์ „์ฒด ๊ธ€

I'm Game Challenger
๐Ÿ“‡ Machine Learning

[ML] Supervised Learning (์ง€๋„ํ•™์Šต)

์ด๋ฒˆ์—๋Š” Supervised Learning (์ง€๋„ํ•™์Šต)์— ๋ฐํ•˜์—ฌ ํ•œ๋ฒˆ ์•Œ์•„๋ณด๊ฒ ์Šต๋‹ˆ๋‹ค. Supervised Learning (์ง€๋„ํ•™์Šต) ์ด๋ž€?์ง€๋„ํ•™์Šต์€ Machine Learning(๊ธฐ๊ณ„ํ•™์Šต)์˜ ํ•œ ๋ถ„์•ผ๋กœ, ์ž…๋ ฅ ๋ฐ์ดํ„ฐ์™€ ๊ทธ์— ๋Œ€์‘ํ•˜๋Š” ์ •๋‹ต(๋ ˆ์ด๋ธ”)์„ ํ•จ๊ป˜ ์ œ๊ณต๋ฐ›์•„ ํ•™์Šตํ•˜๋Š” ๋ฐฉ๋ฒ•์ž…๋‹ˆ๋‹ค. ์ด ๊ณผ์ •์„ ํ†ตํ•ด ์•Œ๊ณ ๋ฆฌ์ฆ˜์€ ์ƒˆ๋กœ์šด ์ž…๋ ฅ ๋ฐ์ดํ„ฐ์— ๋Œ€ํ•ด ์ •ํ™•ํ•œ ์ถœ๋ ฅ์„ ์˜ˆ์ธกํ•  ์ˆ˜ ์žˆ๋Š” ๋ชจ๋ธ์„ ๋งŒ๋“ญ๋‹ˆ๋‹ค. ์ฃผ์š”ํ•œ ํŠน์ง•๋“ค์— ๋ฐํ•˜์—ฌ ๋” ์‚ดํŽด๋ณด๋ฉด 1. ๋ ˆ์ด๋ธ”์ด ์žˆ๋Š” ๋ฐ์ดํ„ฐ ์‚ฌ์šฉ ๊ฐ ๋ฐ์ดํ„ฐ ํฌ์ธํŠธ์—๋Š” ์ž…๋ ฅ๊ฐ’๊ณผ ๊ทธ์— ๋Œ€์‘ํ•˜๋Š” ์ •๋‹ต์ด ํ•จ๊ป˜ ์ œ๊ณต๋ฉ๋‹ˆ๋‹ค.์˜ˆ๋ฅผ ๋“ค์–ด, ์ด๋ฏธ์ง€ ๋ถ„๋ฅ˜ ์ž‘์—…์—์„œ๋Š” ์ด๋ฏธ์ง€(์ž…๋ ฅ)์™€ ๊ทธ ์ด๋ฏธ์ง€๊ฐ€ ๋‚˜ํƒ€๋‚ด๋Š” ๊ฐ์ฒด์˜ ์ด๋ฆ„(์ถœ๋ ฅ)์ด ์Œ์„ ์ด๋ฃน๋‹ˆ๋‹ค.์‚ฌ์ง„๊ณผ ๊ทธ ์‚ฌ์ง„์˜ ํƒœ๊ทธ(์˜ˆ: "๊ฐ•์•„์ง€", "๊ณ ์–‘์ด")๊ฐ€ ์Œ์œผ๋กœ ์ฃผ์–ด์ง€๋ฉด, ๋ชจ๋ธ..

๐Ÿ“„ Thesis

[Paper Review] VGGNet Code ๊ตฌํ˜„ (By PyTorch)

