Upgrade to Pro — share decks privately, control downloads, hide ads and more …

類似画像検索の裏側 - 機械学習と近似近傍探索 - / similar_image_searc...

monochromegane
September 12, 2018

類似画像検索の裏側 - 機械学習と近似近傍探索 - / similar_image_search_inside

ペパボ研究所 in da house #1

monochromegane

September 12, 2018
Tweet

More Decks by monochromegane

Other Decks in Technology

Transcript

  1. - ػցֶशͱۙࣅۙ๣୳ࡧ - ࡾ୐༔հ / Pepabo R&D Institute, GMO Pepabo,

    Inc. 2018.09.11 ϖύϘݚڀॴ in da house #1 ྨࣅը૾ݕࡧͷཪଆ
  2. • ৘ใ୳ࡧϓϩηε͸γεςϜଆͷ ٕज़ৄࡉ͚ͩͰ͸ͳ͘ɺ͜ͷϓϩ ηεΛۦಈ͢ΔओମͰ͋Δར༻ऀ ͕ଘࡏ͢Δ • ར༻ऀαΠυΛத৺ͱͨ͠৘ใ୳ ࡧϓϩηεϞσϧͷઌߦݚڀʹΑ Γɺ৘ใཁٻ͸ɺ༷ʑͳจ຺ʹΑ ΓมԽ͍ͯ͘͜͠ͱ͕Θ͔͍ͬͯ

    Δ 5 ͳΊΒ͔ͳϚονϯάʹ޲͚ͯ ৘ใཁٻΛऔΓרٕ͘ज़ͱϓϩηεϞσϧؔ࿈ਤ จ຺ʹΑΓ࠷దͳԠ౴͕มԽ͢ΔͷͰ͋Ε͹ɺ ٕज़ؒͰͷ༏ҐੑධՁͰ͸ͳ͘ɺ ঢ়گʹԠͨ͡બ୒͕ྑ͍ͷͰ͸ͳ͍͔
  3. • m࣍ݩͷϕΫτϧxΛn࣍ݩͷϕΫτϧy΁ࣸ૾͢Δؔ਺fΛਪఆ͢Δֶशख๏ 10 χϡʔϥϧωοτϫʔΫ: Ϟσϧ x1 x2 xm b W

    y1 y2 yn 1 2 o1 = σ( m ∑ i=0 w1i xi + b1 ) h 3 o = σ(Wx + b) w11 w12 . . w1m w21 w22 . . w2m . . wh1 wh2 . . whm x1 x2 . . xm + b1 b2 . . bh x f y h wh1 wh2 x1 x2 ೖྗ͝ͱʹॏΈXΛ৐ࢉ όΠΞε ͨ͠΋ͷΛ׆ੑԽؔ਺ʹ௨͢ શϊʔυʹର͢Δॲཧ͸ߦྻͱͯ͠ૢ࡞Ͱ͖Δ
  4. 11 χϡʔϥϧωοτϫʔΫ: ֶश x1 x2 xm y1 y2 yn x

    f y • m࣍ݩͷϕΫτϧxΛn࣍ݩͷϕΫτϧy΁ࣸ૾͢Δؔ਺fΛਪఆ͢Δֶशख๏ t tn t2 t1 W(1) W(2) b(1) b(2) ✓(i+1) = ✓(i) ↵rEk E = 1 2 X n (yn tn)2 E = X n tn ln yn rEk = ( @Ek @✓1 , .. @Ek @✓V ) ग़ྗͱਖ਼ղͷޡࠩΛද͢ଛࣦؔ਺Λఆٛ͢Δɻ ೋ৐࿨ޡࠩʢࠨʣɺަࠩΤϯτϩϐʔޡࠩʢӈʣ ଛࣦؔ਺ʹର͢Δ֤ύϥϝλͷภඍ෼ͷ஋ͷू·Γʢޯ഑ʣΛ༻ ͍ͯଛࣦؔ਺ͷ஋͕খ͘͞ͳΔΑ͏ʹύϥϝλΛߋ৽͢Δ͜ͱΛ ޯ഑߱Լ๏ͱݺͿɻಛʹҰ෦ͷ݁ՌͷΈΛར༻͢Δ֬཰తޯ഑߱ Լ๏͕Α͘༻͍ΒΕΔɻ Αͬͯޯ഑͕ফ͑ͳ͍Α͏ͳͳΊΒ͔ͳ׆ੑԽؔ਺͕޷·ΕΔɻ ·ͨɺ֤ύϥϝλͷภඍ෼ΛݸผʹٻΊΔͷͰ͸ͳ͘ɺχϡʔϥ ϧωοτϫʔΫΛදؔ͢਺GΛ߹੒ؔ਺ͱݟཱͯΔ͜ͱͰɺ্ྲྀ ͷޡࠩͱࣗ਎ͷೖྗ஋ͷΈΛ࢖ͬͯܭࢉྔΛ཈͑ͳ͕Βޮ཰తʹ ޯ഑ΛٻΊΔख๏Λޡࠩٯ఻೻๏ͱݺͿɻ
  5. ৞ΈࠐΈχϡʔϥϧωοτϫʔΫ 13        

