続・絵を読む技術 Pythonで読むイラストの心理戦略 / The Art of Reading Illustrations 2nd

PyCon JP 2022 (2022/10/15) @Hirosaji @Hirosaji_ez
https://2022.pycon.jp/timetable?id=JWM39L

=====
Title (English): The Art of Reading Illustrations 2nd: Psychological Strategies for Illustration read in Python

Transcript

1. 1Z$PO
   +1
   
    ଓɾֆΛಡΉٕज़
   1ZUIPOͰಡΉΠϥετͷ৺ཧઓུ )JSPTBKJ
   !IJSPTBKJ
   ʗ
   ͻΖ͞͡
   !IJSPTBKJ@F[
2. ͸͡Ίʹ
3. ଓฤͰ͕͢ɺ୯ಠͰ΋ָ͠ΊΔ಺༰Ͱ͢ɻ΋ָ͠͠ΊͨΒɺڈ೥ͷൃද΋νΣοΫͯ͠Έ͍ͯͩ͘͞ɻ ͜ͷߨԋ͸ଓฤͰ͢ ࡢ೥ղઆ͖͠Εͳ͔ͬͨ಺༰Λਂ۷Γ͠ɺΑΓײੑతͳઓུΛඥղ͖·͢ ࠓ ճ
4. ʮͻΖ͞͡
   
   )JSPTBKJʯͱ͍͏໊લͰ׆ಈ͢Δਓɻେ޷͖ͳΠϥετʹғ·Εɺ޾ͤͳ೔ʑΛૹ͍ͬͯΔɻ ࣾձਓֆඳ͖
   ͻΖ͞͡ʢ!IJSPTBKJ@F[ʣ ɾ1ZUIPOྺ̒೥͘Β͍
   ɾΠϥετΛ؍Δͷ͕޷͖ ɾσδλϧֆࢣ̏೥໨
   ɾΠϥετΛඳ͘ͷ͕޷͖ ͜ͷϓϨθϯΛ͢Δਓ ޏΘΕ8FCΤϯδχΞ
   )JSPTBKJʢ!IJSPTBKJʣ
5. ͜ͷ̎ϲ݄ͰɺֆࢣΛऔΓר͘؀ڥ͸େ͖͘มΘͬͨɻͦͯ͠ࠓ΋ɺֆࢣ͸ա౉ظʹཱ͍ͬͯΔɻ ·ͣ͸ɺ͜ͷ࿩୊ʹ৮Εͳ͚Ε͹… ͍·ɺ"*ֆࢣͷ੎͍͕ࢭ·Βͳ͍ɻ l"*͕ֆΛඳ͘ʁ
   ਐԽ͢Δը૾ੜ੒"*ͷ࠷લઢ
   c
   /),
   l
   ΑΓ ೥݄
   
   
   ը૾ੜ੒"*͕୆಄ ೥݄຤
   
   ֆฑֶश"*͕೾໲ ೥݄಄
   
   /PWFM"*͕୆಄ lΠϥετϨʔλʔͷݸੑΛֶΜͰֆΛlແݶੜ੒z͢Δ"*αʔϏ
   c
   *5NFEJB
   l
   ΑΓ l༷ʑͳݒ೦΍໰୊Λ๊͑ͭͭ΋ʮ͓ֆ͔͖"*ʯͷਐԽ͸ࢭ·Βͣc
   :BIPPχϡʔε
   l
   ΑΓ
6. ؆୯ͳϑϨʔζ΍ϥϑ͕͋Ε͹ɺ୭Ͱ΋ϓϩڃͷΠϥετΛੜ੒Ͱ͖Δ"*ֆࢣɻଟ͘ͷֆࢣ͸ಈ༳͢Δ͕ ͍·ɺ"*ֆࢣͷ੎͍͕ࢭ·Βͳ͍ɻ "*ֆࢣͷ͍͢͝ͱ͜Ζ 
   ্ख͍ֆ͕͙͢ඳ͚Δ 
   ΤϞ͍ֆ͕͙͢ඳ͚Δ lʮͱΜͰ΋ͳ͘ϋΠΫΦϦςΟʔʯ
   ࿩୊ͷը૾"*ʮ/PWFM
   "*ʯͰͻͨ͢Βೋ࣍ݩඒগঁͱඒগ೥Λੜ੒ͯ͠Έͨ
   c
   *5NFEJB
   l
   ΑΓ AIʹֆࢣͷ࢓ࣄΛୣΘΕΔ... ͱ୰͘ਓ΋ ·ͣ͸ɺ͜ͷ࿩୊ʹ৮Εͳ͚Ε͹…
7. ͋͘·Ͱ΋ɺֆͷ্ख͞͸ֆࢣͷٕೳͷҰͭɻֆ্͕ख͍ͱ͍͏ཧ༝͚ͩͰɺϑΝϯʹͳΔ༁Ͱ͸ͳ͍ɻ Q. ֆࢣ͸ֆ্͕ख͚Ε͹͍͍ͷʁ lʲϑΥϩϫʔ਺ʹըྗ
   ͳͷʁʳ͜ͷ౴͕͑Θ͔ͬͯΔਓ͸ɺΊͪΌͪ͘Ό੒௕͠·͢ʂz
   
   ম·ΏΔͷ͓ֆ͔͖ͪΌΜͶΔ
   c
   :PVUVCFʢʣl
   ΑΓ "ɹॏཁͳͷ͸ɺϑΝϯΛت͹ͤΔ͜ͱɻ
   χʔζʹԠ͑Δ͜ͱͰɺϑΝϯ͸تͿɻֆͷ্ख͞͸χʔζʹԠ͑Δखஈɻ
8. ࠓޙ͸ɺ"*ͷීٴͰΠϥετͷΫΦϦςΟ͸શମతʹ্͕Δɻͦͯ͠ɺֆࢣͷϒϥϯυԽ͕͞ΒʹਐΉɻ Q. AIֆࢣͷొ৔ͰԿ͕มΘΔ͔ʁ lෆ͕͍҆ͬͺ͍ʜ😭৽ਓֆࢣ͸"*ʹͭͿ͞ΕΔʁʲ3BEJP
   $MPTFUʳσΟʔϓϒϦβʔυ
   
   ΕͰ͌͘Ζz
   
   σΟʔϓϒϦβʔυ
   c
   :PVUVCFʢʣl
   ΑΓ "ɹ"*͸ΠϥετΛ୹࣌ؒͰߴΫΦϦςΟʹ͢ΔิॿπʔϧʹͳΔɻ
   ͦͯ͠Πϥετ͸ʮͲΜͳֆࢣ͕ඳ͍͔ͨʯ͕ΑΓॏཁࢹ͞ΕΔͩΖ͏ɻ
9. "*ΛֆΛ্ख͘ඳͨ͘Ίͷಓ۩ͱͯ͠࢖͍ͭͭɺΑΓޮ཰తʹϑΝϯͷχʔζʹԠ͑ΔಓΛ୳Γଓ͚Α͏ɻ Q. ͜Ε͔Βֆࢣ͸Ͳ͏͢Δ΂͖ʁ "ɹֆΛ্ख͘ඳͨ͘Ίʹ"*Λ׆༻͢Δͷ͸΋ͪΖΜɺ
   ΋ͬͱ৭ΜͳՄೳੑʹ໨Λ޲͚Δ΂͖ɻ ͻ Ζ ͞ ͡ Ұॹʹ
   χʔζʹԠ͑ΔઓུΛߟ͑Αʂ θ ώ
10. ͔͜͜Βຊ୊
11. "*ͱڞʹߟ͑Α͏ͱ͍ͬͨઓུɻ͜ͷϓϨθϯͰ͸ɺΠϥετͷ৺ཧઓུΛ1ZUIPOΛަ͑ͯղઆ͢Δɻ ͜ͷϓϨθϯͷझࢫ Πϥετͷ৺ཧઓུΛ஌Δ
12. ͪͳΈʹલճͷൃදͰ͸ɺઓུΛʮֆࢣͷૂ͍ʯͱݴ͍׵͑ͯղઆͨ͠ɻ ͜ͷϓϨθϯͷझࢫ Πϥετͷ৺ཧઓུΛ஌Δ ֆࢣͷૂ͍ 
13. ࠓճͷ࿩͸୯ಠͰ΋ָ͠ΊΔ͕ɺલճͷൃදͱͷ஍ଓ͖ͳͷͰɺ؆୯ʹҐஔ෇͚ΛৼΓฦΔɻ ͜ͷϓϨθϯͷझࢫ Πϥετͷ৺ཧઓུΛ஌Δ ֆࢣͷૂ͍  Π લ ճ · Ͱ ͷ ͋ Β ͢ ͡ ͥ Μ ͔ ͍
14. લճ͸ɺΠϥετͷઓུΛ̎ͭʹେผͯ͠ղઆɻͦͷதͰʮͳʹΛ఻͑Δ͔ʯ͸ߏ੒ཁૉͷ঺հʹཹ·ͬͨɻ લ ճ · Ͱ ͷ ͋ Β ͢ ͡ ͥ Μ ͔ ͍ ֆࢣͷૂ͍ Ͳ͜Λ఻͑Δ͔ ͳʹΛ఻͑Δ͔ γΣΠϓ ϥΠϯ ৭ Πϥετͷ৺ཧઓུͷҐஔ෇͚ ޫʢ໌౓ʣ ΩϟϥΫλʔ ʜ ߏਤͷࠎ૊ΈΛߏ੒ ʜ ഑৭όϥϯεΛ౷੍ ʜ ʜ য఺ͷҹ৅Λ੍ޚ ײ৘໘Λࢧ഑ Τ Ϟ Έ ʜ ʢະղઆʣ ࡁ
15. ࠓճ͸ͦΜͳΠϥετͷߏ੒ཁૉͷதͰ΋ɺ৺ཧʹಇ̏ͭ͘ͷཁૉΛऔΓ্͛ͯਂ۷Γ͢Δɻ લ ճ · Ͱ ͷ ͋ Β ͢ ͡ ͥ Μ ͔ ͍ ֆࢣͷૂ͍ Ͳ͜Λ఻͑Δ͔ ͳʹΛ఻͑Δ͔ γΣΠϓ ϥΠϯ ৭ ޫʢ໌౓ʣ ΩϟϥΫλʔ ৺ཧʹޮ͘
    ̏ཁૉ ࠓճͷ
    ਂ۷Γର৅
    🔎 Πϥετͷ৺ཧઓུͷҐஔ෇͚ ࡁ
16. ઓུϐϥϛουͰ੔ཧ͢Δͱ͜ͷ௨ΓɻҾ͖ग़͍ͨ͠ײ৘΍৘ಈʹ߹Θͤͯ৺ཧઓུΛඳ͚ΔΑ͏ʹͳΖ͏ɻ Πϥετͷ৺ཧઓུϐϥϛου ໨త ઓུ ઓज़ ΠϥετΛ؍Δਓͷײ৘΍৘ಈΛҾ͖ग़͢ ޮՌతͳΩϟϥΫλʔ΍ޫʗ৭ͷํ਑ΛબͿ બΜͩํ਑͔Β஌ࣝ΍࣮ײΛ΋ͱʹඳ͘ ୡ੒͍ͨ͠ΰʔϧ ໨తΛୡ੒͢ΔγφϦΦ ઓུΛୡ੒͢ΔΞΫγϣϯ
17. ࠓճͷϓϨθϯͷྲྀΕ͸ͪ͜ΒɻͦΕͧΕͷ৺ཧઓུΛɺదٓ1ZUIPOεΫϦϓτΛަ͑ͳ͕Βղઆ͢Δɻ આ໌͢ΔྲྀΕ 
    ޫͱ৭ͷ৺ཧઓུ ɾશਓྨʹޮ͘ΩϟϥΫλʔͷັྗΛ୳Δ
    ɾ1ZUIPOͰΩϟϥΫλʔͷັྗΛݕग़͢Δ ɾ഑৭ʹΑΔίϯηϓτͱృΓʹΑΔͩ͜ΘΓΛ஌Δ
    ɾ1ZUIPOͰίϯηϓτͱͩ͜ΘΓΛ୳Δ 
    ΩϟϥΫλʔͷ৺ཧઓུ ͸͡Ίʹ ࡁ
18. ΩϟϥΫλʔͷ৺ཧઓུ ̍
19. ΩϟϥΫλʔ͕ొ৔͢ΔΠϥετʹ͸ɺେ͖̎ͭ͘ͷझࢫ͕͋Δɻ̎ͭͷझࢫ͕ڞଘ͢Δ͜ͱ΋ଟ͍͕ ΩϟϥΫλʔΠϥετͷ̎େझࢫ  ετʔϦʔ΍৔໘
    Λ఻͑Δ ΩϟϥΫλʔͷັྗ
    Λ఻͑Δ 
20. ࠓճ͸લऀͷʮΩϟϥΫλʔͷັྗΛ఻͑ΔʯʹղઆΛߜΔʢޙऀ͸ΩϟϥҎ֎ͷཁૉ͕ෳࡶʹབྷΉͨΊʣ ΩϟϥΫλʔΠϥετͷ̎େझࢫ  ετʔϦʔ΍৔໘
    Λ఻͑Δ ΩϟϥΫλʔͷັྗ
    Λ఻͑Δ  Ω ϥ ͕ ओ ໾ Ω ϥ ͸ આ ໌ ࡐ ྉ
21. ΩϟϥΫλʔͷັྗ͕఻ΘΔ৚݅͸ɺϙʔζͱද৘ͰɺΩϟϥΫλʔੑ͕෼͔Γ΍͘͢දݱͰ͖͍ͯΔ͜ͱɻ ັྗతͳΩϟϥΫλʔΠϥετͷ৚݅ ΩϟϥΫλʔੑ
    ͕Θ͔Γ΍͍͢͜ͱ ΩϟϥΫλʔੑ ͦͷΩϟϥΫλʔͷ࣋ͪຯͱͳΔੑ֨΍ಛ௃ͷ͜ͱɻ
    ӳޠͰ͍͏
    lQFSTPOBMJUZz
    ͷχϡΞϯε͕͍ۙɻ Πϥετɿ© ͻΖ͞͡ʢʮ΢Ϛ່
    ϓϦςΟʔμʔϏʔ
    ೋ࣍૑࡞ΨΠυϥΠϯʯ९कʣ lΩϟϥΫλʔΠϥετͷҾ͖ग़͠Λ૿΍͢ϙʔζͱද৘ͷԋग़ςΫχοΫ
    