๋…ผ๋ฌธ์„ ๊ณ„์† ์ฝ์–ด์•ผ์ง€ ์ฝ์–ด์•ผ์ง€ ์ƒ๊ฐํ•˜๋‹ค๊ฐ€.. ์šฉ๊ธฐ๋ฅผ ๋‚ด์–ด์„œ ํ•œ๋ฒˆ ์ฝ์–ด๋ณธ ๋‚ด์šฉ์„ ์ฝ”๋“œ๋กœ ๊ตฌํ˜„ํ•ด ๋ณด๊ฒ ์Šต๋‹ˆ๋‹ค.VGGNet Review๋…ผ๋ฌธ ๋ฆฌ๋ทฐํ•œ ๋‚ด์šฉ์€ ์•„๋ž˜ ๋งํฌ์— ๋‹ฌ์•„๋†“๊ฒ ์Šต๋‹ˆ๋‹ค! [Paper Review] VGGnet Review๋…ผ๋ฌธ์„ ๊ณ„์† ์ฝ์–ด์•ผ์ง€ ์ฝ์–ด์•ผ์ง€ ์ƒ๊ฐํ•˜๋‹ค๊ฐ€.. ์šฉ๊ธฐ๋ฅผ ๋‚ด์–ด์„œ ํ•œ๋ฒˆ ์ฝ์–ด๋ณธ ๋‚ด์šฉ์„ ์ •๋ฆฌํ•ด๋ณด๊ฒ ์Šต๋‹ˆ๋‹ค. VGGNet Paper (2014)VERY DEEP CONVOLUTIONAL NETWORKS FOR LARGE-SCALE IMAGE RECOGNITION.๋…ผ๋ฌธ ์‚ฌ์ดํŠธ ๋งํฌ๋Š” ์•„๋ž˜daehyun-bigbread.tistory.comVGGNet Architecture ๊ทธ๋Ÿฌ๋ฉด ํ•œ๋ฒˆ VGGNet์„ ์ฝ”๋“œ๋กœ ํ•œ๋ฒˆ ๊ตฌํ˜„์„ ํ•˜๋ณด๊ฒ ์Šต๋‹ˆ๋‹ค. - D์—ด์˜ ๋ชจ๋ธ(VGG16)์„ ๊ตฌํ˜„ํ•ด๋ณด์•˜์Šต๋‹ˆ๋‹ค.image input..

๐Ÿ“„ Thesis

[Paper Review] VGGnet Review

๋…ผ๋ฌธ์„ ๊ณ„์† ์ฝ์–ด์•ผ์ง€ ์ฝ์–ด์•ผ์ง€ ์ƒ๊ฐํ•˜๋‹ค๊ฐ€.. ์šฉ๊ธฐ๋ฅผ ๋‚ด์–ด์„œ ํ•œ๋ฒˆ ์ฝ์–ด๋ณธ ๋‚ด์šฉ์„ ์ •๋ฆฌํ•ด๋ณด๊ฒ ์Šต๋‹ˆ๋‹ค. VGGNet Paper (2014)VERY DEEP CONVOLUTIONAL NETWORKS FOR LARGE-SCALE IMAGE RECOGNITION.๋…ผ๋ฌธ ์‚ฌ์ดํŠธ ๋งํฌ๋Š” ์•„๋ž˜์— ๋‚จ๊ฒจ๋†“๊ฒ ์Šต๋‹ˆ๋‹ค. ๊ทธ๋Ÿฌ๋ฉด ํ•œ๋ฒˆ ์ฐจ๊ทผ์ฐจ๊ทผ ๋ฆฌ๋ทฐํ•ด ๋ณด๊ฒ ์Šต๋‹ˆ๋‹ค. Very Deep Convolutional Networks for Large-Scale Image RecognitionIn this work we investigate the effect of the convolutional network depth on its accuracy in the large-scale image recognition setting. Our main ..

