배워봅니다. 책의 내용을 얼마나 잘 이해하는지 스스로 점검해보려면, 이 장을 마친 후 여기서
다룬 내용을 처음부터 다시 만들어보기 바랍니다.
18.1
CAM
볼레 조
Bolei
Zhou
등이 쓴 「
Learning
Deep
Features
for
Discriminative
Localization
(
https
://
oreil
.
ly
/
5hik3
)」 논문에서 소개한
class
activation
map
(
CAM
)은 모델
이 내린 결정의 근거를 최종 합성곱 계층의 출력(평균 풀링 계층 직전)과 모델이 내놓은 예측
을 함께 사용하여 히트맵으로 시각화하는 방법입니다.
좀 더 정확히 설명해보죠. 최종 합성곱 계층의 각 커널을 최종 선형 계층의 각 뉴런에 매핑합니
다.
80
그리고 이렇게 얻은 선형 계층의 활성에 가중치의 점곱을 구해 얻은 특징 맵의 각 위치로
80
최종 합성곱 계층
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.