Upgrade to Pro
— share decks privately, control downloads, hide ads and more …
Speaker Deck
Sign up for free
Menu
Search
Features
All features
Private URLs
Password Protection
Custom URLS
Scheduled publishing
Remove Branding
Restrict embedding
Deck Collections
Notes
Features
All features
Private URLs
Password Protection
Custom URLS
Scheduled publishing
Remove Branding
Restrict embedding
Deck Collections
Notes
Explore
Featured decks
Featured speakers
Programming
Technology
Storyboards
Explore
Featured decks
Featured speakers
Programming
Technology
Storyboards
Pricing
Search
Sign in
Sign up for free
Deep Learningと超解像
Search
Sponsored
·
SiteGround - Reliable hosting with speed, security, and support you can count on.
→
kmt-t
September 04, 2019
Programming
31
0
Share
Embed
Copy iframe code
Copy JS code
Copy link
Start on current slide
Deep Learningと超解像
kmt-t
September 04, 2019
More Decks by kmt-t
See All by kmt-t
組込エンジニアのための深層学習
kmt_t
1
23
Design by Contractとホーア論理
kmt_t
0
51
GCPと機械学習
kmt_t
1
50
進化するART
kmt_t
0
33
Other Decks in Programming
See All in Programming
AI × TiDD / 2026.09.05 Redmine 大阪
tokudiro
1
180
アクセシビリティから考える情報設計
high_g_engineer
0
380
大喜利で理解するLLM as a Judge / Understanding LLM-as-a-Judge through Ogiri
rockname
0
150
iOSDC Japan 2026 - Swiftで作って学ぼう!データベース自作入門
kaseken
2
250
setup-vp GitLab対応の裏側
naokihaba
0
120
JPUG勉強会 OSSデータベースの内部構造を理解しよう(第2回)
oga5
0
260