๐Ÿ”ฅ PyTorch

[PyTorch] Checkpoint Model ์ €์žฅ & ๋ถˆ๋Ÿฌ์˜ค๊ธฐ

โš ๏ธ ๋ณธ ๋‚ด์šฉ์€ PyTorch Korea์˜ ๊ณต์‹ ๋ฌธ์„œ์— ๊ธฐ๋ฐ˜ํ•˜์—ฌ ๊ณต๋ถ€ํ•œ ๋‚ด์šฉ์„ ์ ์€๊ฒƒ์ด๋‹ˆ ์–‘ํ•ด๋ฐ”๋ž๋‹ˆ๋‹ค! PyTorch์—์„œ ์ผ๋ฐ˜์ ์ธ ์ฒดํฌํฌ์ธํŠธ(checkpoint) ์ €์žฅํ•˜๊ธฐ & ๋ถˆ๋Ÿฌ์˜ค๊ธฐ์ถ”๋ก (inference) ๋˜๋Š” ํ•™์Šต(training)์˜ ์žฌ๊ฐœ๋ฅผ ์œ„ํ•ด ์ฒดํฌํฌ์ธํŠธ(checkpoint) ๋ชจ๋ธ์„ ์ €์žฅํ•˜๊ณ  ๋ถˆ๋Ÿฌ์˜ค๋Š” ๊ฒƒ์€ ๋งˆ์ง€๋ง‰์œผ๋กœ ์ค‘๋‹จํ–ˆ๋˜ ๋ถ€๋ถ„์„ ์„ ํƒํ•˜๋Š”๋ฐ ๋„์›€์„ ์ค„ ์ˆ˜ ์žˆ์Šต๋‹ˆ๋‹ค. ์ฒดํฌํฌ์ธํŠธ๋ฅผ ์ €์žฅํ•  ๋•Œ๋Š”tutorials.pytorch.krPyTorch์—์„œ Inference & Training์„ ๋‹ค์‹œ ํ•˜๊ธฐ ์œ„ํ•ด์„œ Checkpoint Model์„ ์ €์žฅ & ๋ถˆ๋Ÿฌ์˜ค๋Š”๊ฒƒ์„ ํ•œ๋ฒˆ ํ•ด๋ณด๊ฒ ์Šต๋‹ˆ๋‹ค.IntroPyTorch์—์„œ ์—ฌ๋Ÿฌ Checkpoint๋“ค์„ ์ €์žฅํ•˜๊ธฐ ์œ„ํ•ด์„  ์‚ฌ์ „(Dictionary)์— Checkpoint๋“ค์„ ๊ตฌ์„ฑํ•œํ›„..

๐Ÿ“‡ Machine Learning

[ML] Model์˜ ํ•™์Šต๊ณผ ํ‰๊ฐ€

๋จธ์‹ ๋Ÿฌ๋‹ ๋ชจ๋ธ์˜ ํ•™์Šต๊ณผ ํ‰๊ฐ€ ๊ณผ์ •์—์„œ ์ค‘์š”ํ•œ ์š”์†Œ๋“ค์— ๋Œ€ํ•ด ๋‹ค๋ฃจ๊ฒ ์Šต๋‹ˆ๋‹ค.ํ›ˆ๋ จ ๋ฐ์ดํ„ฐ์™€ ํ…Œ์ŠคํŠธ ๋ฐ์ดํ„ฐ์˜ ๋ถ„ํ• ๋ชจ๋ธ์˜ ์„ฑ๋Šฅ์„ ์ •ํ™•ํžˆ ํ‰๊ฐ€ํ•˜๊ณ  ์ผ๋ฐ˜ํ™” ๋Šฅ๋ ฅ์„ ํ™•์ธํ•˜๊ธฐ ์œ„ํ•ด ๋ฐ์ดํ„ฐ์…‹์„ ํ›ˆ๋ จ ๋ฐ์ดํ„ฐ์™€ ํ…Œ์ŠคํŠธ ๋ฐ์ดํ„ฐ๋กœ ๋ถ„ํ• ํ•ฉ๋‹ˆ๋‹ค.ํ›ˆ๋ จ ๋ฐ์ดํ„ฐ๋Š” ๋ชจ๋ธ์„ ํ•™์Šต์‹œํ‚ค๋Š” ๋ฐ ์‚ฌ์šฉ๋˜๋ฉฐ, ํ…Œ์ŠคํŠธ ๋ฐ์ดํ„ฐ๋Š” ํ•™์Šต๋˜์ง€ ์•Š์€ ๋ฐ์ดํ„ฐ์—์„œ ๋ชจ๋ธ์˜ ์„ฑ๋Šฅ์„ ํ‰๊ฐ€ํ•˜๋Š” ๋ฐ ์‚ฌ์šฉ๋ฉ๋‹ˆ๋‹ค.์ผ๋ฐ˜์ ์ธ ๋น„์œจ:Train(ํ›ˆ๋ จ ๋ฐ์ดํ„ฐ) : Test(ํ…Œ์ŠคํŠธ ๋ฐ์ดํ„ฐ) = 70:30Train(ํ›ˆ๋ จ ๋ฐ์ดํ„ฐ) : Test(ํ…Œ์ŠคํŠธ ๋ฐ์ดํ„ฐ) = 80:20๋ฐ์ดํ„ฐ ๋ถ„ํ•  ๋ฐฉ๋ฒ•Train(ํ›ˆ๋ จ ๋ฐ์ดํ„ฐ) & Test(ํ…Œ์ŠคํŠธ ๋ฐ์ดํ„ฐ)๋ฅผ ์–ด๋– ํ•œ ๋น„์œจ๋กœ ๋‚˜๋ˆ„๋Š”์ง€ ์•Œ์•˜์Šต๋‹ˆ๋‹ค. ๊ทธ๋Ÿฌ๋ฉด ์–ด๋– ํ•œ ๋ฐฉ๋ฒ•์œผ๋กœ ๋ถ„๋ฆฌํ• ๊นŒ์š”?์ž„์˜ ๋ถ„ํ• (Random Split):๋ฐ์ดํ„ฐ๋ฅผ ๋ฌด์ž‘์œ„๋กœ ์„ž์€ ํ›„, ์ง€์ •๋œ ๋น„์œจ์— ๋”ฐ๋ผ..

