March 2026
Intermediate
504 pages
11h 26m
Korean
Content preview from 파이토치로 배우는 LLM & AI
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.
89
3
장
고급 컴퓨터 비전: 이미지에서 특징 감지하기
그다음
forward
메서드에서 이 층을 쌓습니다. 데이터
x
를
layer1
에 전달하여
out
을 얻고, 이
를 다시
layer2
에 전달하여 새로운
out
을 얻습니다. 이 시점에 학습된 합성곱의 결과를 얻게
됩니다. 그다음 이 결과를 펼쳐서
fc1
과
fc2
에 전달합니다.
out
=
out
.
view
(
out
.
size
(
0
),
-
1
)
이 이를 위한 코드입니다.
이 신경망을
2
장에서처럼
50
번 에폭 동안 훈련하면 잘 동작하는 것을 볼 수 있습니다. 테스트
세트에서
91
% 정확도를 손쉽게 도달합니다.
훈련 에폭: 44 -- 손실: 0.091689
훈련 에폭: 45 -- 손실: 0.066864
훈련 에폭: 46 -- 손실: 0.061322
훈련 에폭: 47 -- 손실: 0.056557
훈련 에폭: 48 -- 손실: 0.039695
훈련 에폭: 49 -- 손실: 0.056213
10000개의 테스트 이미지에 대한 신경망의 정확도: 91.31%
따라서 신경망에 합성곱 층을 추가하면 확실히 이미지 분류 능력이 향상됩니다. 다음으로 이미
지가 신경망을 통과하는 과정을 살펴보면서 왜 효과적인지 조금 더 자세히 이해해 보겠습니다.
NOTE
_
책의 깃허브 코드를 보면
model
.
to
(
device
)
와 같은 코드가 자주 등장합니다. ...
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.