Java 27新機能 / Java 27 new features
kishida
2
150
選挙速報を多くのユーザーへ 届ける Live Activities 設計
hamayokokuririn
0
150
手動確認はもう限界 〜XCUITestでCustom URL Schemeの遷移を起動種別ごとに自動テストする〜 / Testing Custom URL Schemes with XCUITest
otouto
0
320
Kiroで創り、AgentCoreで繋ぐ!AWSで実践する「AI-DLC」から「AIエージェント統合」までの最新地図
licux
4
720
JRuby: Past, Present, and Future
headius
0
170
App Intentsのビルドプロセスを支える技術
kntkymt
0
410
Featured
See All Featured
The Success of Rails: Ensuring Growth for the Next 100 Years
eileencodes
47
8.3k
Practical Tips for Bootstrapping Information Extraction Pipelines
honnibal
25
2.1k
Distributed Sagas: A Protocol for Coordinating Microservices
caitiem20
333
23k
Public Speaking Without Barfing On Your Shoes - THAT 2023
reverentgeek
1
570
Embracing the Ebb and Flow
colly
88
5.2k
Six Lessons from altMBA
skipperchong
29
4.5k
Hiding What from Whom? A Critical Review of the History of Programming languages for Music
tomoyanonymous
3
1.2k
Helping Users Find Their Own Way: Creating Modern Search Experiences
danielanewman
31
3.4k
Done Done
chrislema
186
17k
HDC tutorial
michielstock
2
880
エンジニアに許された特別な時間の終わり
watany
109
250k
Leading Effective Engineering Teams in the AI Era
addyosmani
9
2.6k
Transcript
Deep Learningͱղ૾ ൃදऀ দӬ 1/57
ࣗݾհ • ໊લ : দӬ (kmt_t) • ৬ۀ :
ϓϩάϥϚ • ஶॻ : AndroidͷԾϚγϯ 2/57
ࣗݾհ • ઐ • ը૾ॲཧ (ओʹ࠷దԽ) • ίϯϐϡʔλάϥϑΟοΫε • ϑΝΠϧγεςϜ
• ԾϚγϯ • σΟʔϓϥʔχϯάͷࣄͨ·ʹͬͯ·͢ 3/57
σΟʔϓϥʔχϯά؆୯ͩʂ 4/57