๐Ÿ“‡ Machine Learning

[ML] Naive Bayes (๋‚˜์ด๋ธŒ ๋ฒ ์ด์ฆˆ)

์ด๋ฒˆ์—๋Š” Naive Bayes (๋‚˜์ด๋ธŒ ๋ฒ ์ด์ฆˆ)๋ผ๋Š” ๊ฐœ๋…์— ๋ฐํ•˜์—ฌ ํ•œ๋ฒˆ ์•Œ์•„๋ณด๊ฒ ์Šต๋‹ˆ๋‹ค.Naive Bayes (๋‚˜์ด๋ธŒ ๋ฒ ์ด์ฆˆ)๋‚˜์ด๋ธŒ ๋ฒ ์ด์ฆˆ(Naive Bayes)๋Š” ์กฐ๊ฑด๋ถ€ ํ™•๋ฅ ์„ ํ™œ์šฉํ•˜์—ฌ ๋ถ„๋ฅ˜๋ฅผ ์ˆ˜ํ–‰ํ•˜๋Š” ์ง€๋„ ํ•™์Šต ์•Œ๊ณ ๋ฆฌ์ฆ˜์ž…๋‹ˆ๋‹ค.์ด ์•Œ๊ณ ๋ฆฌ์ฆ˜์€ ๋…๋ฆฝ ๋ณ€์ˆ˜๋“ค์ด ์„œ๋กœ ๋…๋ฆฝ์ ์ด๋ผ๊ณ  ๊ฐ€์ •ํ•˜์—ฌ ์ž‘๋™ํ•ฉ๋‹ˆ๋‹ค.์ด๋Ÿฌํ•œ ๊ฐ€์ • ํ•˜์—์„œ ๋‚˜์ด๋ธŒ ๋ฒ ์ด์ฆˆ๋Š” ๊ฐ„๋‹จํ•˜์ง€๋งŒ ๊ฐ•๋ ฅํ•œ ๋ถ„๋ฅ˜ ๋ชจ๋ธ์„ ์ œ๊ณตํ•ฉ๋‹ˆ๋‹ค.Bayes' Theorem (๋ฒ ์ด์ฆˆ ์ •๋ฆฌ)๋‚˜์ด๋ธŒ ๋ฒ ์ด์ฆˆ ์•Œ๊ณ ๋ฆฌ์ฆ˜์€ ๋ฒ ์ด์ฆˆ ์ •๋ฆฌ์— ๊ธฐ๋ฐ˜์„ ๋‘๊ณ  ์žˆ์Šต๋‹ˆ๋‹ค.๋ฒ ์ด์ฆˆ ์ •๋ฆฌ๋Š” ์กฐ๊ฑด๋ถ€ ํ™•๋ฅ ์„ ์‚ฌ์šฉํ•˜์—ฌ ํŠน์ • ์‚ฌ๊ฑด์˜ ์‚ฌํ›„ ํ™•๋ฅ ์„ ๊ณ„์‚ฐํ•˜๋Š” ์ˆ˜ํ•™์  ์›๋ฆฌ์ž…๋‹ˆ๋‹ค. ์•„๋ž˜๋Š” ๋ฒ ์ด์ฆˆ ์ •๋ฆฌ์˜ ์ˆ˜์‹์ž…๋‹ˆ๋‹ค. P(AโˆฃB)P(A|B)P(AโˆฃB): ์‚ฌ๊ฑด B๊ฐ€ ์ผ์–ด๋‚ฌ์„ ๋•Œ ์‚ฌ๊ฑด A๊ฐ€ ์ผ์–ด๋‚  ํ™•๋ฅ  (์‚ฌํ›„ ํ™•๋ฅ , Posterior ..