    ΧϦϚϦΧ
    c
    ᠳӭࣾʢʣl
    ΑΓ ϙʔζ ද৘ ʴ Ͱදݱ ΩϟϥΫλʔɿΠΫϊσΟΫλεʢ© ΢Ϛ່
    ϓϦςΟʔμʔϏʔ
    
    $ZHBNFTʣ
22. ΩϟϥΫλʔੑʢϙʔζʗද৘ʣ͸ɺ఻͍͑ͨײ৘΍γνϡΤʔγϣϯΛ΋ͱʹࢼߦࡨޡͯ͠σβΠϯ͢Δɻ Q. ϙʔζʗද৘͸Ͳ͏ܾ·Δ͔ lʲΠϥετϝΠΩϯάʳߏਤΛܾΊΔ࣌ʹߟ͍͑ͯΔ͜ͱʲ΢Ϛ່ϚϠϊτοϓΨϯʳz
    
    ֆ༿·͠ΖͷͪΌΜͶΔ
    c
    :PVUVCFʢʣl
    ΑΓ "ɹશͯΦʔμʔϝΠυɻ
    ඳ͘ΩϟϥΫλʔΛܾΊɺදݱ͍ͨ͜͠ͱΛܾΊɺ࢓্͛Δֆͷߏ૝͢Δɻ ΩϟϥΫλʔɿϚϠϊτοϓΨϯʢ© ΢Ϛ່
    ϓϦςΟʔμʔϏʔ
    
    $ZHBNFTʣ :PVUVCFಈըɿ© ֆ༿·͠Ζ
23. ΩϟϥΫλʔੑʢϙʔζʗද৘ʣ͸ɺ఻͍͑ͨײ৘΍γνϡΤʔγϣϯΛ΋ͱʹࢼߦࡨޡͯ͠σβΠϯ͢Δɻ Q. ϙʔζʗද৘͸Ͳ͏ܾ·Δ͔ lʲΠϥετϝΠΩϯάʳߏਤΛܾΊΔ࣌ʹߟ͍͑ͯΔ͜ͱʲ΢Ϛ່ϚϠϊτοϓΨϯʳz
    
    ֆ༿·͠ΖͷͪΌΜͶΔ
    c
    :PVUVCFʢʣl
    ΑΓ "
    શͯΦʔμʔϝΠυɻ
    ɹ
    ඳ͘ΩϟϥΫλʔΛܾΊɺදݱ͍ͨ͜͠ͱΛܾΊɺ࢓্͛Δֆͷߏ૝͢Δɻ ౎౓ΦʔμʔϝΠυͱ͸͍͑
    ఆੴ͸Կ͔͋Δ͸ͣ 🤔
24. ΩϟϥΫλʔͷັྗΛҾ͖ग़͢ఆੴ͸͋ΔɻதͰ΋ࠓճ͸ɺશਓྨʹޮ͍͘͢͝ఆੴΛ̎ͭ঺հ͢Δɻ ັྗతͳΩϟϥΫλʔͷఆੴ ᶃ
    ίϯτϥϙετ ࠷΋ݪ࢝తͳఆੴ ࠷΋୅දతͳఆੴ ᶄ
    ੑઓུ
25. ఆੴͷҰͭ͸ɺίϯτϥϙετɻلݩલɺݹ୅ΪϦγΞ࣌୅ͷூࠁͰൃ໌͞Εɺࠓ΋ड͚ܧ͕ΕΔɻ ΩϟϥΫλʔͷັྗΛҾ͖ग़͢ఆੴᶃɿίϯτϥϙετ ίϯτϥϙετͱ͸ +PIO
    4JOHFS
    4BSHFOU
    r
    c
    QVCMJD
    EPNBJO 4BOESP
    #PUUJDFMMJ
    r
    c
    QVCMJD
    EPNBJO 5IF
    CJSUI
    PG
    7FOVT .BEBNF
    9 .JDIFMBOHFMP
    r
    c
    $$
    #:4"
     %BWJE ίϯτϥϙετ͸ɺ
    ମॏͷଟ͕͘ย٭ʹ͔͔ͬͨ࢟੎ͷ͜ͱɻ
    ༂ಈײΛੜΉ࢟੎ͱͯ͠لݩલ̐ੈلࠒʹൃ໌ɻ
    ݱ୅ʹ΋޿͘ड͚ܧ͕Ε͍ͯΔɻ lιοΧͷඒज़ղ๤ֶϊʔτ
    
    ιΫδϣϯώϣϯ
    c
    ΦʔϜࣾʢʣl
    ଞΑΓ
26. ͳͥίϯτϥϙετ͕ΩϟϥΫλʔΛັྗతʹ͢Δͷ͔ɻ·ͣ͸ɺͦͷҰͭͷཧ༝Λղઆ͢Δɻ lιοΧͷඒज़ղ๤ֶϊʔτ
    
    ιΫδϣϯώϣϯ
    c
    ΦʔϜࣾʢʣl
    ଞΑΓ ίϯτϥϙετͷ࿦ཧͦͷ̍ɿࣗવͱΩϟϥΫλʔੑ͕ݱΕΔ ΩϟϥΫλʔͷັྗΛҾ͖ग़͢ఆੴᶃɿίϯτϥϙετ ɾย଍ʹମॏ͕͔͔ͬͨ࢟੎͸ɺ
    ɹߦಈͷ్தͰෆ҆ఆͳঢ়ଶɻ ɾମͷॏ৺ʹζϨ͕ੜ͡ɺ
    ɹແҙࣝతʹ಄ɾମɾ྆ख଍ͰόϥϯεΛऔΔɻ
27. ย଍ʹମॏ͕͔͔Δͱࠎ൫͕܏͖ɺͦΕʹ࿈ΕΒΕͯ਎ମதͷ෦ҐͰόϥϯε͕औΒΕΔʢཱͪ௚Γ൓Ԡʣ lιοΧͷඒज़ղ๤ֶϊʔτ
    
    ιΫδϣϯώϣϯ
    c
    ΦʔϜࣾʢʣl
    ଞΑΓ ίϯτϥϙετͷ࿦ཧͦͷ̍ɿࣗવͱΩϟϥΫλʔੑ͕ݱΕΔ ΩϟϥΫλʔͷັྗΛҾ͖ग़͢ఆੴᶃɿίϯτϥϙετ ɾย଍ʹମॏ͕͔͔ͬͨ࢟੎͸ɺ
    ɹߦಈͷ్தͰෆ҆ఆͳঢ়ଶɻ ɾମͷॏ৺ʹζϨ͕ੜ͡ɺ
    ɹແҙࣝతʹ಄ɾମɾ྆ख଍ͰόϥϯεΛऔΔɻ
28. ͭ·Γɺશ਎ͰͷδΣενϟʔ͕ൃੜ͠ɺߦಈ΍ҙࢥɺͻ͍ͯ͸ΩϟϥΫλʔੑ͕෼͔Γ΍͍͢ঢ়ଶʹͳΔɻ lιοΧͷඒज़ղ๤ֶϊʔτ
    
    ιΫδϣϯώϣϯ
    c
    ΦʔϜࣾʢʣl
    ଞΑΓ ίϯτϥϙετͷ࿦ཧͦͷ̍ɿࣗવͱΩϟϥΫλʔੑ͕ݱΕΔ ΩϟϥΫλʔͷັྗΛҾ͖ग़͢ఆੴᶃɿίϯτϥϙετ ɾย଍ʹମॏ͕͔͔ͬͨ࢟੎͸ɺ
    ɹߦಈͷ్தͰෆ҆ఆͳঢ়ଶɻ ɾମͷॏ৺ʹζϨ͕ੜ͡ɺ
    ɹແҙࣝతʹ಄ɾମɾ྆ख଍ͰόϥϯεΛऔΔɻ 㲈
    શ਎Λ࢖ͬͨδΣενϟʔ ΩϟϥΫλʔੑ͕શ਎ʹදΕͨঢ়ଶ
29. ɾҰํͰɺΩϟϥΫλʔΛݟΔਓͷ࿩ɻ
    ɾਓؒ͸ຊೳతʹɺ໨ͷલͷةػΛճආ͢ΔͨΊʹɺ
    ɹ໨ͷલͰ࣍ʹى͜Γ͏Δ͜ͱΛৗʹਪଌ͍ͯ͠Δɻ
    ɾߦಈͷ్தͷΩϟϥΫλʔ͸ਅͬઌʹ෼ੳͨ͘͠ͳΔɻ ҰํͰͦΕΛݟΔਓ͸ɺةػճආͷੜཧ൓Ԡ͕ಇ͖ɺ໨ͷલͷδΣενϟʔʹ໨ΛୣΘΕΔɻ lιοΧͷඒज़ղ๤ֶϊʔτ
    