                      ੵ࿨ԋࢉ ৞ΈࠐΈ                  ࠷େ஋ ೖྗσʔλʹରͯ͠ੵ࿨ԋࢉΛߦ͏ϑΟϧλΛద༻͠ɺ ಛ௃Ϛοϓͱͯ͠ग़ྗ͢Δɻۭؒ৘ใΛߟྀͰ͖Δɻ ࠷దͳϑΟϧλͷॏΈ͸ֶशʹΑͬͯ֫ಘ͢Δɻ • ۭؒత৘ใΛߟྀͨ͠χϡʔϥϧωοτϫʔΫ ϓʔϦϯά ೖྗσʔλʹରۭͯؒ͠ͷू໿Λߦ͏ϑΟϧλΛద༻ ͢Δɻ࠷େ஋΍ฏۉ஋Λར༻͢ΔͷͰֶश͕ෆཁɻ ࡉ͔ͳҐஔมԽʹର͢Δؤڧੑʹߩݙ͢Δɻ ಛ௃நग़ث ࣝผث
  6. 14

  7. 4QPUJGZBOOPZ w "QQSPYJNBUF/FBSFTU /FJHICPST0I:FBI w $ ϥΠϒϥϦͱ1ZUIPO౳ͷό ΠϯσΟϯάΛఏڙ w ϥϯμϜαϯϓϦϯάͨ͠ೋ఺Λ

    ݩʹۭؒΛೋ෼ׂΛ܁Γฦͯ͠໦ ߏ଄Λෳ਺ߏங w ୳ࡧ࣌͸෼ׂϕΫτϧͰৼΓ෼͚
  8. • ಛ௃ྔม׵ • ݸʑͷը૾σʔλͷྨࣅੑΛఆྔతʹൺֱՄೳͳܗࣜʹม׵͢Δ
 ‎ ఆੑతͳධՁʹ͍ۙ͠ಛ௃ྔม׵ػߏͱͯ͠ͷDeep CNN
 ➕ ֶशͱ༧ଌΛॲཧ͢ΔͨΊͷ֦ுੑͱαʔϏε͔Βͷಠཱੑ •

    ۙ๣୳ࡧ • ม׵ͯ͠ಘΒΕͨಛ௃ྔͲ͏͠Λൺֱ͠ɼྨࣅ͢Δू߹Λಛఆ͢Δ
 ‎ ਫ਼౓ͱ଎౓Λཱ྆͢ΔANN(ۙࣅۙ๣୳ࡧ)
 ➕ σʔλͷू໿ͱαʔϏε͔Βͷಠཱੑ 20 ྨࣅը૾ݕࡧΛࢧ͑Δٕज़
  9. Similar images search system using ANN 21 Feature Similar items

    ANN [2048]float64 query response Deep CNN index Features [n][2048]float64 Deep CNN register find similar features
  10. • ϩά΍DBͳͲͷαʔϏεࢿ࢈ͱ࿈ܞͰ͖Δ
 ‎ ೖग़ྗ͕Cloud Storageܦ༝ • ൺֱత༰қʹϞσϧͷߏஙͱࢼߦ͕ߦ͑Δ
 ‎ TensorFlowΛ࠾༻ •

    ֶश݁ՌΛར༻͢ΔͨΊͷखஈͱͯ͠APIΛఏڙ͢Δ
 ‎ ΦϯϥΠϯ༧ଌαʔϏεʹΑΓϞσϧͷAPIԽ • ্هͷ࢓૊Έ͕εέʔϥϒϧͰ͋Δ͜ͱ
 ‎ ෼ࢄܕτϨʔχϯάΠϯϑϥͱෛՙ෼ࢄαʔϏεͷ࿈ܞ 22 ػցֶशج൫ͱͯ͠ͷGoogle Cloud ML
  11. mruby_annoy on ngx_mruby 26 class NNS def call(env) params =

    env['QUERY_STRING'].split('&') .map {|kv| kv.split('=') }.to_h category_id = params['category_id'].to_i product_id = params['product_id'].to_i limit = (params['limit'] || 10).to_i userdata = Userdata.new "annoy_data_key" annoy = userdata.send("category_#{category_id}") return not_found unless annoy nns = annoy.get_nns_by_item(product_id, limit) [200, content_type, [nns.to_json]] end private def not_found return [404, content_type, [{'error' => 'not_found'}.to_json]] end def content_type {'Content-Type' => 'application/json;charset=utf-8'} end end run NNS.new
  12. 28 monochromegane/gannoy(-yahoo/NGT) # Add item $ curl \ ’http://localhost:1323/databases/hoge/features/100’ \