๐Ÿ“‡ Machine Learning

[ML] Linear Regression (์„ ํ˜•ํšŒ๊ท€)

์ด๋ฒˆ์—๋Š” Linear Regression (์„ ํ˜•ํšŒ๊ท€)์— ๋ฐํ•˜์—ฌ ์•Œ์•„๋ณด๊ฒ ์Šต๋‹ˆ๋‹ค.Linear Regression (์„ ํ˜•ํšŒ๊ท€)์„ ํ˜• ํšŒ๊ท€(Linear Regression)๋Š” ๋จธ์‹ ๋Ÿฌ๋‹์—์„œ ๋„๋ฆฌ ์‚ฌ์šฉ๋˜๋Š” ํšŒ๊ท€ ๋ถ„์„ ๊ธฐ๋ฒ• ์ค‘ ํ•˜๋‚˜๋กœ,๋…๋ฆฝ ๋ณ€์ˆ˜์™€ ์ข…์† ๋ณ€์ˆ˜ ๊ฐ„์˜ ๊ด€๊ณ„๋ฅผ ์„ ํ˜• ๋ฐฉ์ •์‹์œผ๋กœ ํ‘œํ˜„ํ•ฉ๋‹ˆ๋‹ค.์ด ๋ฐฉ๋ฒ•์€ ์ฃผ์–ด์ง„ ๋ฐ์ดํ„ฐ๋ฅผ ์ด์šฉํ•ด ๊ฐ€์žฅ ์ž˜ ๋งž๋Š” ์ง์„ ์„ ์ฐพ๋Š” ๊ฒƒ์ด ๋ชฉํ‘œ์ž…๋‹ˆ๋‹ค.์„ ํ˜• ํšŒ๊ท€๋Š” ๋ชจ๋ธ์ด ๋น„๊ต์  ๊ฐ„๋‹จํ•˜๊ณ  ํ•ด์„์ด ์šฉ์ดํ•˜๋‹ค๋Š” ์žฅ์ ์ด ์žˆ์Šต๋‹ˆ๋‹ค.ํšŒ๊ท€ ๋ฐฉ์ •์‹์„ ํ˜• ํšŒ๊ท€ ๋ชจ๋ธ์€ ๋‹ค์Œ๊ณผ ๊ฐ™์€ ํ˜•ํƒœ์˜ ๋ฐฉ์ •์‹์„ ์‚ฌ์šฉํ•ฉ๋‹ˆ๋‹ค. Y = β0 โ€‹ +β1โ€‹X + ฯต Y: ์ข…์† ๋ณ€์ˆ˜ (์˜ˆ์ธกํ•˜๋ ค๋Š” ๊ฐ’)X: ๋…๋ฆฝ ๋ณ€์ˆ˜ (์„ค๋ช… ๋ณ€์ˆ˜)β0: ์ ˆํŽธ (Intercept)β1โ€‹: ๊ธฐ์šธ๊ธฐ (Slope)ฯต: ์˜ค์ฐจ ํ•ญ (Error Term, ๋ชจ๋ธ์˜ ์˜ˆ์ธก๊ณผ ์‹ค์ œ ..

๐Ÿ“‡ Machine Learning

[ML] Supervised Learning (์ง€๋„ํ•™์Šต)