    ιΫδϣϯώϣϯ
    c
    ΦʔϜࣾʢʣl
    ଞΑΓ ίϯτϥϙετͷ࿦ཧͦͷ̍ɿࣗવͱΩϟϥΫλʔੑ͕ݱΕΔ ΩϟϥΫλʔͷັྗΛҾ͖ग़͢ఆੴᶃɿίϯτϥϙετ
30. ͦͯ͠ΩϟϥΫλʔੑͷ໌շ͔͞Β಺໘Λ஌Γɺ಺໘Λ஌Δͱਓ͸ͦͷਓ෺ʹ޷ײΛ࣋ͭʢख़஌ੑͷݪཧʣ lιοΧͷඒज़ղ๤ֶϊʔτ
    
    ιΫδϣϯώϣϯ
    c
    ΦʔϜࣾʢʣl
    ଞΑΓ ίϯτϥϙετͷ࿦ཧͦͷ̍ɿࣗવͱΩϟϥΫλʔੑ͕ݱΕΔ ɾҰํͰɺΩϟϥΫλʔΛݟΔਓͷ࿩ɻ
    ɾਓؒ͸ຊೳతʹɺ໨ͷલͷةػΛճආ͢ΔͨΊʹɺ
    ɹ໨ͷલͰ࣍ʹى͜Γ͏Δ͜ͱΛৗʹਪଌ͍ͯ͠Δɻ
    ɾߦಈͷ్தͷΩϟϥΫλʔ͸ਅͬઌʹ෼ੳͨ͘͠ͳΔɻ ΩϟϥΫλʔͷັྗΛҾ͖ग़͢ఆੴᶃɿίϯτϥϙετ ΩϟϥΫλʔͷ಺໘Λ஌Δͱɺͦͷਓ෺΁ͷ޷ײ͕૿͢
31. ͦΜͳҰ࿈ͷਓؒͷशੑΛύοέʔδԽͨ͠ͷ͕ίϯτϥϙετɻ͜Ε͕ັྗΛҾ͖ग़͢࿦ཧͷҰͭɻ lιοΧͷඒज़ղ๤ֶϊʔτ
    
    ιΫδϣϯώϣϯ
    c
    ΦʔϜࣾʢʣl
    ଞΑΓ ίϯτϥϙετͷ࿦ཧͦͷ̍ɿࣗવͱΩϟϥΫλʔੑ͕ݱΕΔ ίϯτϥϙετ͸ɺ͜ΕΒਓؒͷशੑΛύοέʔδԽͨ͠ϙʔζ ΩϟϥΫλʔͷັྗΛҾ͖ग़͢ఆੴᶃɿίϯτϥϙετ ΩϟϥΫλʔੑ͕Θ͔Γ΍͍͢ ࢥΘͣݟͪΌ͏ ޷ײ΍਌ۙײΛ࣋ͭ
32. ͦͯ͠΋͏Ұͭͷ࿦ཧ͸୯७ɻϓϩϙʔγϣϯ͕ྑ͍ΩϟϥΫλʔͷັྗɺ೑ମඒΛڧௐ͢ΔޮՌ͕͋Δɻ lιοΧͷඒज़ղ๤ֶϊʔτ
    
    ιΫδϣϯώϣϯ
    c
    ΦʔϜࣾʢʣl
    ଞΑΓ ίϯτϥϙετͷ࿦ཧͦͷ̎ɿ೑ମඒ͕ڧௐ͞ΕΔ ΩϟϥΫλʔͷັྗΛҾ͖ग़͢ఆੴᶃɿίϯτϥϙετ ɾྑ͍ϓϩϙʔγϣϯΛҰ૚ڧௐ͢ΔޮՌ͕͋Δɻ
    ɾಛʹݦஶͳͷ͕ɺେ͖ͳ4ࣈΧʔϒΛඳ͘λΠϓɻ
33. ಛʹޮՌ͕ߴ͍ͷ͕4ࣈϙʔζɻ਎ମͷߏ଄্ɺঁੑ͕ಘҙɻϘσΟϥΠϯ΍ࠎ൫ͷ޿͕͞ڧௐ͞ΕΔɻ lιοΧͷඒज़ղ๤ֶϊʔτ
    
    ιΫδϣϯώϣϯ
    c
    ΦʔϜࣾʢʣl
    ଞΑΓ ίϯτϥϙετͷ࿦ཧͦͷ̎ɿ೑ମඒ͕ڧௐ͞ΕΔ ΩϟϥΫλʔͷັྗΛҾ͖ग़͢ఆੴᶃɿίϯτϥϙετ 4ࣈϙʔζ͸਎ମͷߏ଄্ɺঁੑ͕ಘҙ ਎ମͷϥΠϯ΍Ԝತ͕ࡍཱͪɺ
    ݩʑྑ͍ϓϩϙʔγϣϯ͕ߋʹڧௐ͞ΕΔ ɾྑ͍ϓϩϙʔγϣϯΛҰ૚ڧௐ͢ΔޮՌ͕͋Δɻ
    ɾಛʹݦஶͳͷ͕ɺେ͖ͳ4ࣈΧʔϒΛඳ͘λΠϓɻ
34. ·ͨɺٯసͷΞϓϩʔνͱͯ͠ɺϙʔδϯάͷࢿྉ͔Βย଍ཱͪҎ֎ͷ̎ͭͷ৚݅Λݟग़͞Εͨɻ ϙʔδϯάʹ࢖ΘΕΔίϯτϥϙετͷ৚݅ lඳ͖͍ͨ΋ͷΛཧ࿦Ͱ͔ͭΉ
    ϙʔζͷఆཧ
    
    ࣰ๪࿡࿠
    c
    ,"%0,"8"ʢʣl
    ΑΓ ਓΛऒ͖͚ͭΔϙʔδϯάʹ͸ڞ௨఺͕͋Γ·͢ɻ “ ” ঁੑͷࣸਅࢿྉͷଟ͕͘ɺ͜ͷ̏ͭͷ৚݅Λຬͨ͢ɻ ɾย଍ཱͪ
    PS
    ͦΕʹ͍ۙॏ৺όϥϯε
    ɾ಑ମʹཱମతͳͻͶΓ͕͋Δ
    ɾݞͱࠊͷࠨӈͷߴ͕͞ޓ͍ҧ͍ ( ΩϟϥΫλʔͷັྗΛҾ͖ग़͢ఆੴᶃɿίϯτϥϙετ
35. Ͱ͸͜͜Ͱɺͦͷ৚݅ͷҰͭʹண໨͠ɺ1ZUIPOͰίϯτϥϙετͷݕग़ʹ௅ΜͰΈΔɻ %&.0
    63- 
 IUUQTDPMBCSFTFBSDIHPPHMFDPNESJWFWK+3MB&6W*CQE36I,FYIR#@*%LH4 ίϯτϥϙετΛݕग़͢Δ ɾย଍ཱͪ
    PS
    ͦΕʹ͍ۙॏ৺όϥϯε
    ɾ಑ମʹཱମతͳͻͶΓ͕͋Δ
    ɾݞͱࠊͷࠨӈͷߴ͕͞ޓ͍ҧ͍ ( ͷ৚݅Λຬͨ͢ϙʔζΛݕग़͢Δ ΩϟϥΫλʔͷັྗΛҾ͖ग़͢ఆੴᶃɿίϯτϥϙετ
36. ·ͣ%ը૾͔Β%ͷΩʔϙΠϯτਪఆΛ͢Δɻਪఆ͸ɺ405"ͷख๏ʢ.F53"CTʣʹͯ4.1-Λ׆༻ɻ ίϯτϥϙετΛݕग़͢Δ
     ʢ5'ʹͯ%࢟੎ਪఆϞσϧ 4.1- Λར༻ʣ # import library import tensorflow as tf # load model model = tf.saved_model.load(download_model('metrabs_mob3l_y4t')) # load input image image = tf.image.decode_jpeg(tf.io.read_file(img_name)) pred = model.detect_poses(image, skeleton='smpl_24') # visualize by MeTRAbs demo method visualize( image.numpy(), pred['boxes'].numpy(), pred['poses3d'].numpy(), pred['poses2d'].numpy(), model.per_skeleton_joint_edges['smpl_24'].numpy()) ࢟੎ਪఆ͸શ਎ֆͷΈ༗ޮɻ ΩϟϥΫλʔͷັྗΛҾ͖ग़͢ఆੴᶃɿίϯτϥϙετ ಥඈͳϙʔζ͸ɺ
    ͏·࢟͘੎ਪఆͰ͖ͳ͍
37. ਪఆͨ͠ΩʔϙΠϯτͷ࠲ඪಉ࢜ͷ૬ରతͳҐஔؔ܎Λܭࢉ͠ɺݞͱࠊͷࠨӈͷߴ͕͞ޓ͍ҧ͍͔൑ผɻ ίϯτϥϙετΛݕग़͢Δ
     ʢ5'ʹͯ%࢟੎ਪఆϞσϧ 4.1- Λར༻ʣ # adjusting the visualize method def visualize(…): ... # detect contrast per estimated humans # using coordinate transformation is_contra = detect_contra(pred['poses3d'].numpy()[i]) ... # visualize by MeTRAbs demo method visualize( image.numpy(), pred['boxes'].numpy(), pred['poses3d'].numpy(), pred['poses2d'].numpy(), model.per_skeleton_joint_edges['smpl_24'].numpy()) ࠲Ґͷίϯτϥϙετ΋ਪఆՄɻ ݕग़ͨ͠ίϯτϥϙετΛɺ
    ੺࿮ͷCCPYͰғΉɻ ΩϟϥΫλʔͷັྗΛҾ͖ग़͢ఆੴᶃɿίϯτϥϙετ
38. ίϯτϥϙετ͸ελΠϧͷྑ͍ਓ෺ʹ༗རͳఆੴɻ࣍͸ɺผͷ࣋ͪຯ΋׆͖ΔʮੑઓུʯΛ঺հ͢Δɻ ΋ͪΖΜɺ೑ମඒ͚͕ͩ޷·ΕΔ৚݅Ͱ͸ͳ͍ ɾͨͩɺΩϟϥΫλʔશͯͷϓϩϙʔγϣϯ͕
    ɹ༏Ε͍ͯΔΘ͚Ͱ͸ͳ͍ɻ
    ɾڝ͏ͳɺ࣋ͪຯΛΠΧͤɻ
    ɾϓϩϙʔγϣϯͷྑ͞΋ؚΊͯɺ
    ɹશਓྨ͕ऒ͔ΕΔΩϟϥΫλʔͷ࣋ͪຯΛ
    ɹ͍͔ͭ͘঺հ͢Δɻ ΩϟϥΫλʔͷັྗΛҾ͖ग़͢ఆੴᶃˠᶄ ͙͵͵
39. Ҩ఻ࢠϨϕϧͰ޷·ΕΔಛ௃͸ɺஉঁผʹɺҟੑɾಉੑɾࢠڙͱ͍͏ଐੑʹ෼͚Δͱ੔ཧ͠΍͍͢ɻ lਐԽ৺ཧֶ͔Βߟ͑ΔϗϞαϐΤϯε
    Ұສ೥มԽ͠ͳ͍Ձ஋؍
    
    Ξϥϯɾ4ɾϛϥʔ
    c
    ύϯϩʔϦϯάגࣜձࣾʢʣl
    ΑΓ உঁͷੑઓུʹجͮ͘޷·ΕΔಛ௃ ࢲͨͪͷҨ఻ࢠͷϓϩάϥϜ͞Εͨɺऒ͔ΕΔΩϟϥΫλʔͷಛ௃ͱ͸ʜʁ ΩϟϥΫλʔͷັྗΛҾ͖ग़͢ఆੴᶄɿੑઓུ ରɾҟੑ ରɾಉੑ ରɾࢠڙ ʁ ʁ ʁ ʁ ʁ ʁ
40. ·ͣ͸உੑ͕޷Ήঁੑͷಛ௃ɻஉੑ͸ɺ׬શʹݟͨ໨͚ͩͰए݈͘߁Ͱ͋Δ͜ͱ͕൑ผͰ͖Δಛ௃Λ޷Ήɻ lਐԽ৺ཧֶ͔Βߟ͑ΔϗϞαϐΤϯε
    Ұສ೥มԽ͠ͳ͍Ձ஋؍
    