ൃදͷҙࣄ߲ • ൃදऀ͕ࠐ։ൃऀͳͷͰࠐલఏͰ͠·͢ • ࣜɺܭࢉ΄ͱΜͲলུ͠·͢ • ಠࣗͷղऍɺཧతཪ͚ͷബ͍༰ؚ͕·Ε·͢ • εϥΠυͷຕ͕ଟ͍ͷͰएׯૣ͍ਐߦʹͳΓ·͢ 5/57
ൃදͷΞτϥΠϯ • લఏࣝ • σΟʔϓϥʔχϯάʁ • SRCNN • ೋޡࠩ •
ίϯϘϦϡʔγϣϯ 6/57
ൃදͷΞτϥΠϯ • վળ • ܭࢉྔͷ࠷దԽ • ͞ΒͳΔը࣭ͷվળ • ͱԠ༻ •
ੑೳධՁ 7/57
લఏࣝ 8/57
σΟʔϓϥʔχϯάʁ • ز͔ͭͷ͕͋Γɺ֊ʹͳ͍ͬͯΔ • ʹϊʔυ͕ͨ͘͞Μ͋Δ • Լͷͱͻͱ্ͭͷͷͯ͢ͷϊʔ υଓ͞Ε͍ͯΔ (શ݁߹) 9/57
σΟʔϓϥʔχϯάʁ • ଓॏΈΛ࣋ͪɺೖྗͷϊʔυͷ׆ ੑʹॏΈΛ͔͚ͨͷ͕ग़ྗͷϊʔυ ʹՃࢉ͞ΕΔ • ଓͷॏΈֶशʹΑΓௐ͞Εɺҙ ຯͷ͋Δग़ྗ͕ಘΒΕΔΑ͏ʹ͢Δ • ͜ΕΛχϡʔϥϧωοτϫʔΫͱݺͼɺ
֊͕ਂ͍ͷΛʮσΟʔϓϥʔχϯ άʯͱݺͿ 10/57
σΟʔϓϥʔχϯάͷֶश • ωοτϫʔΫͷग़ྗͱಘ͍ͨ݁ՌͷࠩΛʮޡࠩʯͱݺͿ • ޡ͕ࠩগͳ͘ͳΔΑ͏ʹωοτϫʔΫʹൖͤ͞ɺௐ͢Δ • ͜ͷௐΛʮόοΫϓϩύήʔγϣϯʯͱݺͿ 11/57
SRCNN 12/57
SRCNNͷհ • SRCNNχϡʔϥϧωοτϫʔΫΛͬͨղ૾ٕज़ • จʮImage Super-Resolution Using Deep Convolutional Networksʯ
• http://arxiv.org/abs/1501.00092 ※ waifu2xͰരൃతʹ༗໊ʹͳͬͨख๏ ※ waifu2x @ultraist ࢯ͕࡞ͬͨιϑτΣΞͰ͢ʂ 13/57
SRCNNͷޮՌ 14/57
SRCNNͷޮՌ 15/57
SRCNNจཁ ʮίϯϘϦϡʔγϣϯͯ͠ೋޡࠩΛͱΔͱղ૾Ͱ͖ΔΑʯ • ೋޡࠩͬͯʁ • ίϯϘϦϡʔγϣϯͬͯʁ 16/57
ೋޡࠩ • ೋޡࠩඪσʔλͱωοτϫʔΫͷग़ྗσʔλͷࠩͷೋ • ೋޡࠩͰͲΕ͙Β͍ඪͱҧ͏͔ܭࢉͰ͖Δ • ޡ͕ࠩখ͘͞ͳΔΑ͏ʹόοΫϓϩύήʔγϣϯͰֶश͢Δ • ༗໊ͳʮΦʔτΤϯίʔμʯೋޡࠩΛ͔ͭͬͯωοτϫʔ Ϋͷग़ྗ͔Βೖྗ͕෮ݩͰ͖ΔΑ͏ʹֶश͢Δ
17/57
ೋޡࠩΛֶͬͨशͷԠ༻ • ղ૾ • ϊΠζϦμΫγϣϯ • ৭ਂϋΠϏοτԽ • ௨ৗը૾ͷHDRԽ •
ϞϊΫϩը૾ͷϑϧΧϥʔԽ • ըॲཧҎ֎Ͱෆશͳσʔλ͔Βશͳσʔλ͕༧ଌͰ͖Δ 18/57
ίϯϘϦϡʔγϣϯ • ίϯϘϦϡʔγϣϯͱपลͷըૉʹ ॏΈΛ͔͚ͯ͢ • ݫີͳίϯϘϦϡʔγϣϯͷܭࢉํ ๏ޙͰઆ໌ • ੵܭࢉ͢Δը૾ͷൣғΛΟϯυ ͱݺͿ
• ίϯϘϦϡʔγϣϯσδλϧϑΟϧλ • ϑΟϧλͷ (ॏΈ) ΛόοΫϓϩ ύήʔγϣϯͰֶश͢Δ 19/57
SRCNNΞϧΰϦζϜ (ֶश) 1.ཧը૾ͱαΠζΛʹͯ͠2ഒʹֶͨ͠शը૾Λ༻ҙ 2.ֶशը૾ΛωοτϫʔΫͰͻͨ͢ΒίϯϘϦϡʔγϣϯ 3.ίϯϘϦϡʔγϣϯͨ͠ը૾ͱཧը૾ͷೋޡࠩΛͱΔ 4.όοΫϓϩύήʔγϣϯͰޡࠩௐ 20/57
SRCNNΞϧΰϦζϜ (ղ૾) 1.֦େ͍ͨ͠ը૾ͷαΠζΛ2ഒʹ͢Δ 2.ݩը૾Λֶशͨ͠ωοτϫʔΫͰͻΒ͢ΒίϯϘϦϡʔγϣϯ 3.͓ΘΓ 21/57
