이제 합성곱 신경망을 만들기 위한 모든 구성 요소를 배웠습니다. 이들을 어떻게 조합하는지 알
아봅시다.
13.4
CNN
구조
전형적인
CNN
구조는 몇 개의 합성곱층을 쌓고(각각
ReLU
층을 그 뒤에 놓고), 그다음에 풀
링층을 쌓고, 그다음에 또 몇 개의 합성곱층(+
ReLU
)을 쌓고, 그다음에 다시 풀링층을 쌓는
식입니다. 네트워크를 통과하여 진행할수록 이미지는 점점 작아지지만, 합성곱층 때문에 일반
적으로 점점 더 깊어집니다(즉, 더 많은 특성 맵을 가집니다(그림
13
-
9
). 맨 위층에는 몇 개의
완전 연결 층(+
ReLU
)으로 구성된 일반적인 피드포워드 신경망
feedfoward
neural
network
23
이 추
가되고 마지막 층(예를 들면 ...
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.
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.
Head of Cybersecurity
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.
Field Engineer
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.
Data Platform Tech Lead
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.