    Ξϥϯɾ4ɾϛϥʔ
    c
    ύϯϩʔϦϯάגࣜձࣾʢʣl
    ΑΓ ݟͨ໨ͰΘ͔Δಛ௃ ͘ͼΕͨࡉ͍΢ΤετɺԒͷ͋Δ௕͍൅ɺ
    ๛ຬͰϋϦͷ͋Δόετɺؙ͘ઑֺͬͨɺ
    γϫͷͳ͍៉ྷͳटݩɺ෯ͷ޿͍ࠎ൫ɺ
    ϋϦͷ͋Δ៉ྷͳखɺ೑෇͖ͷྑ͍٭
    FUD ˠ ए݈͘߁Ͱ
    ൟ৩Ձ͕ߴ͍ உঁͷੑઓུʹجͮ͘޷·ΕΔಛ௃
    <உੑ
    ˠ
    ҟੑ> உੑ͸جຊతʹൟ৩Ձ͕ߴ͍ʢ೛৷͕੒ޭ͠΍͍͢ʣঁੑΛ޷Ήɻ
    ೛৷͸ɺ݈߁Ͱए͍ঁੑ΄Ͳ੒ޭ཰্͕͕ΔͷͰɺݟͨ໨ͷ݈߁͞ͱए͕͞γάφϧɻ ΩϟϥΫλʔͷັྗΛҾ͖ग़͢ఆੴᶄɿੑઓུ
41. ·ͣ͸உੑ͕޷Ήঁੑͷಛ௃ɻஉੑ͸ɺ׬શʹݟͨ໨͚ͩͰए݈͘߁Ͱ͋Δ͜ͱ͕൑ผͰ͖Δಛ௃Λ޷Ήɻ lਐԽ৺ཧֶ͔Βߟ͑ΔϗϞαϐΤϯε
    Ұສ೥มԽ͠ͳ͍Ձ஋؍
    
    Ξϥϯɾ4ɾϛϥʔ
    c
    ύϯϩʔϦϯάגࣜձࣾʢʣl
    ΑΓ ݟͨ໨ͰΘ͔Δಛ௃ ͘ͼΕͨࡉ͍΢ΤετɺԒͷ͋Δ௕͍൅ɺ
    ๛ຬͰϋϦͷ͋Δόετɺؙ͘ઑֺͬͨɺ
    γϫͷͳ͍៉ྷͳटݩɺ෯ͷ޿͍ࠎ൫ɺ
    ϋϦͷ͋Δ៉ྷͳखɺ೑෇͖ͷྑ͍٭
    FUD ˠ ए݈͘߁Ͱ
    ൟ৩Ձ͕ߴ͍ உঁͷੑઓུʹجͮ͘޷·ΕΔಛ௃
    <உੑ
    ˠ
    ҟੑ> உੑ͸جຊతʹൟ৩Ձ͕ߴ͍ʢ೛৷͕੒ޭ͠΍͍͢ʣঁੑΛ޷Ήɻ
    ೛৷͸ɺ݈߁Ͱए͍ঁੑ΄Ͳ੒ޭ཰্͕͕ΔͷͰɺݟͨ໨ͷ݈߁͞ͱए͕͞γάφϧɻ ΩϟϥΫλʔͷັྗΛҾ͖ग़͢ఆੴᶄɿੑઓུ ঁੑΩϟϥʹඳ͔ΕΔϑΣνͷଟ͕͘ʮए͞ʯͱʮ݈߁ʯͷσϑΥϧϝ FUD Ԓͷ͋Δ௕͍൅ ๛ຬͰϋϦͷ͋Δόετ ؙ͘ઑֺͬͨ ͘ͼΕͨࡉ͍΢Τετ ෯ͷ޿͍ࠎ൫ γϫͷͳ͍៉ྷͳख ೑෇͖ͷྑ͍٭ γϫͷͳ͍៉ྷͳटݩ ੒ख़͠ɺ࿝͚͍ͯͳ͍ ੒ख़͠ɺ͔ͭ҆࢈͕ݟࠐΊΔ ੒ख़͠ɺ࿝͚͍ͯͳ͍ ੒ख़͠ɺ݈߁తͰ͋Δ පؾͰͳ͘ɺ೛৷͍ͯ͠ͳ͍ ੒ख़͠ɺਨΕΔ೥ྸͰ͸ͳ͍ ൅Λ৳͹͢ظؒɺ݈߁Ͱए͍ ೕࣃ͕ແ͍೥ྸͰɺଠͬͯͳ͍
42. ঁੑ͸உੑʹൺ΂ɺҟੑʹର͠௕ظతͳؔ܎Λ๬Ήɻ·ͨɺൺֱతࢿ࢈͕ଟ͘஍Ґͷߴ͍೥্Λ޷Έ΍͍͢ɻ lਐԽ৺ཧֶ͔Βߟ͑ΔϗϞαϐΤϯε
    Ұສ೥มԽ͠ͳ͍Ձ஋؍
    
    Ξϥϯɾ4ɾϛϥʔ
    c
    ύϯϩʔϦϯάגࣜձࣾʢʣl
    ΑΓ ݟͨ໨ͰΘ͔Δಛ௃ ʁʁʁ ೥্ɺଞʁ ˠ ˠ ڧ݈͘߁Ͱੜଘ͠ଓ͚Δ ࣋ଓతʹՈఉΛࢧԉͰ͖Δ ঁੑ͸࣋ଓతʹࣗ෼΍࣮ࢠΛࢧԉͰ͖ΔɺͣͬͱຯํͰ͍ͯ͘ΕΔڧ͍உੑΛ޷Ήɻ
    ݈߁Ͱࢿ࢈͕ଟ͘ɺͦΕΒ͕ࣗ෼΍࣮ࢠͷͨΊʹ࢖ΘΕΔͱ͍͏҆৺ײ΋େࣄɻ உঁͷੑઓུʹجͮ͘޷·ΕΔಛ௃
    <ঁੑ
    ˠ
    ҟੑ> ΩϟϥΫλʔͷັྗΛҾ͖ग़͢ఆੴᶄɿੑઓུ
43. ҟੑʹରͯ͠إͷඒ͠͞ΛٻΊΔͷ͸ɺஉঁڞ௨ɻࠨӈରশͳإ͸ɺ༏ΕͨҨ఻ࢠΛड͚ܧ͙৅௃Ͱ΋͋Δɻ lਐԽ৺ཧֶ͔Βߟ͑ΔϗϞαϐΤϯε
    Ұສ೥มԽ͠ͳ͍Ձ஋؍
    
    Ξϥϯɾ4ɾϛϥʔ
    c
    ύϯϩʔϦϯάגࣜձࣾʢʣl
    ଞΑΓ lݱ୅ϚϯΨʹ͓͚Δʮ͔Θ͍͍ΩϟϥΫλʔʯͷ෼ੳͱ૑࡞
    
    ཥӱ௒
    c
    ژ౎ਫ਼՚େֶʢʣl
    ΑΓҾ༻ average() ݟͨ໨ͰΘ͔Δಛ௃ ࠨӈରশ පؾͳͲͰࠨӈͷ࿪Έ͕ͳ͍ ଟ༷ͳҨ఻ࢠΛड͚ܧ͍Ͱܗ੒͞Εͨإ ฏۉإ ˠ ˠ உঁͷੑઓུʹجͮ͘޷·ΕΔಛ௃
    <உঁ
    ˠ
    ҟੑ> உঁͱ΋ʹɺإ͕ඒ͍͠ҟੑΛٻΊΔɻ
    ࠨӈରশͰฏۉతͳإ͕ඒ͍͠ͱ͞Ε͍ͯΔɻ ΩϟϥΫλʔͷັྗΛҾ͖ग़͢ఆੴᶄɿੑઓུ
44. ·ͨɺஉঁͱ΋ʹࣗ෼Λ޷͍ͨҟੑΛ޷Ήɻஉੑͷ޷Ήൟ৩ɺঁੑͷ޷Ή௕ظతͳؔ܎ɺ྆ํʹ༗ޮͳͨΊɻ lਐԽ৺ཧֶ͔Βߟ͑ΔϗϞαϐΤϯε
    Ұສ೥มԽ͠ͳ͍Ձ஋؍
    
    Ξϥϯɾ4ɾϛϥʔ
    c
    ύϯϩʔϦϯάגࣜձࣾʢʣl
    ଞΑΓ ݟͨ໨ͰΘ͔Δಛ௃ ࣗ෼ʹإΛ޲͚Δɺಏ޸͕։͘ সإ ˠ ˠ ࣗ෼ʹڵຯ͕͋Δ ࣗ෼ʹ޷ײΛ࣋ͭ உঁͷੑઓུʹجͮ͘޷·ΕΔಛ௃
    <உঁ
    ˠ
    ҟੑ> உঁͱ΋ʹɺࣗ෼ʹڵຯ΍޷ײΛ࣋ͭҟੑʹ΋ऒ͔ΕΔɻ
    ࢹઢ΍ಏ޸ͱ͍͕ͬͨ໨ͷ༷ࢠ͔Βਪଌ͢Δ͜ͱ͕ଟ͍ɻ ΩϟϥΫλʔͷັྗΛҾ͖ग़͢ఆੴᶄɿੑઓུ
45. ࣍ʹಉੑʹରͯ͠ɻஉঁͱ΋ʹࣗ෼ͷརӹ࠷େԽͷͨΊɺ਎಺΍͓खຊʹͳΔಉੑΛ޷Ήʢ಺ूஂόΠΞεʣ lਐԽ৺ཧֶ͔Βߟ͑ΔϗϞαϐΤϯε
    Ұສ೥มԽ͠ͳ͍Ձ஋؍
    
    Ξϥϯɾ4ɾϛϥʔ
    c
    ύϯϩʔϦϯάגࣜձࣾʢʣl
    ΑΓ ݟͨ໨ͰΘ͔Δಛ௃ ʁʁʁ ʁʁʁ ˠ ˠ ݟฦΓ͕ظ଴Ͱ͖Δ ༏ΕͨೳྗΛࢀߟʹͰ͖Δ உঁͷੑઓུʹجͮ͘޷·ΕΔಛ௃
    <உঁ
    ˠ
    ಉੑ> ΩϟϥΫλʔͷັྗΛҾ͖ग़͢ఆੴᶄɿੑઓུ ಉੑʹରͯ͠͸உঁͱ΋ʹɺ
    ࣗ෼ͷੑઓུͷো֐ͱͳΒͳ͍ڠྗؔ܎ʹ͋ΔಉੑΛ޷Ήɻ
46. ࠷ޙʹɺࢠڙʹରͯ͠ɻஉঁͱ΋ʹϕϏʔεΩʔϚΛ࣋ͭ΋ͷʹ͸ɺਓͰ΋ಈ෺Ͱ΋ѪΒ͘͠ײ͡Δɻ l%JF
    BOHFCPSFOFO
    'PSNFO
    NÖHMJDIFS
    &SGBISVOH
    
    -PSFO[
    ,
    c
    ;FJUTDISJGU
    'ÛS
    5JFSQTZDIPMPHJFʢʣl
    ΑΓ ݟͨ໨ͰΘ͔Δಛ௃ ϕϏʔεΩʔϚ
    <େ͖ͳ໨ɺ๲ΒΜͩ๹ɺؙ͍͓Ͱ͜ɺ
    