์ด๋ฒˆ์—๋Š” Supervised Learning (์ง€๋„ํ•™์Šต)์— ๋ฐํ•œ ๊ฐœ๋…์— ๋ฐํ•˜์—ฌ ํ•œ๋ฒˆ ์•Œ์•„๋ณด๊ฒ ์Šต๋‹ˆ๋‹ค.Supervised Learning (์ง€๋„ํ•™์Šต)์ง€๋„ํ•™์Šต์€ ๋จธ์‹ ๋Ÿฌ๋‹์˜ ํ•œ ๋ถ„์•ผ๋กœ, ๋ผ๋ฒจ์ด ์žˆ๋Š” ๋ฐ์ดํ„ฐ๋ฅผ ๊ธฐ๋ฐ˜์œผ๋กœ ํ•™์Šตํ•˜๋Š” ์•Œ๊ณ ๋ฆฌ์ฆ˜์ž…๋‹ˆ๋‹ค.์ž…๋ ฅ ๋ฐ์ดํ„ฐ์™€ ์ด์— ์ƒ์‘ํ•˜๋Š” ์ถœ๋ ฅ ๊ฐ’(๋ชฉํ‘œ ๋˜๋Š” ๋ผ๋ฒจ)์ด ์ฃผ์–ด์ง€๋ฉฐ, ๋ชจ๋ธ์€ ์ด ๋ฐ์ดํ„ฐ๋ฅผ ํ†ตํ•ด ํ•™์Šตํ•˜์—ฌ ์ƒˆ๋กœ์šด ์ž…๋ ฅ์— ๋Œ€ํ•ด ์˜ˆ์ธก์„ ์ˆ˜ํ–‰ํ•  ์ˆ˜ ์žˆ์Šต๋‹ˆ๋‹ค.์ง€๋„ํ•™์Šต์€ ํฌ๊ฒŒ ํšŒ๊ท€(Regression)์™€ ๋ถ„๋ฅ˜(Classification)๋กœ ๋‚˜๋‰ฉ๋‹ˆ๋‹ค.Regression (ํšŒ๊ท€)ํšŒ๊ท€๋Š” ์—ฐ์†์ ์ธ ์ˆซ์ž ๊ฐ’์„ ์˜ˆ์ธกํ•˜๋Š” ๋ฌธ์ œ๋ฅผ ๋‹ค๋ฃน๋‹ˆ๋‹ค.์˜ˆ๋ฅผ ๋“ค์–ด, ์ฃผํƒ์˜ ๋ฉด์ , ๋ฐฉ ๊ฐœ์ˆ˜, ์œ„์น˜ ๋“ฑ์„ ๊ธฐ๋ฐ˜์œผ๋กœ ์ฃผํƒ ๊ฐ€๊ฒฉ์„ ์˜ˆ์ธกํ•˜๋Š” ๊ฒฝ์šฐ๊ฐ€ ์ด์— ํ•ด๋‹นํ•ฉ๋‹ˆ๋‹ค.ํšŒ๊ท€ ๋ฌธ์ œ์—์„œ๋Š” ์˜ˆ์ธกํ•˜๋ ค๋Š” ๊ฐ’์ด ์—ฐ์†์ ์ธ ์ˆซ์ž๋กœ ํ‘œํ˜„๋ฉ๋‹ˆ๋‹ค.์˜ˆ..

๐Ÿ”ฅ PyTorch

[PyTorch] Model ์ €์žฅ & ๋ถˆ๋Ÿฌ์˜ค๊ธฐ

โš ๏ธ ๋ณธ ๋‚ด์šฉ์€ PyTorch Korea์˜ ๊ณต์‹ ๋ฌธ์„œ์— ๊ธฐ๋ฐ˜ํ•˜์—ฌ ๊ณต๋ถ€ํ•œ ๋‚ด์šฉ์„ ์ ์€๊ฒƒ์ด๋‹ˆ ์–‘ํ•ด๋ฐ”๋ž๋‹ˆ๋‹ค! ๋ชจ๋ธ ์ €์žฅํ•˜๊ณ  ๋ถˆ๋Ÿฌ์˜ค๊ธฐํŒŒ์ดํ† ์น˜(PyTorch) ๊ธฐ๋ณธ ์ตํžˆ๊ธฐ|| ๋น ๋ฅธ ์‹œ์ž‘|| ํ…์„œ(Tensor)|| Dataset๊ณผ Dataloader|| ๋ณ€ํ˜•(Transform)|| ์‹ ๊ฒฝ๋ง ๋ชจ๋ธ ๊ตฌ์„ฑํ•˜๊ธฐ|| Autograd|| ์ตœ์ ํ™”(Optimization)|| ๋ชจ๋ธ ์ €์žฅํ•˜๊ณ  ๋ถˆ๋Ÿฌ์˜ค๊ธฐ ์ด๋ฒˆ ์žฅ์—์„œ๋Š” ์ €์žฅํ•˜๊ธฐ๋‚˜tutorials.pytorch.krModel ์ €์žฅํ•˜๊ณ  ๋ถˆ๋Ÿฌ์˜ค๊ธฐ์ด๋ฒˆ์—๋Š” ์ €์žฅ or ๋ถˆ๋Ÿฌ์˜ค๊ธฐ๋ฅผ ํ†ตํ•ด ๋ชจ๋ธ์˜ ์ƒํƒœ ์œ ์ง€(persist)๋ฐ ๋ชจ๋ธ์˜ ์˜ˆ์ธก์„ ์‹œํ–‰ํ•˜๋Š” ๋ฐฉ๋ฒ•์„ ๋ณด๊ฒ ์Šต๋‹ˆ๋‹ค.import torchimport torchvision.models as modelsModel Weight(๊ฐ€์ค‘์น˜) ์ €์žฅํ•˜๊ณ  ๋ถˆ๋Ÿฌ์˜ค๊ธฐPyT..

