August 2021
Beginner to intermediate
720 pages
15h 32m
Korean
Content preview from fastai와 파이토치가 만나 꽃피운 딥러닝
Become an O’Reilly member and get unlimited access to this title plus top books and audiobooks from O’Reilly and nearly 200 top publishers, thousands of courses curated by job role, 150+ live events each month,
O’Reilly covers everything we've got, with content to help us build a world-class technology community, upgrade the capabilities and competencies of our teams, and improve overall team performance as well as their engagement.I wanted to learn C and C++, but it didn't click for me until I picked up an O'Reilly book. When I went on the O’Reilly platform, I was astonished to find all the books there, plus live events and sandboxes so you could play around with the technology.I’ve been on the O’Reilly platform for more than eight years. I use a couple of learning platforms, but I'm on O'Reilly more than anybody else. When you're there, you start learning. I'm never disappointed.I'm always learning. So when I got on to O'Reilly, I was like a kid in a candy store. There are playlists. There are answers. There's on-demand training. It's worth its weight in gold, in terms of what it allows me to do.
561
14
ResNets
이 장은 앞 장에서 소개한
CNN
을 기반으로
ResNet
(잔차 신경망)을 구축하고 구조를 설명합
니다.
ResNet
은 케이밍 허
Kaiming
He
등이
2015
년에 「
Deep
Residual
Learning
for
Image
Recognition
(
https
://
oreil
.
ly
/
b68K8
)」 논문에서 소개했으며, 지금까지 가장 많이 사용
하는 모델 구조입니다. 최근에 개발된 이미지 모델은 대부분 같은 잔차 연결
residual
connection
기
법을 사용하며, 결국 원본
ResNet
을 약간 변형한 모델에 불과합니다.
우선은
ResNet
을 처음 제안했던 당시의 기본 구조를 살펴본 다음, 이를 개선한 최신 기법
을 설명하는 순서로 진행합니다. 하지만 간단한
CNN
으로도
100
% 정확도에 근접했으므로
MNIST
보다는 좀 더 어려운 데이터셋을 먼저 구해야 합니다.
14.1
앞 장에서
MNIST
데이터셋에 대해 달성한 정확도는 이미 상당히 높습니다. 여기서 모델의 구
조를 바꿔도 해당 모델이 성능 개선에 기여한 정도를 파악하기가 어렵겠죠. 따라서 이미지네트
데이터셋을 사용해서 좀 더 어려운 이미지 분류 문제를 시도해보겠습니다. 빠른 실험을 위해
이미지 크기는 작게 유지합니다.
우선 데이터를 가져옵니다.
160
픽셀로 ...
Become an O’Reilly member and get unlimited access to this title plus top books and audiobooks from O’Reilly and nearly 200 top publishers, thousands of courses curated by job role, 150+ live events each month,
and much more.
Read now
Unlock full access
More than 5,000 organizations count on O’Reilly
O’Reilly covers everything we've got, with content to help us build a world-class technology community, upgrade the capabilities and competencies of our teams, and improve overall team performance as well as their engagement.Julian F.
I wanted to learn C and C++, but it didn't click for me until I picked up an O'Reilly book. When I went on the O’Reilly platform, I was astonished to find all the books there, plus live events and sandboxes so you could play around with the technology.Addison B.
I’ve been on the O’Reilly platform for more than eight years. I use a couple of learning platforms, but I'm on O'Reilly more than anybody else. When you're there, you start learning. I'm never disappointed.Amir M.
I'm always learning. So when I got on to O'Reilly, I was like a kid in a candy store. There are playlists. There are answers. There's on-demand training. It's worth its weight in gold, in terms of what it allows me to do.