    େ͖ͳ಄ɺ஄ྗ͋Δഽɺ୹͍ख଍
    FUD> ˠ อޢͨ͘͠ͳΔ
    ༊͞ΕΔ உঁͷੑઓུʹجͮ͘޷·ΕΔಛ௃
    <உঁ
    ˠ
    ࢠڙ> ࢠڙʹରͯ͠͸உঁͱ΋ʹɺ
    ʮϕϏʔεΩʔϚʯͰఆٛ͞ΕΔࢠڙΒ͍͠਎ମతಛ௃ΛѪΒ͘͠ࢥ͏ɻ ΩϟϥΫλʔͷັྗΛҾ͖ग़͢ఆੴᶄɿੑઓུ
47. ࠷ޙʹɺࢠڙʹରͯ͠ɻஉঁͱ΋ʹϕϏʔεΩʔϚΛ࣋ͭ΋ͷʹ͸ɺਓͰ΋ಈ෺Ͱ΋ѪΒ͘͠ײ͡Δɻ l%JF
    BOHFCPSFOFO
    'PSNFO
    NÖHMJDIFS
    &SGBISVOH
    
    -PSFO[
    ,
    c
    ;FJUTDISJGU
    'ÛS
    5JFSQTZDIPMPHJFʢʣl
    ΑΓ ݟͨ໨ͰΘ͔Δಛ௃ ϕϏʔεΩʔϚ
    <େ͖ͳ໨ɺ๲ΒΜͩ๹ɺؙ͍͓Ͱ͜ɺ
    
    େ͖ͳ಄ɺ஄ྗ͋Δഽɺ୹͍ख଍
    FUD> ˠ อޢͨ͘͠ͳΔ
    ༊͞ΕΔ உঁͷੑઓུʹجͮ͘޷·ΕΔಛ௃
    <உঁ
    ˠ
    ࢠڙ> ࢠڙʹରͯ͠͸உঁͱ΋ʹɺ
    ʮϕϏʔεΩʔϚʯͰఆٛ͞ΕΔࢠڙΒ͍͠਎ମతಛ௃ΛѪΒ͘͠ࢥ͏ɻ ΩϟϥΫλʔͷັྗΛҾ͖ग़͢ఆੴᶄɿੑઓུ ࢠڙͷ਎ମతಛ௃͸ɺ࣮೥ྸ΋छ଒΋࣍ݩ΋ؔ܎ͳ͘ѪΒ͍͠
48. Ҏ্͕ɺੑઓུΛ΋ͱʹ੔ཧͨ͠޷·ΕΔಛ௃ɻ֎ݟ͔ΒಡΈऔΓ΍͍͢ԫ৭͸ɺΠϥετʹԠ༻͠΍͍͢ɻ lਐԽ৺ཧֶ͔Βߟ͑ΔϗϞαϐΤϯε
    Ұສ೥มԽ͠ͳ͍Ձ஋؍
    
    Ξϥϯɾ4ɾϛϥʔ
    c
    ύϯϩʔϦϯάגࣜձࣾʢʣl
    ଞΑΓ உঁͷੑઓུʹجͮ͘޷·ΕΔಛ௃
    <·ͱΊ> ରɾҟੑ ରɾಉੑ ରɾࢠڙ ए͞ ݈߁͞ʗإͷྑ͞ʗࣗ෼ʹؔ৺͕͋Δ ࣗ෼ʹརӹΛ΋ͨΒ͢ ࢠڙΒ͍͠਎ମతಛ௃Λ࣋ͭ ࣋ଓతͳڧ͍ຯํʹͳΔ ΩϟϥΫλʔͷັྗΛҾ͖ग़͢ఆੴᶄɿੑઓུ
49. ͨͩ͠ɺແܭըʹҰ෦ͷײੑΛܹࢗ͢ΔΑ͏ͳΠϥετΛඳ͘ͷ͸ةݥɻཁ݅ʹݟ߹͏ൣғͰ׆༻͠Α͏ɻ lʮӺ೫Έ͔ͪʯεέεέεΧʔτ͕େ෺ٞɹ౦ژϝτϩɺ൷൑ड͚ඍົʹʮमਖ਼ʯʢʣ
    c
    +$"45χϡʔεz
    ΑΓ ͨͩ͠ɺੑઓུͷσϑΥϧϝ͸৻ॏʹ ΩϟϥΫλʔΛັྗతʹݟͤΔͷ΋େࣄ͕ͩɺ
    ڧௐ͢Δͷ͸ΩϟϥΫλʔͷཁ݅ʹ߹ͬͨັྗʹߜΔඞཁ͕͋Δɻ ʮެڞަ௨ػؔͷΩϟϥΫλʔͱͯ͠;͞Θ͘͠ͳ͍ʯ “ ” ͱͯ͠෺ٞΛৢ͠ɺʮӺ೫Έ͔ͪʯͷσβΠϯ͸मਖ਼͞Εͨɻ मਖ਼ ΩϟϥΫλʔͷັྗΛҾ͖ग़͢ఆੴᶄɿੑઓུ
50. Ͱ͸ੑઓུʹجͮ͘ಛ௃Λڧௐ͠ա͍͗ͯͳ͍͔ɺ࿐ࠎͳදݱΛ1ZUIPOͰݕग़ͯ͠ΈΔɻ %&.0
    63- 
 IUUQTDPMBCSFTFBSDIHPPHMFDPNESJWFC%G@.GVB@8NRWO.I/::Y[.%6 ࿐ࠎͳදݱΛݕग़͢Δ ΩϟϥΫλʔͷັྗΛҾ͖ग़͢ఆੴᶄɿੑઓུ
51. ਺ߦͰݕग़͢Δྫɻ/4'8
    'JMUFS͸4/4΍ݕࡧͳͲͷࣄྫ͕ଟ͘ɺ044΋ଟ͍ɻϑϦʔϥΠυ͠΍͍͢ɻ ࿐ࠎͳදݱΛݕग़͢Δʢ/VEFOFUͷֶशࡁΈϞσϧʗ൑ผثΛར༻ʣ # import library import nudenet as NudeDetector # load input image and put local (omitted) # initialize detector (adjusted NudeDetector in nudenet) detector = NudeDetector() # run censor method # -> detect nudity & set bbox & display image detector.censor(img_name) ݕग़࣌ʹ
    ܯࠂʁ ΩϟϥΫλʔͷັྗΛҾ͖ग़͢ఆੴᶄɿੑઓུ
52. લ൒·ͱΊɻΩϟϥΫλʔͷັྗΛදݱ͢Δࣗ༝౓͕ߴ͍͜ͱΛ౿·͑ͯɺશਓྨʹ༗ޮͳఆੴΛࣔͨ͠ɻ ΩϟϥΫλʔͷ৺ཧઓུɿ·ͱΊ ϙʔζ ද৘ Ͳ͏ັྗΛ఻͑Δ͔ ίϯτϥϙετ ఆੴ ੑઓུ ʜ ΩϟϥΫλʔੑͱ
    ೑ମඒ ʜ உ͸ൟ৩ɺ
    ঁ͸Ϧιʔε ಛ௃ᶃ ಛ௃ᶇ ಛ௃ᶄ ಛ௃ᶆ ಛ௃ᶅ ϙʔζʗද৘ΛܾΊΔ ΩϟϥΫλʔͷັྗΛ఻͑Δ ετʔϦʔ΍৔໘Λ఻͑Δ Ωϟϥֆͷझࢫ
53. ίϯτϥϙετ ఆੴ ੑઓུ ʜ ΩϟϥΫλʔੑͱ
    ೑ମඒ ʜ உ͸ൟ৩ɺ
    ঁ͸Ϧιʔε ಛ௃ᶃ ಛ௃ᶇ ಛ௃ᶄ ಛ௃ᶆ ಛ௃ᶅ ϙʔζʗද৘ΛܾΊΔ ʁʁʁ ʁʁʁ ϙʔζ ද৘ Ͳ͏ັྗΛ఻͑Δ͔ ΩϟϥΫλʔͷັྗΛ఻͑Δ ετʔϦʔ΍৔໘Λ఻͑Δ Ωϟϥֆͷझࢫ ࠓճ঺հͨ͠ఆੴ͸σϞͰࣔͨ͠௨Γɺ1ZUIPO΍"*Ͱ΋ཧղ͠΍͍͢ɻֆࢣ͕஫ྗ͢΂͖͸ଞͷཁૉ͔΋ɻ ΩϟϥΫλʔͷ৺ཧઓུɿΫϦΤΠλʔ͕஫ྗ͢΂͖͸…ʁ
54. ̎ ޫͱ৭ͷ৺ཧઓུ
55. l৭ృΓνϡʔτϦΞϧ
    σδλϧ࠼৭ͷجຊ
    
    ύΫɾϦϊ
    c
    Ϛʔϧࣾʢʣl
    ΑΓ લఏ஌ࣝͱͯ͠ɺޫ͸෺ཧݱ৅Ͱɺ৭͸৺ཧݱ৅Ͱ͋Δ͜ͱɻͦͯ͠৭͸ޫʹґଘ͍ͯ͠Δɻ ޫͱ৭ ৭͸ޫʹґଘ͢Δ ന৭ޫ ੺͍ޫ ੺ʂ
56. ΋͠΋ޫݯ͕ϒϧʔϥΠτ͔͠ͳ͔ͬͨΒɺࢲͨͪ͸੨͔ࠇ͔͠ೝࣝ͢Δ͜ͱ͕Ͱ͖ͳ͍ɻ ޫͱ৭ ৭͸ޫʹґଘ͢Δ ϒϧʔϥΠτ ൓ࣹޫ ࠇʁ ੨ʁ l৭ృΓνϡʔτϦΞϧ
    σδλϧ࠼৭ͷجຊ
    
    ύΫɾϦϊ
    c
    Ϛʔϧࣾʢʣl
    ΑΓ
57. ΋͠΋ޫݯ͕ϒϧʔϥΠτ͔͠ͳ͔ͬͨΒɺࢲͨͪ͸੨͔ࠇ͔͠ೝࣝ͢Δ͜ͱ͕Ͱ͖ͳ͍ɻ ޫͱ৭ ৭͸ޫʹґଘ͢Δ ϒϧʔϥΠτ ൓ࣹޫ ࠇʁ ੨ʁ l৭ృΓνϡʔτϦΞϧ
    σδλϧ࠼৭ͷجຊ
    