๐Ÿ•น๏ธ ํ˜ผ๊ณต๋จธ์‹ 

[ํ˜ผ๊ณต๋จธ์‹ ] Tree's Ensemble - Gradient Boosting (๊ทธ๋ ˆ์ด์–ธํŠธ ๋ถ€์ŠคํŒ…)

Gradient Boosting (๊ทธ๋ ˆ์ด์–ธํŠธ ๋ถ€์ŠคํŒ…)๊ทธ๋ ˆ์ด๋””์–ธํŠธ ๋ถ€์ŠคํŒ…(Gradient Boosting)์€ ์–•์€ ๊ฒฐ์ • ํŠธ๋ฆฌ๋“ค์„ ์‚ฌ์šฉํ•˜์—ฌ ์ด์ „ ํŠธ๋ฆฌ์˜ ์˜ค์ฐจ๋ฅผ ๋ณด์™„ํ•˜๋Š” ๋ฐฉ์‹์œผ๋กœ ์•™์ƒ๋ธ”์„ ๊ตฌ์„ฑํ•˜๋Š” ๊ธฐ๋ฒ•์ž…๋‹ˆ๋‹ค.์‚ฌ์ดํ‚ท๋Ÿฐ์˜ GradientBoostingClassifier๋Š” ๊ธฐ๋ณธ์ ์œผ๋กœ ๊นŠ์ด๊ฐ€ 3์ธ ๊ฒฐ์ • ํŠธ๋ฆฌ๋ฅผ 100๊ฐœ ์‚ฌ์šฉํ•ฉ๋‹ˆ๋‹ค. ์–•์€ ๊ฒฐ์ • ํŠธ๋ฆฌ๋ฅผ ์‚ฌ์šฉํ•˜๊ธฐ ๋•Œ๋ฌธ์— ๊ณผ๋Œ€์ ํ•ฉ์— ๊ฐ•ํ•˜๊ณ , ์ผ๋ฐ˜์ ์œผ๋กœ ๋†’์€ ์ผ๋ฐ˜ํ™” ์„ฑ๋Šฅ์„ ๊ธฐ๋Œ€ํ•  ์ˆ˜ ์žˆ์Šต๋‹ˆ๋‹ค.'๊ทธ๋ ˆ์ด๋””์–ธํŠธ'๋ผ๋Š” ์ด๋ฆ„์—์„œ ์•Œ ์ˆ˜ ์žˆ๋“ฏ์ด, ์ด ๋ฐฉ๋ฒ•์€ ๊ฒฝ์‚ฌ ํ•˜๊ฐ•๋ฒ•์„ ์‚ฌ์šฉํ•˜์—ฌ ํŠธ๋ฆฌ๋ฅผ ์•™์ƒ๋ธ”์— ์ถ”๊ฐ€ํ•ฉ๋‹ˆ๋‹ค. ๋ถ„๋ฅ˜ ๋ฌธ์ œ์—์„œ๋Š” ๋กœ์ง€์Šคํ‹ฑ ์†์‹ค ํ•จ์ˆ˜๋ฅผ ์‚ฌ์šฉํ•˜๊ณ , ํšŒ๊ท€ ๋ฌธ์ œ์—์„œ๋Š” ํ‰๊ท  ์ œ๊ณฑ ์˜ค์ฐจ ํ•จ์ˆ˜๋ฅผ ์‚ฌ์šฉํ•ฉ๋‹ˆ๋‹ค.๊ฒฝ์‚ฌ ํ•˜๊ฐ•๋ฒ•์˜ ์›๋ฆฌ์ฒ˜๋Ÿผ, ๊ทธ๋ ˆ์ด๋””์–ธํŠธ ๋ถ€์ŠคํŒ…์€ ์†์‹ค ํ•จ์ˆ˜์˜ ์ตœ์†Œ์ ์„ ์ฐพ๊ธฐ ์œ„ํ•ด ๋ชจ๋ธ..

Bigbread1129
My Dev & Research Repository