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
Lightning Talk @ Chainer Meetup
Search
Sinhrks
October 14, 2015
Programming
0
53k
Lightning Talk @ Chainer Meetup
Sinhrks
October 14, 2015
Tweet
Share
More Decks by Sinhrks
See All by Sinhrks
daskperiment: Reproducibility for Humans
sinhrks
1
390
PythonとApache Arrow
sinhrks
6
1.9k
大規模データの機械学習におけるDaskの活用
sinhrks
10
3.2k
機械学習と解釈可能性
sinhrks
7
5.6k
LIME
sinhrks
2
1.3k
データ分析言語R 1年の振り返り
sinhrks
5
2.5k
pandasでのOSS活動事例と最初の一歩
sinhrks
2
19k
Dask Distributedによる分散機械学習
sinhrks
4
1.5k
Data processing using pandas and Dask
sinhrks
1
250
Other Decks in Programming
See All in Programming
Optimizing JRuby 10
headius
0
590
ComposeでのPicture in Picture
takathemax
0
130
Embracing Ruby magic
vinistock
2
230
Rubyの!メソッドをちゃんと理解する
alstrocrack
1
270
Improve my own Ruby
sisshiki1969
1
110
In geheimer Mission: AI Agents entwickeln
joergneumann
0
110
エンジニアが挑む、限界までの越境
nealle
1
330
オープンソースコントリビュート入門
_katsuma
0
130
KawaiiLT 登壇資料 キャリアとモチベーション
hiiragi
0
160
今話題のMCPサーバーをFastAPIでサッと作ってみた
yuukis
0
130
知識0からカンファレンスやってみたらこうなった!
syossan27
4
130
KANNA Android の技術的課題と取り組み
watabee
1
450
Featured
See All Featured
Save Time (by Creating Custom Rails Generators)
garrettdimon
PRO
31
1.2k
Build your cross-platform service in a week with App Engine
jlugia
230
18k
Designing for Performance
lara
608
69k
How to Create Impact in a Changing Tech Landscape [PerfNow 2023]
tammyeverts
52
2.5k
The Cost Of JavaScript in 2023
addyosmani
49
7.8k
[RailsConf 2023] Rails as a piece of cake
palkan
54
5.5k
A Tale of Four Properties
chriscoyier
159
23k
Improving Core Web Vitals using Speculation Rules API
sergeychernyshev
13
840
Designing Dashboards & Data Visualisations in Web Apps
destraynor
231
53k
How STYLIGHT went responsive
nonsquared
100
5.5k
Easily Structure & Communicate Ideas using Wireframe
afnizarnur
194
16k
Rails Girls Zürich Keynote
gr2m
94
13k
Transcript
Lightning Talk@ Chainer Meetup by sinhrks
ࣗݾհ • ϝʔΧʔʹͯσʔλੳ • OSS ׆ಈ: • PyData Development Team
(pandasίϛολ) • Blaze Development Team (Daskίϛολ) • NumPyαϒηοτͷฒྻࢄndarrayͷ࣮͋Γ • GitHub: https://github.com/sinhrks
Chainer ͷར༻໘ • ֶࣗࣗश • ۀͰͷ Deep Learning ׆༻ͳ͠
Chainer ͷྑ͍ͱ͜Ζ • ڧ͍ํ͕࡞͍ͬͯΔ • ϨΠϠఆ͕ٛతͰ໌ྎ • ෦ͷ࣮͕ಡΈ͍͢
Chainer ͷվળ • ֶशશମͷॲཧΛهड़͢Δඞཁ͕͋Δ • ҎԼͷΑ͏ͳఆ൪ॲཧͷͨΊͷ؆қه๏(ؔ/Ϋ ϥε)͕ཉ͍͠ • ॳճͷΈάϥϑग़ྗ •
epoch ͝ͱͷଛࣦ • early stopping • ՄࢹԽ
Chainer ͷ ՄࢹԽπʔϧ࡞Γ͍ͨ
֓ཁ • ֶशͷϞχλϦϯά • Computational Graph • ॏΈߦྻ (ະணख) •
ͳͲΛɺϦϞʔτ (Jupyter / Webϒϥβ) ͔Β ֬ೝ͍ͨ͠ • →Bokeh
ֶशͷϞχλϦϯά • ͪ͜ΒͷϒϩάΤϯτϦͷ༰ import chainer_vis.visualizer as visualizer iv = visualizer.JupyterVisualizer()
monitor = iv.get_classification_monitor() for … monitor.update(test_loss=loss, test_accuracy=acc)