    ύΫɾϦϊ
    c
    Ϛʔϧࣾʢʣl
    ΑΓ %B[
    4UVEJP
    *SBZ
    ʹͯ࡞੒ lըͮ͘ΓͷͨΊͷޫͷतۀ
    
    ϦνϟʔυɾϤοτ
    c
    #//৽ࣾʢʣl
    ΑΓ ༦ํͷଠཅޫ ۭ৭ͷఱۭޫ ೔ৗੜ׆Ͱ΋ɺ৭͕ภΔޫܠ͸Α͘ݟΒΕΔ
58. Ͱ͸·ͣ͸ɺΠϥετ͔Βޫͱ৭Λ෼཭ͯٞ͠࿦͢ΔͨΊɺ1ZUIPOͰর໌ͷ৭Λ෼཭ͯ͠ΈΔɻ %&.0
    63- 
 IUUQTDPMBCSFTFBSDIHPPHMFDPNESJWFG0G5Y:OE30-DR['M*-23G),(D,0D' PythonͰΠϥετͷޫͷ৭Λ୳Δ Πϥετ͔Βর໌ͷ৭Λফ͢
59. # crone Deep_White_Balance !git clone https://github.com/mahmoudnafifi/Deep_White_Balance.git # run test script !python demo_single_image.py \ —input INPUT_IMAGE_PATH \ --output_dir OUTPUT_DIR \ --model_dir MODEL_DIR # crone mixedillWB !git clone https://github.com/mahmoudnafifi/mixedillWB.git # run test script !python test.py \ --wb-settings T F D C S \ --model-name WB_model_p_64_D_S_T_F_C \ —testing-dir INPUT_DIR --outdir OUTPUT_DIR ϗϫΠτόϥϯεͷ่ΕΛิਖ਼͠ɺෳ਺ͷর໌ͷ৭Λิਖ਼͢Δͱ͍͏̎ͭͷख๏Λ࠾༻ʢ঎༻ར༻ෆՄʣ র໌ͷ৭Λݕग़ʗന͘ิਖ਼͢Δʢ%FFQ8#
    NJYFEJMM8#Λར༻
    6/FUʣ ("'"ࣾһΒͷެ։͢ΔSFQPͷ
    αϯϓϧεΫϦϓτΛ࣮ߦ͢Δ͚ͩɻ PythonͰΠϥετͷޫͷ৭Λ୳Δ
60. # crone Deep_White_Balance !git clone https://github.com/mahmoudnafifi/Deep_White_Balance.git # run test script !python demo_single_image.py \ —input INPUT_IMAGE_PATH \ --output_dir OUTPUT_DIR \ --model_dir MODEL_DIR # crone mixedillWB !git clone https://github.com/mahmoudnafifi/mixedillWB.git # run test script !python test.py \ --wb-settings T F D C S \ --model-name WB_model_p_64_D_S_T_F_C \ —testing-dir INPUT_DIR --outdir OUTPUT_DIR ϗϫΠτόϥϯεͷ่ΕΛิਖ਼͠ɺෳ਺ͷর໌ͷ৭Λิਖ਼͢Δͱ͍͏̎ͭͷख๏Λ࠾༻ʢ঎༻ར༻ෆՄʣ র໌ͷ৭Λݕग़ʗന͘ิਖ਼͢Δʢ%FFQ8#
    NJYFEJMM8#Λར༻
    6/FUʣ ("'"ࣾһΒͷެ։͢ΔSFQPͷ
    αϯϓϧεΫϦϓτΛ࣮ߦ͢Δ͚ͩɻ PythonͰΠϥετͷޫͷ৭Λ୳Δ ࣮ࣸ
    
    % 👍 Πϥετ σϑΥϧϝऑΊ 👍 Πϥετ σϑΥϧϝڧΊ 🤔 ͨͩ͠σϑΥϧϝ͕ڧ͘ͳΔ΄Ͳɺ৭ͷิਖ਼͕͏·͍͔͘ͳ͘ͳΔɻ ڧ ऑ
61. Πϥετͷޫͷදݱ͸ɺ෺ཧ๏ଇʹ४ڌ͸ͯ͠΋ɺ९क͸͞Εͳ͍ɻͦͷͨΊҰఆͷϧʔϧͷநग़͸ࠔ೉ɻ PythonͰΠϥετͷޫͷ৭Λ୳Δ → Failed 2
    ΠϥετͷϗϫΠτόϥϯεɺԿނ͏·͍͔͘ͳ͍ͷ͔ έʔε̍ɹهԱ৭ʢయܕ৭ʣΛڧௐ έʔε̎ɹཱମදݱ͕লུ "ɹཧ༝͸ʮޫͷ෺ཧ๏ଇʹैΘͳ͍࠼৭ʯ͔ͩΒ ˠ ҰఆͷϧʔϧԽ͸ࠔ೉ ʜ l৭࠼ݕఆ
    ެࣜςΩετ
    ڃฤ
    ೥վగ൛
    ʗ6$ڃ
    ೥վగ൛
    
    ৭࠼ݕఆڠձ
    c
    ৭࠼ݕఆڠձl
    ଞΑΓ ڧௐ লུ
62. Πϥετͷޫͷදݱ͸ɺ෺ཧ๏ଇʹ४ڌ͸ͯ͠΋ɺ९क͸͞Εͳ͍ɻͦͷͨΊҰఆͷϧʔϧͷநग़͸ࠔ೉ɻ PythonͰΠϥετͷޫͷ৭Λ୳Δ → Failed 2
    ΠϥετͷϗϫΠτόϥϯεɺԿނ͏·͍͔͘ͳ͍ͷ͔ έʔε̍ɹཱମදݱ͕লུ έʔε̎ɹهԱ৭ʢయܕ৭ʣΛڧௐ "ɹཧ༝͸ʮޫͷ෺ཧ๏ଇʹैΘͳ͍࠼৭ʯ͔ͩΒ ˠ ҰఆͷϧʔϧԽ͸ࠔ೉ লུ ڧௐ ʜ l৭࠼ݕఆ
    ެࣜςΩετ
    ڃฤ
    ೥վగ൛
    ʗ6$ڃ
    ೥վగ൛
    
    ৭࠼ݕఆڠձ
    c
    ৭࠼ݕఆڠձl
    ଞΑΓ Πϥετσʔλͷ෼ੳͰ͸
    ޫΛ௚઀ѻ͏ͷ͸೉͍͠ɺ৭ʹूத͢Δ 🥲 ઓུతఫୀ
    ͥ͟ΔΛಘͳ͍
63. ৭ͷ໾໨͸ɺ੍࡞ϑϩʔͷஈ֊ʹΑͬͯେ͖̎ͭ͘ʹ෼͔ΕΔɻ a ੍ ࡞ ϑ ϩ 
    Πϥετશମͷ৭ΛܾΊΔ 
    ඃࣸମʢʴഎܠʣΛඳ͖ࠐΉ ৭ͷ໾໨ͱ੍࡞ϑϩʔ
64. ҰൠʹɺґཔऀʹΠϥετΛൃ஫͞Εͨ৔߹ɺΠϥετΛ࢓্͛Δલʹ·ͣશମͷ഑৭Λ֬ೝͯ͠΋Β͏ɻ a 
    Πϥετશମͷ৭ΛܾΊΔ 
    ඃࣸମʢʴഎܠʣΛඳ͖ࠐΉ ੍ ࡞ ϑ ϩ ৭ΛృΓ࢝ΊΔલʹ
    ৭ͷϥϑΛ͍͔ͭ͘ඳ͍ͯɺ
    ґཔओͱೝࣝΛ߹ΘͤΔɻ ˠ
    ίϯηϓτΛܾΊΔ ৭ͷ໾໨ͱ੍࡞ϑϩʔ
65. a ੍ ࡞ ϑ ϩ 
    Πϥετશମͷ৭ΛܾΊΔ 
    ඃࣸମʢʴഎܠʣΛඳ͖ࠐΉ ܾ·ͬͨ഑৭Λϕʔεʹ
    ண৭͠ɺࡉ෦Λඳ͖ࠐΉɻ ˠ
    ΫΦϦςΟΛ্͛Δ ˠ
    ίϯηϓτΛܾΊΔ ഑৭Ͱґཔऀͱͷ߹ҙ͕औΕͨΒɺΫΦϦςΟʔΛ্͛ΔͨΊʹΠϥετʹ৭Λඳ͖ࠐΜͰ͍͘ɻ ৭ͷ໾໨ͱ੍࡞ϑϩʔ
66. a ੍ ࡞ ϑ ϩ ഑৭Ͱ
    ίϯηϓτܾఆ 
    Πϥετશମͷ৭ΛܾΊΔ ˠ
    ίϯηϓτΛܾΊΔ ృΓͰ
    ΫΦϦςΟ61 
    ඃࣸମʢʴഎܠʣΛඳ͖ࠐΉ ˠ
    ΫΦϦςΟΛ্͛Δ ʜ
    ⁞ ʜ
      ͭ·Γɺ৭ʹ͸ʮ഑৭ͰίϯηϓτΛܾΊΔʯʮృΓͰΫΦϦςΟΛ্͛Δʯͱ͍͏̎ͭͷ໾໨͕͋Δɻ ৭ͷ໾໨ͱ੍࡞ϑϩʔ
67. ⁞
    ഑৭ͰίϯηϓτΛܾΊΔɿ఻͑Δҹ৅͕୯৭ or ෳ਺৭ l৭࠼ݕఆ
    ެࣜςΩετ
    ڃฤ
    ೥վగ൛
    ʗ6$ڃ
    ೥վగ൛
    
    ৭࠼ݕఆڠձ
    c
    ৭࠼ݕఆڠձl
    ଞΑΓ Πϥετશମʹ࢖ΘΕΔ৭͸ྨࣅͯ͠Δʁ෼ࢄͯ͠Δʁ શମͷ৭͸ྨࣅ͔෼ࢄ͔ ྨࣅ ྨࣅ৭ͷதͰ
    ࠷΋໘ੵͷଟ͍৭ͷ
    ҹ৅·ͨ͸࿈૝Πϝʔδ 
    ֆࢣ͕఻͍͑ͨײ৘ ෼ࢄ ෼ࢄͨ͠഑৭ͷ
    ૊Έ߹ΘͤʹΑΔ
    ҹ৅·ͨ͸࿈૝Πϝʔδ 
    ֆࢣ͕఻͍͑ͨײ৘ Ұͭ໨ɺ഑৭ͰͲΜͳίϯηϓτΛܾΊΔ͔ɻ఻͍͑ͨΠϝʔδʹ߹Θͤͯɺશମͷ৭Λྨࣅʗ෼ࢄͤ͞Δɻ
68. ඃࣸମͱഎܠ͸ରൺ͔ಉԽ͔ ରൺ ಉԽ ඃࣸମͱഎܠͷ৭ͷ෼෍͕େ͖͘ҟͳΔʁࣅ͍ͯΔʁ ˠɹඃࣸମ͕࣋ͭײ৘ʹ஫໨͍ͤͨ͞ ˠɹΠϥετશମ͕࣋ͭײ৘ʹ஫໨͍ͤͨ͞ ⁞
    ഑৭ͰίϯηϓτΛܾΊΔɿओ໾͕ඃࣸମ or શମ l৭࠼ݕఆ
    ެࣜςΩετ
    ڃฤ
    ೥վగ൛
    ʗ6$ڃ
    ೥վగ൛
    