    -H "Content-type: application/json” \ -X PUT \ -d '{"features": [1.0, 0.5, 0.2,..]}’ # Search $ curl \ ’http://localhost:1323/search?database=hoge&id=100’
  13. ྨࣅը૾ݕࡧ 29 Nyah products#show product_id nearest products products#update Gannoy Object

    Storage GCP data to feature vectorizer by Inception-V3 ˞ۙࣅۙ๣୳ࡧ࣌ʹେ෦෼ͷ ΠϯσοΫε΁ͷΞΫηε͕ ൃੜ͢ΔͨΊ࣮༻తͳ଎౓Λ ಘΔͨΊʹ͸σʔλϕʔεϑΝ Πϧ͕શͯϖʔδΩϟογϡ ʹࡌΔαΠζͷϝϞϦ͕ඞཁ • ݕࡧ࣌͸࡞඼IDΛݩʹొ࿥͞Εͨಛ௃ྔͷۙ๣ू߹Λฦ٫͢Δ • ߋ৽࣌͸ߋ৽ޙͷಛ௃ྔΛҰ࣌తʹอଘɼఆظతʹࠩ෼൓өͯ͠੾Γସ͑
  14. • ಛ௃ྔม׵ • ݸʑͷը૾σʔλͷྨࣅੑΛఆྔతʹൺֱՄೳͳܗࣜʹม׵͢Δ
 ‎ ఆੑతͳධՁʹ͍ۙ͠ಛ௃ྔม׵ػߏͱͯ͠ͷDeep CNN
 ↪︎ αʔϏεʹಛԽͨ͠”ྨࣅੑ”Λ֫ಘ͢Δ •

    ۙ๣୳ࡧ • ม׵ͯ͠ಘΒΕͨಛ௃ྔͲ͏͠Λൺֱ͠ɼྨࣅ͢Δू߹Λಛఆ͢Δ
 ‎ ਫ਼౓ͱ଎౓Λཱ྆͢ΔANN(ۙࣅۙ๣୳ࡧ)
 ↪︎ ΑΓߴ଎Ͱߴਫ਼౓ͳANN 34 ྨࣅը૾ݕࡧΛࢧ͑Δٕज़
  15. • ΫΤϦͱߴ࣍ݩϕΫτϧू߹Λ೚ҙͷ࣍ݩ਺Ͱ౳෼ͨ͠෦෼ϕΫτϧ୯ҐͰฒ ߦʹۙ๣୳ࡧͨ݁͠Ռͷ࿨ू߹Ͱ͋Δۙ๣ީิ͔Βɼ࠶౓ۙ๣୳ࡧΛߦ͏ɽ 37 ఏҊख๏ (଎౓໘) R@ R@ R@ 9@

    9@ 9@ /SFDPSET // R@ Y@O Y㱨9@ // R@ Y@O Y㱨9@ // R@ Y@O Y㱨9@ \   ^ \   ^ \   ^ BSHNJOE R Y Y㱨\    ^ 㱮 㱮 ෼ղલ ෼ղޙ ᶃ௿࣍ݩۭؒͷฒߦͨۙ͠๣୳ࡧ ᶄݻఆ਺ͷۙ๣ީิͷू໿ ᶅۙ๣ީิͷઢܗ୳ࡧ ᶃ ᶄ ᶅ ଎౓վળ ᶃ ᶄ ᶅ 2VFSZ
  16. 39 Sanny: ఏҊख๏ͷ࣮૷ 4BOOZ 4BOOZ 4BOOZ // // 㱮 //

    // ᶃ ᶄ ᶅ 2VFSZ "MHPSJTN "MHPSJTN "MHPSJTN • ΫΤϦฒͼʹ୳ࡧର৅σʔλͷ೚ҙ࣍ݩ΁ͷ౳෼ͱ݁Ռͷू໿Λ୲౰͢Δ • ෦෼ϕΫτϧͷۙ๣୳ࡧΞϧΰϦζϜ͸໰Θͳ͍ • ෦෼ϕΫτϧ͝ͱͷ୳ࡧॲཧ͸ಠཱͷͨΊ෼ࢄߏ੒͕Մೳ