SRCNNͷΈ • ཧͷը૾ • ը૾ΛྼԽͤ͞Δؔ • Ϩϯζͷ৭ऩࠩ • ϞΞϨࢭ༻ͷϩʔύεϑΟϧλ •
JPEGϊΠζ • ྼԽͨ͠ը૾ 22/57
SRCNNͷΈ • ྼԽͨ͠ը૾Λݩʹ͢ ٯؔ • ͕͋Ε Λ ʹ͢͜ͱ͕Ͱ͖Δ • 23/57
SRCNNͷΈ • ٯؔ ͳΜͯଘࡏ͢Δͷ͔ʁܭࢉग़དྷΔͷ͔ʁ • ΛχϡʔϥϧωοτϫʔΫͰۙࣅ͢Δ • ΛٻΊΔͷʹԿͷςΫχοΫ͍Βͳ͍SRCNN • ٯؔ
ΛٻΊΔղ૾ͷख๏ଞʹ͋Δ 24/57
ܭࢉྔͷ࠷దԽ 25/57
ίϯϘϦϡʔγϣϯͷ ܭࢉྔ Οϯυ෯ ɹɹɹɹ× Οϯυ෯ ɹɹɹɹ× ೖྗνϟϯωϧ ɹɹɹɹ× ग़ྗνϟϯωϧ ɹɹɹɹʹ
1ϐΫηϧ͋ͨΓͷੵܭࢉճ 26/57
SRCNNܭࢉྔͷݮΒ͠ํ • ίϯϘϦϡʔγϣϯͷܭࢉྔΛܶతʹݮΒ͢ʹɺ • Οϯυ෯Λখ͘͢͞Δ (Ұ൪ޮՌ͋Γ) • ೖྗνϟϯωϧΛߜΔ • ग़ྗνϟϯωϧΛߜΔ
• ࠷ѱͳͷͯ͢ͷύϥϝʔλ͕େ͖͍έʔε • ܭࢉྔΛؾʹ͢ΔͳΒ͍ͣΕ͔ͷύϥϝʔλΛߜΔ 27/57
SRCNN࠷దԽ • ίϯϘϦϡʔγϣϯϑΟϧλͷՄࢹԽ • νϟωϧؒͷ݁߹ͷධՁ 28/57
SRCNN࠷దԽͷίπ • ֊͕ઙ͍΄͏͕ޡ͕ࠩೖྗଆͷ·Ͱ͏·͘ൖ͢Δ • ग़ྗଆͷνϟϯωϧ͕ଟ͗͢Δͱೖྗଆʹޡ͕ࠩ͠ͳ͍ • ೖྗଆ·ͰޡࠩΛൖͤ͞ΔʹֶशճΛ૿͢ • ೖྗଆͷΟϯυ͍ํ͕͍͍͕͗͢Δͱֶशࠔ •
࣍ͷʹࢀর͞Εͳ͍νϟϯωϧ͕͋Δͱνϟϯωϧ͕ଟ͗͢ 29/57
waifu2xͷωοτϫʔΫઃܭ • ܭࢉྔͷ߹ܭʹ • ͨͩ͠ը૾Λ2ഒʹ͢Δ߹ܭࢉྔ͕΄΅1/4 30/57
࠷దԽޙͷωοτϫʔΫߏ • 7͔Β4ʹมߋ • PSNRྼԽ͢Δ͕ࢹ֮తʹڐ༰ൣғ (ओ؍ʹΑΔ) 31/57
ܭࢉྔ͕۩ମతʹΠϝʔδग़དྷͳ͍ • 1TFLOPSͷܭࢉػͰϑϧHDը૾Λॲཧ͢ΔͱԿඵʁ • GeForce GTX 480 ͩͱ 1.345TFLOPS •
ͻͱੲલͷGPU͕ͩͦΕͰࠓͷΈࠐΈDSPͳͲΑΓڧྗ 32/57
ܭࢉྔ͕۩ମతʹΠϝʔδग़དྷͳ͍ • waifu2x • 54ສੵܭࢉ/ϐΫηϧ • 1920x1080ϐΫηϧ/1133ms@1TFLOPS • ࠷దԽޙ •
2.3ສੵܭࢉ/ϐΫηϧ • 1920x1080ϐΫηϧ/48ms@1TFLOPS 33/57
ͦΕͰଟ͗͢Δܭࢉྔ • ࠷దԽޙͰΈࠐΈʹΈࠐΉʹͭΒ͍ܭࢉྔ • ͱ͍͏ͷͷϥϯμϜΞΫηεͳ͠ɺ͔ͭฒྻԽ૬؆୯ 34/57
ΈࠐΈ։ൃͷԠ༻ͷ՝ • ଳҬͳϝϞϦ͕ͳ͍ͱͭΒ͍ • ղ૾ΑΓ؆୯ͳλεΫͳΒܭࢉྔ·ͩݮΒͤΔ • ؆୯ͳλεΫʹ৭ௐิਖ਼ɺϊΠζআڈɺϋΠϏοτԽ͋ͨΓ • ϓϩάϥϜ։ൃඇৗʹ؆୯ͳͷͰͳ͍ 35/57
͞ΒͳΔը࣭ͷվળ 36/57
ࣝผϞσϧͱੜϞσϧ • ࣝผϞσϧ • ର͕Կ͔Λྨɺࣝผ͢ΔͨΊͷϞσϧ • ੜϞσϧ • ༩͑ΒΕͨύϥϝʔλ͔ΒσʔλΛੜ͢Δ •
ҰൠతʹࣝผϞσϧΛ͔ͭͬͨԠ༻͕ଟ͍ • ࣮ੜϞσϧ͕͍ʂ 37/57
Generative Adversarial Networks • GANͰ༩͑ΒΕͨύϥϝʔλ͔Βը૾ Λੜ͢Δ • ύϥϝʔλ͝ͱʹҙຯ͕͋Γɺੜ͞ ΕΔը૾ͷ੍ޚՄೳ •