    ৭࠼ݕఆڠձ
    c
    ৭࠼ݕఆڠձl
    ଞΑΓ ͦͯ͠ඃࣸମʹ஫໨͍͔ͤͨ͞ɺഎܠʹೃછ·͍͔ͤͨɺͱ͍͏ૂ͍ʹ߹Θͤͯ৭ΛରൺʗಉԽͤ͞Δɻ
69. Ͱ͸࣮ࡍʹΠϥετͷ৭Λ1ZUIPOͰநग़ʗՄࢹԽͯ͠ɺ͜ΕΒͷํ਑Λ୳ͬͯΈΑ͏ %&.0
    63- 
 IUUQTDPMBCSFTFBSDIHPPHMFDPNESJWF92H++YYC.N4SD&U[LZ"6X/@+9Y0U PythonͰΠϥετ͔Β৭ͷํ਑Λ୳Δ ഑৭Λ၆ᛌ͢Δɿྨࣅ͔෼ࢄ͔ ʴ
70. ഑৭Λ၆ᛌ͢Δɿྨࣅ͔෼ࢄ͔
     ʢશମ૾ΛϚϯηϧද৭ܥͰ೺Ѳʣ # import library from matplotlib.colors import ListedColormap import matplotlib.pyplot as plt # prepare dataset C = [[1032 1033 1034 ... 1072 1073 1074] [ 989 990 991 ... 1029 1030 1031] ... [ 43 44 45 ... 83 84 85] [ 0 1 2 ... 40 41 42]] masked_cc = ['#ba2237' ... ‘#ffffff', ‘#411434', '#ffffff'] cmap = ListedColormap(masked_cc) # draw pcolormesh ax = plt.pcolormesh(C, cmap=cmap) plt.colorbar(ax) ը૾ʹແ͍৭͸
    ͰϚεΫ͢Δ #ffffff PythonͰΠϥετ͔Β৭ͷํ਑Λ୳Δ Ϛϯηϧද৭ܥͷσʔλΛ༻ҙͰ͖Ε͹ɺNBUQMPUMJCͷϝογϡඳըͰ഑৭ͷશମ૾͕ϚοϐϯάͰ͖Δɻ
71. ഑৭Λ၆ᛌ͢Δɿྨࣅ͔෼ࢄ͔
     ʢ৭૬෼෍Λ৭૬؀ώετάϥϜͰ೺Ѳʣ # import library import cv2 import matplotlib.pyplot as plt # prepare dataset (omitted) Polar_df = pd.DataFrame({'Hue': ..., 'Count': …}) # plot polar axis ax = plt.subplot(polar=True) # draw bars bars = ax.bar( x=[element * width for element in Polar_df.index], height=Polar_df.Count, width=2*np.pi / len(Polar_df.index), bottom=Polar_df[‘Count'].max()/3) ෼ࢄʁ ྨࣅʁ PythonͰΠϥετ͔Β৭ͷํ਑Λ୳Δ .BUQMPUMJCͷۃ࠲ඪάϥϑͰɺ৭૬؀Λ໛ͨ͠ώετάϥϜ΋දݱՄೳɻNBUQMPUMJC͸͍͍ͧɻ
72. ഑৭Λ၆ᛌ͢Δɿྨࣅ͔෼ࢄ͔
     ʢ৭૬෼෍Λ৭૬؀ώετάϥϜͰ೺Ѳʣ # import library import cv2 import matplotlib.pyplot as plt # prepare dataset (omitted) Polar_df = pd.DataFrame({'Hue': ..., 'Count': …}) # plot polar axis ax = plt.subplot(polar=True) # draw bars bars = ax.bar( x=[element * width for element in Polar_df.index], height=Polar_df.Count, width=2*np.pi / len(Polar_df.index), bottom=Polar_df[‘Count'].max()/3) ෼ࢄʁ ྨࣅʁ PythonͰΠϥετ͔Β৭ͷํ਑Λ୳Δ .BUQMPUMJCͷۃ࠲ඪάϥϑͰɺ৭૬؀Λ໛ͨ͠ώετάϥϜ΋දݱՄೳɻNBUQMPUMJC͸͍͍ͧɻ શମͷ৭ΛϚοϐϯάͯ͠ɺ഑৭ͷํ਑Λ໌Β͔ʹ͢Δʢ෼ࢄͷྫʣ ੺ ੺ ԫ ෼ੳྫɿ੺ͱԫʹ෼ࢄ͍ͯͯ͠Ҿཱ͖ͯ߹͍ɺܹࢗతͳҹ৅ɻ ෼ࢄʁ ྨࣅʁ
73. ഑৭Λ၆ᛌ͢Δɿྨࣅ͔෼ࢄ͔
     ʢ৭૬෼෍Λ৭૬؀ώετάϥϜͰ೺Ѳʣ # import library import cv2 import matplotlib.pyplot as plt # prepare dataset (omitted) Polar_df = pd.DataFrame({'Hue': ..., 'Count': …}) # plot polar axis ax = plt.subplot(polar=True) # draw bars bars = ax.bar( x=[element * width for element in Polar_df.index], height=Polar_df.Count, width=2*np.pi / len(Polar_df.index), bottom=Polar_df[‘Count'].max()/3) ෼ࢄʁ ྨࣅʁ PythonͰΠϥετ͔Β৭ͷํ਑Λ୳Δ .BUQMPUMJCͷۃ࠲ඪάϥϑͰɺ৭૬؀Λ໛ͨ͠ώετάϥϜ΋දݱՄೳɻNBUQMPUMJC͸͍͍ͧɻ શମͷ৭ΛϚοϐϯάͯ͠ɺ഑৭ͷํ਑Λ໌Β͔ʹ͢Δʢྨࣅͷྫʣ ෼ࢄʁ ྨࣅʁ ੨ʙ੺ ෼ੳྫɿࢵʹྨࣅ͢Δ৭Ͱ౷Ұ͞ΕɺϛεςϦΞεͳҹ৅ɻ
74. ഑৭Λ၆ᛌ͢Δɿྨࣅ͔෼ࢄ͔
     ʢ৭૬෼෍Λ৭૬؀ώετάϥϜͰ೺Ѳʣ # import library import cv2 import matplotlib.pyplot as plt # prepare dataset (omitted) Polar_df = pd.DataFrame({'Hue': ..., 'Count': …}) # plot polar axis ax = plt.subplot(polar=True) # draw bars bars = ax.bar( x=[element * width for element in Polar_df.index], height=Polar_df.Count, width=2*np.pi / len(Polar_df.index), bottom=Polar_df[‘Count'].max()/3) ෼ࢄʁ ྨࣅʁ PythonͰΠϥετ͔Β৭ͷํ਑Λ୳Δ .BUQMPUMJCͷۃ࠲ඪάϥϑͰɺ৭૬؀Λ໛ͨ͠ώετάϥϜ΋දݱՄೳɻNBUQMPUMJC͸͍͍ͧɻ ৭૬؀ώετάϥϜͰɺΑΓࡉ͔͍ύλʔϯʢ৭࠼ௐ࿨࿦ΑΓʣ͕୳ΕΔ ྨࣅ ྨࣅ ෼ࢄ ෼ࢄ ෼ࢄ ෼ࢄ l(VJEF
    UP
    $SFBUJOH
    $PMPS
    4DIFNFT
    
    "35
    30$,&5l
    ΑΓ
75. ଓ͍ͯɺඃࣸମͱഎܠΛ෼͚ͯɺͦΕͧΕͷ৭ͷؔ܎ੑΛ୳ͬͯΈΑ͏ɻ %&.0
    63- 
 IUUQTDPMBCSFTFBSDIHPPHMFDPNESJWFC$*3'GV)TV)/R)XWE%*6H768F*N PythonͰΠϥετ͔Β৭ͷํ਑Λ୳Δ ඃࣸମͱഎܠͷؔ܎Λ୳Δɿରൺ͔ಉԽ͔
76. # import library import torch from carvekit.api.high import HiInterface # create CarveKit interface interface = HiInterface(batch_size_seg=5, batch_size_matting=1, device='cuda' if torch.cuda.is_available() else 'cpu', seg_mask_size=320, matting_mask_size=2048) images_without_background = interface([img_name]) # save object only image cat_wo_bg = images_without_background[0] cat_wo_bg.save(‘object_only.png') PythonͰΠϥετ͔Β৭ͷํ਑Λ୳Δ ඃࣸମͱഎܠͷؔ܎Λ୳Δɿରൺ͔ಉԽ͔ʢ$BSWF,JUͰ෼཭ʣ ඃࣸମͱഎܠͷ෼཭͸ɺڊਓͷݞʢ4FHNFOUBUJPOʣ͕୔ࢁɻࠓճ͸$BSWF,JUͱ͍͏'8Λར༻ͨ͠ɻ
77. # import library import torch from carvekit.api.high import HiInterface # create CarveKit interface interface = HiInterface(batch_size_seg=5, batch_size_matting=1, device='cuda' if torch.cuda.is_available() else 'cpu', seg_mask_size=320, matting_mask_size=2048) images_without_background = interface([img_name]) # save object only image cat_wo_bg = images_without_background[0] cat_wo_bg.save(‘object_only.png') PythonͰΠϥετ͔Β৭ͷํ਑Λ୳Δ ඃࣸମͱഎܠͷؔ܎Λ୳Δɿରൺ͔ಉԽ͔ʢ$BSWF,JUͰ෼཭ʣ ඃࣸମͱഎܠͷ෼཭͸ɺڊਓͷݞʢ4FHNFOUBUJPOʣ͕୔ࢁɻࠓճ͸$BSWF,JUͱ͍͏'8Λར༻ͨ͠ɻ ඃࣸମͱഎܠΛ෼͚ͯ෼ੳ͠ɺؔ܎ੑΛ໌Β͔ʹ͢ΔʢಉԽͷྫʣ ରൺʁ ಉԽʁ ෼ੳྫɿΧϥϑϧͰ೐΍͔ͳҹ৅ɻඃࣸମͷ഑৭ʹ͍ۙԫ৭Λഎܠ͕ิ͍ಉԽ͍ͯ͠Δɻ
78. # import library import torch from carvekit.api.high import HiInterface # create CarveKit interface interface = HiInterface(batch_size_seg=5, batch_size_matting=1, device='cuda' if torch.cuda.is_available() else 'cpu', seg_mask_size=320, matting_mask_size=2048) images_without_background = interface([img_name]) # save object only image cat_wo_bg = images_without_background[0] cat_wo_bg.save(‘object_only.png') PythonͰΠϥετ͔Β৭ͷํ਑Λ୳Δ ඃࣸମͱഎܠͷؔ܎Λ୳Δɿରൺ͔ಉԽ͔ʢ$BSWF,JUͰ෼཭ʣ ඃࣸମͱഎܠͷ෼཭͸ɺڊਓͷݞʢ4FHNFOUBUJPOʣ͕୔ࢁɻࠓճ͸$BSWF,JUͱ͍͏'8Λར༻ͨ͠ɻ ඃࣸମͱഎܠΛ෼͚ͯ෼ੳ͠ɺؔ܎ੑΛ໌Β͔ʹ͢Δʢରൺͷྫʣ ରൺʁ ಉԽʁ ෼ੳྫɿ੺ͱ྘ͷରൺɻάϨʔτʔϯͷ྘ͷ্Ͱ઱΍͔ͳ੺͕ࡍཱ͍ͬͯΔɻ
79. # import library import torch from carvekit.api.high import HiInterface # create CarveKit interface interface = HiInterface(batch_size_seg=5, batch_size_matting=1, device='cuda' if torch.cuda.is_available() else 'cpu', seg_mask_size=320, matting_mask_size=2048) images_without_background = interface([img_name]) # save object only image cat_wo_bg = images_without_background[0] cat_wo_bg.save(‘object_only.png') PythonͰΠϥετ͔Β৭ͷํ਑Λ୳Δ ඃࣸମͱഎܠͷؔ܎Λ୳Δɿରൺ͔ಉԽ͔ʢ$BSWF,JUͰ෼཭ʣ ඃࣸମͱഎܠͷ෼཭͸ɺڊਓͷݞʢ4FHNFOUBUJPOʣ͕୔ࢁɻࠓճ͸$BSWF,JUͱ͍͏'8Λར༻ͨ͠ɻ ಉ༷ͷΞϓϩʔνͰɺΑΓৄࡉͳఆੑ෼ੳʹ௅Ήࣄྫ΋͋Γ·͢ lਓؾֆࢣͷ࡞඼͔ΒֶͿ഑৭ͷώϛπ
    
