Upgrade to Pro
— share decks privately, control downloads, hide ads and more …
Speaker Deck
Features
Speaker Deck
PRO
Sign in
Sign up for free
Search
Search
少ないデータで画像分類の性能を上げるには
Search
masa-ita
February 21, 2019
Technology
0
370
少ないデータで画像分類の性能を上げるには
CNNを使った画像分類において少ないデータで過学習を抑制し性能を上げる方法を紹介
masa-ita
February 21, 2019
Tweet
Share
More Decks by masa-ita
See All by masa-ita
Ollamaを使ったLocal Language Model活用法
itagakim
1
130
Run Instant NeRF on Docker
itagakim
1
2.3k
3D Clustering and Metric Learning
itagakim
0
330
Cloud TPUの使い方〜BigBirdの日本語学習済みモデルを作る〜
itagakim
0
660
多言語学習済みモデルmT5とは?
itagakim
1
670
AWSのGPUを安く使ってTensorFlowモデルを訓練する方法
itagakim
0
360
最近の自然言語処理モデルの動向
itagakim
1
560
ディープラーニングで芸術はできるか?〜生成系ネットワークの進展〜
itagakim
0
330
AWSとTerraform初心者がやってみたこと
itagakim
1
460
Other Decks in Technology
See All in Technology
american aa airlines®️ USA Contact Numbers: Complete 2025 Support Guide
aaguide
0
500
無理しない AI 活用サービス / #jazug
koudaiii
0
100
Introduction to Bill One Development Engineer
sansan33
PRO
0
260
All About Sansan – for New Global Engineers
sansan33
PRO
1
1.2k
60以上のプロダクトを持つ組織における開発者体験向上への取り組み - チームAPIとBackstageで構築する組織の可視化基盤 - / sre next 2025 Efforts to Improve Developer Experience in an Organization with Over 60 Products
vtryo
3
1.9k
VS CodeとGitHub Copilotで爆速開発!アップデートの波に乗るおさらい会 / Rapid Development with VS Code and GitHub Copilot: Catch the Latest Wave
yamachu
3
460
QuickSight SPICE の効果的な運用戦略~S3 + Athena 構成での実践ノウハウ~/quicksight-spice-s3-athena-best-practices
emiki
0
290
セキュアなAI活用のためのLiteLLMの可能性
tk3fftk
1
340
An introduction to Claude Code SDK
choplin
2
1.2k
LLM拡張解体新書/llm-extension-deep-dive
oracle4engineer
PRO
23
6.3k
推し書籍📚 / Books and a QA Engineer
ak1210
0
140
ポストコロナ時代の SaaS におけるコスト削減の意義
izzii
1
470
Featured
See All Featured
The Straight Up "How To Draw Better" Workshop
denniskardys
235
140k
"I'm Feeling Lucky" - Building Great Search Experiences for Today's Users (#IAC19)
danielanewman
229
22k
The Language of Interfaces
destraynor
158
25k
Learning to Love Humans: Emotional Interface Design
aarron
273
40k
We Have a Design System, Now What?
morganepeng
53
7.7k
How to train your dragon (web standard)
notwaldorf
96
6.1k
CSS Pre-Processors: Stylus, Less & Sass
bermonpainter
357
30k
Design and Strategy: How to Deal with People Who Don’t "Get" Design
morganepeng
130
19k
Sharpening the Axe: The Primacy of Toolmaking
bcantrill
44
2.4k
Side Projects
sachag
455
42k
JavaScript: Past, Present, and Future - NDC Porto 2020
reverentgeek
50
5.5k
Speed Design
sergeychernyshev
32
1k
Transcript
" "
PYTHON'&IN# RESTART#5 2019/2/23 !$%
GOOGLE COLAB
60? • 2C0?%"' A@/"!3>.6 - "! ,8 •
%"' A@/"! =B5:< D. :< • %"'#&$!49A@/"! 7 )(*+ • cf. A@0?1;
/% -* " ) " ' ,
#+ -* &$# &$.# (+ !
)#/ & • ( • .- •
4" !2 • %0" + , %*", L1/L2%0" • 13$ ,' https://towardsdatascience.com/deep-learning-3-more-on-cnns-handling-overfitting-2bd5d99abe5d
• 6"(! + 1-37. $) • Keras
Dropout:% *4 • 2/, 9508 &'# https://keras.io/layers/core/#dropout
"BATCH NORMALIZATION • & #"% ' • Keras keras.layers.BatchNormalization()
• Google! $
L1/L2 /7* • 64(0"!$ +, #1 "!"8-&) •
2/7*kernel_regularizer • 3.*/7*activity_regularizer • Keras'5 /7*(0 • L1/7*keras.regularizers.l1(p) • L2/7*keras.regularizers.l2(p • 9%Elastic Netkeras.regularizers.l1_l2(l1=p1, l2=p2) https://keras.io/regularizers/
GOOGLE COLAB
@> • 15 04 #%' • 9B3* $' • KerasImageDataGenerator2,)!CA-&<8
• 0/F6%. width_shift_range, height_shift_range • D(+=brightness_rangeE%:?shear_range • zoom_range "channel_shift_range • 0/F6%.7;horizontal_flip, vertical_flip https://keras.io/preprocessing/image/#imagedatagenerator-class
GOOGLE COLAB
2?5%!$- • #!$E@0 )#," *& +(6!$ • /=+',9 :B;A ImageNethttp://www.image-
net.org/ ILSVRC2012."$:B1203D1000+ E@0 7 • KerasXceptionVGG16VGG19ResNet50InceptionV3 InceptionResNetV2MobileNetDenseNetNASNetMobileNetV2 C >41<8 https://keras.io/applications/
8H; %:6-4 • CLO' • 8H; %(1P>KA,3CLGO' "$9?
• '3 CLGB %,350* 8H) • DF8H • =I/ 8H; %2 %<> MJ ) • !&#& • DF8H.8H; %'3@1+50* N7E
LOQ+)8; • !A%.( ON29 +)6B • IJ@>229R51 G
+): ?C =D • HIJ@29R5 1% 7E@=D : ?C99% • 4<3 +)KF $,'0-/0�*'0 -/0&OQ+) 4<M • LOQ+)>P"