http://qiita.com/rezoolab/ items/5cc96b6d31153e0c86bc 38/57
GANͷΞϧΰϦζϜ • ύϥϝʔλ͔ΒσʔλΛੜ͢Δੜث • σʔλͷຊͬΆ͞Λఆ͢Δࣝผث 39/57
GANͷΞϧΰϦζϜ 1.ੜث༩͑ΒΕͨύϥϝʔλ͔ΒσʔλΛੜ͢Δ 2.ࣝผثੜ͞ΕͨσʔλͷຊͬΆ͞Λఆ͢Δ 3.ຊͬΆ͘ͳ͍߹͍Λޡࠩͱͯ͠ੜثʹֶशͤ͞Δ 4.ࣝผثಉ࣌ʹຊͬΆ͞ͷఆΛֶश͢Δ Ҏ্Λ܁Γฦ͢ͱͦΕͬΆ͍σʔλ͕ੜ͞ΕΔ 40/57
ੜϞσϧͷԠ༻ • ఏҊख๏ : SRCNNʴੜϞσϧ • ࣮ͳ༧ʴΑΓߴͳωοτϫʔΫ͔ΒͷΞυόΠε • ΞϧΰϦζϜ •
SRCNNͷޡࠩʹࣝผثͷఆΛՃࢉ͢Δ 41/57
SRCNNʴGANͷޮՌ • SRCNNݻ༗ͷบ͕Ωϟϯηϧ͞ΕΔ • ਓͷ͔Βݟͨࣗવ͞ͷվળ • पಛੑͷվળ • ୯ମͷωοτϫʔΫͰࠔͳֶश͕Մೳ •
ωοτϫʔΫͷදݱྗͷݶքΛҾ͖ग़͢ 42/57
SRCNNʴGANͷ • ֶशʹ͕͔͔࣌ؒ͘͢͝Δ • ࣝผثͷֶशͷ΄͏͕ॏ͍ • ࣝผثͷஅͰੜث͕ߟ͑͜ΉͷͰऩଋͮ͠Β͍ • ࣝผثͷੑೳͰը࣭ͷ͕ܾ·Δ •
ղ૾ʹ͔͔Δ࣌ؒΛֶशʹసՇ͍ͯ͠Δ 43/57
SRCNNʴGANͷޮՌ 44/57
SRCNNʴGANͷޮՌ 45/57
SRCNNʴGANͷ෭࡞༻ • ߴपΛେ෯ʹΔͨΊɺϦοϓϧ͕ൃੜ͍͢͠ • ϦοϓϧܰݮʹࣝผثʹϦοϓϧΛݟഁΒͤ͞Δ • ࣝผثੜثΑΓݡ͘͢Δ • ࣝผثֶशϑΣʔζʹ͔͠ΘΕͳ͍ •
ࣝผثͷॲཧ͕ͯ͘ղ૾ॲཧʹແؔ 46/57
ͱԠ༻ 47/57
SRCNNͷ • ωοτϫʔΫ͕ಛఆͷλεΫɺը૾δϟϯϧʹґଘ͢Δ • ΠϥετͰֶशͨ͠ωοτϫʔΫΛࣸਅͰ͏ͱഁ͢Δ • ը૾δϟϯϧ͝ͱʹωοτϫʔΫΛมߋ͢Δඞཁ͋Δ 48/57
SRCNNͷ • ΠϥετϨʔγϣϯͱࣸਅͷҧ͍ • Πϥετཧঢ়ଶͷը૾Λ༻ҙ͢Δͷ͕ඇৗʹ༰қ • ͦͷͨΊSRCNNͷαϯϓϧը૾Πϥετ͕ଟ͍ • ཧͷը૾ΛࡱӨͰ͖ΔΧϝϥ࣮ࡏ͠ͳ͍ 49/57
ࣸਅͷԠ༻ • ཧͷࣸਅը૾࡞ • ΧϝϥϝʔΧʔͰͳ͚Εແཧ • झຯͰΔ͜ͱͰͳ͍ • ࣗఘΊͨ 50/57
ࣸਅͷԠ༻ • ཧը૾ΛྼԽͤͯ͞ղ૾લը૾ͱ͢Δ • ཧը૾Λղ૾લͷը૾ʹม͢Δ • JPEGͰྼԽͤ͞Δ • ϊΠζΛՃ͢Δ 51/57
ࣸਅͷԠ༻ • पಛੑΛσδλϧϑΟϧλͰྼԽͤ͞Δ • ϨϯζͳͲΧϝϥͷಛੑʹґଘ͢Δ • ղ૾͍ͨ͠ΧϝϥͷϨϯζಛੑΛܭଌ͢Δ • ଌఆͨ͠ಛੑΛσδλϧϑΟϧλͰ࠶ݱ͢Δ •
ۚଐεϦοτࡱӨʁ • ϗϫΠτϊΠζࡱӨʁ 52/57
ੑೳධՁ 53/57
ൃදख๏ͷੑೳධՁ 54/57
ൃදख๏ͷੑೳධՁ • ը࣭ධՁʹPSNR͕Α͘ΘΕΔ • ࠷େըૉʹରͯ͠ޡ͕ࠩͲΕ͙Β͍͋Δ͔ • ͕େ͖͍΄Ͳը࣭͕Α͍ • • 55/57
ൃදख๏ͷੑೳධՁ • SRCNN+GANఆྔతͳੑೳత͕ѱ͍ • SRCNN+GANੜϞσϧͳͷͰৄࡉ Ͷͭ 56/57
͝ਗ਼ௌ͋Γ͕ͱ͏͍͟͝·ͨ͠ Կ͔࣭ʁ 57/57