' Related Articles +

Statement = Proposition : ๋ช…์ œ

- ์ •์˜: ์ฐธ์ด๋‚˜ ๊ฑฐ์ง“์œผ๋กœ ํŒ๋‹จํ•  ์ˆ˜ ์žˆ๋Š” ๋ฌธ์žฅ

- ์ข…๋ฅ˜

1) Universal Statement: ํ•œ ์ง‘ํ•ฉ์˜ ๋ชจ๋“  ์š”์†Œ์— ๋Œ€ํ•ด์„œ ์ฐธ

2) Conditional Statement: ํŠน์ • ์กฐ๊ฑด๋งŒ ํฌํ•จ

3) Existential Statement: ์กฐ๊ฑด์„ ๋งŒ์กฑํ•˜๋Š” ์š”์†Œ๊ฐ€ 1๊ฐœ ์ด์ƒ ์žˆ๋‹ค.

4) Universal Conditional Statement: universal & conditional

5) Universal Existential Statement: ์ฒซ ๋ถ€๋ถ„์€ universal, ๋‘ ๋ฒˆ์งธ ๋ถ€๋ถ„์€ existential

6) Existential Universal Statement: ์ฒซ ๋ถ€๋ถ„์€ existential, ๋‘ ๋ฒˆ์งธ ๋ถ€๋ถ„์€ universal

 

Set : ์ง‘ํ•ฉ

- ์ •์˜: ํŠน์ • ์กฐ๊ฑด์„ ๋งŒ์กฑํ•˜๋Š” ์š”์†Œ๋“ค์˜ ๋ชจ์ž„

- ex) { x | 0 < x < 5 }

 

Russell's Paradox

R = {x | x is a set and x is not an element of itself}

์ •์˜์— ๋”ฐ๋ฅด๋ฉด R์ด R์˜ ์š”์†Œ๋ผ๋ฉด, R์€ R์˜ ์š”์†Œ์ผ ์ˆ˜ ์—†๋‹ค.

๋˜ํ•œ, R์ด R์˜ ์š”์†Œ๊ฐ€ ์•„๋‹ˆ๋ผ๋ฉด, R์€ R์˜ ์š”์†Œ์ด๋‹ค.

-> ๋ชจ์ˆœ์ 

 

Cartesian product

A X B : Cartesian product of A and B

B X A : Cartesian product of B and A

์ •์˜: A X B = {(x, y) | x is a member of A, y is a member of B}

ex) A = {1, 2} / B = {3, 4} -> A X B = {(1,3), (1,4), (2,3), (2,4)}

 

Relation

- ๊ณต์ง‘ํ•ฉ์ด ์•„๋‹Œ ์ง‘ํ•ฉ A์— ๋Œ€ํ•ด A์— ๋Œ€ํ•œ relation = A X A์˜ subset

- ์ข…๋ฅ˜

1) Reflexive

ex) A = {1, 2, 3, 4}์ผ ๋•Œ

R1 = { (1, 1), (2, 2) } ๋ผ๋ฉด, ์ด ์ง‘ํ•ฉ์€ Reflexiveํ•˜์ง€ ์•Š๋‹ค.

์ด์œ : (3, 3), (4, 4)๊ฐ€ ์—†๋‹ค.

R2 = { (1, 1), (2, 2), (3, 3), (4, 4), (2, 3) } ๋ผ๋ฉด, ์ด ์ง‘ํ•ฉ์€ Reflexiveํ•˜๋‹ค.

์ด์œ : (1, 1)~(4, 4)๊ฐ€ ๋ชจ๋‘ ์žˆ๋‹ค. (2, 3)์€ ์ƒ๊ด€์ด ์—†๋‹ค.

 

2) Symmetric

ex) R3 = ๊ณต์ง‘ํ•ฉ์ด๋ผ๋ฉด, ์ด ์ง‘ํ•ฉ์€ Symmetricํ•˜๋‹ค.

์ด์œ : ์ง‘ํ•ฉ์—์„œ ์š”์†Œ๋“ค์˜ ์Œ์ด ์—†๊ธฐ ๋•Œ๋ฌธ์—

R4 = { (1, 2), (2, 1), (2, 2) } ๋ผ๋ฉด, ์ด ์ง‘ํ•ฉ์€ Symmetricํ•˜๋‹ค.

R5 =  { (1, 2), (2, 1), (2, 3) } ๋ผ๋ฉด, (3, 2)๊ฐ€ ์—†์–ด Symmetricํ•˜์ง€ ์•Š๋‹ค.

 

3) Transitive

R6 = { (1, 5), (5, 1), (1, 1) } ์ด๋ผ๋ฉด ๋งŒ์กฑํ•  ์ˆ˜ ์—†๋‹ค.

(1, 5), (5, 1) -> (1, 1) ์ด์ง€๋งŒ

(5, 1), (1, 5) -> (5, 5)๋„ ์žˆ์–ด์•ผ ํ•˜๋Š”๋ฐ ์—†๋‹ค.

1 2 3 4