    Ҵ༿ོ
    c
    ݰޫࣾʢʣ
    l
    ΑΓ Φεεϝʂ
80. l/PWJDF
    4USBUFHJFT
    GPS
    6OEFSTUBOEJOH
    1BJOUJOHT
    
    +"
    4DINJEUΒ
    c
    "QQMJFE
    $PHOJUJWF
    1TZDIPMPHZ
    ʢʣl
    ΑΓ  
    ృΓͰΫΦϦςΟΛ্͛Δ ࣮ࣸੑΛߴΊΔృΓ͸ɺֆࢣͷͩ͜ΘΓϙΠϯτ ৭Λඳ͖ࠐΉ͜ͱͰɺ࣭ײ΍Ԟߦ͖͕දݱͰ͖ɺ࣮ࣸੑ͕૿͢ɻ
    ༠໨ੑΛߴΊɺ຅ೖײ͕༩͑ΔͨΊɺඃࣸମͷڧௐʹΑ͘࢖ΘΕΔɻ ഑৭ʹଓ͘ɺ΋͏Ұͭͷ৭ͷ໾ׂ͕ʮృΓʯɻֆࢣ͸ͩ͜ΘΓ͍ͨ෦෼͸ಛʹ೤৺ʹඳ͖ࠐΉɻ
81. ͪͳΈʹృΓͰඳ͖ࠐΈྔ͕ଟ͍ྖҬ͸ɺ1ZUIPOͰ؆୯ʹਪఆͰ͖Δɻ %&.0
    63- 
 IUUQTDPMBCSFTFBSDIHPPHMFDPNESJWF@XM47U:+)H2G#CS6UYC#ESY[33@) PythonͰΠϥετ͔ΒృΓͷͩ͜ΘΓΛ୳Δ ඳ͖ࠐΈ͕ଟ͍ྖҬΛਪఆ͢Δ
82. ྫ͑͹ಡΈࠐΜͩΠϥετΛ/෼ׂͯ͠ɺ֤ྖҬͷΤϯτϩϐʔΛܭࢉɻృΓͰ૿͑ͨ৘ใྔ͕ਪఆͰ͖Δɻ # import library (omitted) # load image (omitted) # divide gray scale image x0, y0, n, h, w = ... divided = [gray_image[x0*x:x0*(x+1), y0*y:y0*(y+1)] for x in range(n) for y in range(n)] # calculate entropy for each division entropies = [] for img in divided: img = np.array(img) e = calcEntropy_method(img) entropies.append(e) # visualize (omitted) ͋ʂ؈ͷඳ͖ࠐΈ͕ଟ͍ʂ
    ͳͲɺͩ͜ΘΓʹؾ෇͚Δ ඳ͖ࠐΈ͕ଟ͍ྖҬΛਪఆ͢ΔʢΤϯτϩϐʔͰܭࢉʣ PythonͰΠϥετ͔ΒృΓͷͩ͜ΘΓΛ୳Δ
83. ޙ൒·ͱΊɻ৭ͷ໾໨Λ഑৭ͱృΓʹ෼͚ɺಛʹ഑৭ʹΑΔίϯηϓτͷಡΈํΛ࣮ફΛ௨ͯ͠ղઆͨ͠ɻ ޫͱ৭ͷ৺ཧઓུɿ·ͱΊ ৭ ഑৭Ͱίϯηϓτ શମͷ৭ ྨࣅ ෼ࢄ ରൺ ಉԽ ඃࣸମͱഎܠ ޫ ʜ ʜ ඳ͖ࠐΈྔʹͩ͜ΘΓ͕දΕΔ ʜ ৭୯ମͷΠϝʔδΛ׆༻ ʜ ʜ ʜ ৭ͷ૊Έ߹ΘͤΠϝʔδΛ׆༻ ඃࣸମΛ஫໨ͤ͞Δ Πϥετશମʹ໨Λ޲͚ͤ͞Δ ৭͸ޫʹґଘ͢Δʢͨͩ͠ɺޫΛΠϥετ͔Β෼཭͢Δͷ͸ࠔ೉ʣ ృΓͰΫΦϦςΟ
84. ͜ͷதͰֆࢣ͕஫ྗ͢΂͖͸ɺ΍͸Γ఻͑ΔΠϝʔδΛܾΊΔίϯηϓτઃܭͳͷͰ͸ͳ͍͔ͱ૝૾͢Δɻ ޫͱ৭ͷ৺ཧઓུɿΫϦΤΠλʔ͕஫ྗ͢΂͖͸…ʁ ৭ ഑৭Ͱίϯηϓτ શମͷ৭ ྨࣅ ෼ࢄ ରൺ ಉԽ ඃࣸମͱഎܠ ޫ ʜ ʜ ඳ͖ࠐΈྔʹͩ͜ΘΓ͕දΕΔ ʜ ৭୯ମͷΠϝʔδΛ׆༻ ʜ ʜ ʜ ৭ͷ૊Έ߹ΘͤΠϝʔδΛ׆༻ ඃࣸମΛ஫໨ͤ͞Δ Πϥετશମʹ໨Λ޲͚ͤ͞Δ ৭͸ޫʹґଘ͢Δʢͨͩ͠ɺޫΛΠϥετ͔Β෼཭͢Δͷ͸ࠔ೉ʣ ృΓͰΫΦϦςΟ ˠ
    ࠓޙ͜͜͸"*ֆࢣʹ೚ͤΒΕΔ͔΋ʁ
85. ·ͱΊ
86. ࠷ޙʹɺϓϨθϯͷ·ͱΊɻࠓճ͸৺ཧઓུͷߏ଄Խʹ௅Έɺֆࢣ͕஫ྗ͢΂͖ϙΠϯτΛ໛ࡧͨ͠ɻ ·ͱΊ  ΩϟϥΫλʔͱޫʗ৭ͷ৺ཧઓུΛߏ଄Խ͠ɺ 
 ͦͷ͍͔ͭ͘Λ1ZUIPOͰ࠶ݱͨ͠ 
    ΩϟϥΫλʔͷັྗΛҾ͖ग़͢ఆੴͱ 
 ɹ
    ഑৭ʹΑΔίϯηϓτઃܭΛॏ఺తʹղઆͨ͠
87. ͪͳΈʹɺॴʑͰొ৔ͨ͠ΠϥετͷҰ෦͸4UBCMF
    %J ff VTJPOϕʔεͷ"*ֆࢣ͕ඳ͍ͨ΋ͷͰͨ͠ɻ ऴΘΓʹɿ͜ͷࢿྉ͸AIֆࢣͷྗΛआΓͯ࡞Γ·ͨ͠ ϓϨθϯࢿྉˍσϞૉࡐͱͯ͠ɺ
    ֆฑֶश"*ͷੜ੒ΠϥετΛ׆༻͠·ͨ͠ 4QFDJBM
    UIBOLT
    UP
    ͍͔͢Έ͞Μʂ
    ʢ!L@JLBTVNJQPXEFSʣ
88. Ҏ্ɺ͝੩ௌ͋Γ͕ͱ͏͍͟͝·ͨ͠ɻ SFGFSFODF
    ෺ཧ Thank you! ͨ͘͞Μͷٕ๏ॻͷ
    ΤοηϯεΛ٧ΊࠐΈ·ͨ͠
89. • ◦×ͰΘ͔Δ෩ܠ࡞ը ਆٕ࡞ըγϦʔζ - ͚͞ϋϥε | KADOKAWAʢ2020ʣ • ΩϟϥΫλʔΠϥετͷҾ͖ग़͠Λ૿΍͢ϙʔζͱද৘ͷԋग़ςΫχοΫ - ΧϦϚϦΧ | ᠳӭࣾʢ2022ʣ • ιοΧͷඒज़ղ๤ֶϊʔτ - ιΫδϣϯώϣϯ | ΦʔϜࣾʢ2018ʣ • ΩϜɾϥοΩͷਓମυϩʔΠϯά - ΩϜɾϥοΩ | ΦʔϜࣾʢ2020ʣ • ඳ͖͍ͨ΋ͷΛཧ࿦Ͱ͔ͭΉ ϙʔζͷఆཧ - ࣰ๪࿡࿠ | KADOKAWAʢ2022ʣ Ҏ্ɺ͝੩ௌ͋Γ͕ͱ͏͍͟͝·ͨ͠ɻ SFGFSFODF
     Thank you! • Die angeborenen Formen möglicher Erfahrung - Lorenz, K. | Zeitschrift Für Tierpsychologieʢ1943ʣ • ਐԽ৺ཧֶ͔Βߟ͑ΔϗϞαϐΤϯε Ұສ೥มԽ͠ͳ͍Ձ஋؍ - ΞϥϯɾSɾϛϥʔ | ύϯϩʔϦϯάʢ2019ʣ
90. • ৭ృΓνϡʔτϦΞϧ σδλϧ࠼৭ͷجຊ - ύΫɾϦϊ | Ϛʔϧࣾʢ2020ʣ • ޫͱ৭ͷνϡʔτϦΞϧ - ӄӨͱ৭࠼ΛࣗࡏʹૢΔʂ - ύΫɾϦϊ | Ϛʔϧࣾʢ2021ʣ • ৭࠼ݕఆ ެࣜςΩετ 1ڃฤ (2020೥վగ൛) - ৭࠼ݕఆڠձ | ৭࠼ݕఆڠձ • ৭࠼ݕఆ ެࣜςΩετ 3ڃฤ (2020೥վగ൛) - ৭࠼ݕఆڠձ | ৭࠼ݕఆڠձ • ৭࠼ݕఆ ެࣜςΩετ UCڃ (2022೥վగ൛) - ৭࠼ݕఆڠձ | ৭࠼ݕఆڠձ Ҏ্ɺ͝੩ௌ͋Γ͕ͱ͏͍͟͝·ͨ͠ɻ SFGFSFODF
     Thank you! • Χϥʔ&ϥΠτ ϦΞϦζϜͷͨΊͷ৭࠼ͱޫͷඳ͖ํ - δΣʔϜεɾΨʔχʔ | Ϙʔϯσδλϧʢ2012ʣ • ৭࠼ݕఆ ެࣜςΩετ 2ڃฤ (2020೥վగ൛) - ৭࠼ݕఆڠձ | ৭࠼ݕఆڠձ
91. • ਓؾֆࢣͷ࡞඼͔ΒֶͿ഑৭ͷώϛπ - Ҵ༿ོ | ݰޫࣾʢ2022ʣ • ΠϥετɺອըͷͨΊͷ഑৭ڭࣨ - দԬ৳࣏ | MdNʢ2018ʣ • ഑৭ͷڭՊॻ - ৭࠼จԽݚڀձ | PIE Internationalʢ2018ʣ • The Art of GUWEIZ ά΢ΣΠζըू - GUWEIZ | ϗϏʔδϟύϯʢ2021ʣ • mignon͕͔ͬ͠Γڭ͑ΔʮഽృΓʯͷൿ݃ - mignon | SBΫϦΤΠςΟϒʢ2020ʣ Ҏ্ɺ͝੩ௌ͋Γ͕ͱ͏͍͟͝·ͨ͠ɻ SFGFSFODF
     Thank you! • ཧܥ೴Ͱඳ͘๖͑ֆ - ݾଈੋۭʢ2017ʣ
92. • Vision ετʔϦʔΛ఻͑Δɿ৭ɺޫɺߏਤ - ϋϯεɾPɾόοϋʔ | Ϙʔϯσδλϧʢ2019ʣ • ֆΛݟΔٕज़ ໊ըͷߏ଄ΛಡΈղ͘ - ळాຑૣࢠ | ே೔ग़൛ࣾʢ2019ʣ • ޫͱ৭࠼ ղମ৽ॻ - μςφΦτ | ϚΠφϏग़൛ʢ2018ʣ • ըͮ͘ΓͷͨΊͷޫͷतۀ - দԬ৳࣏ | ϏʔɾΤψɾΤψ৽ࣾ ʢ2019ʣ • ײ֮৘ใͷ஌֮ϝΧχζϜ - ਗ਼ਫ๛ | ણҡ੡඼ফඅՊֶʢ1987ʣ Ҏ্ɺ͝੩ௌ͋Γ͕ͱ͏͍͟͝·ͨ͠ɻ SFGFSFODF
     Thank you! • Novice Strategies for Understanding Paintings - JA SchmidtΒ | Applied Cognitive Psychology 3.1ʢ1989ʣ • ֆըؑ৆ʹ͓͚Δೝ஌త੍໿ͱͦͷ؇࿨ - ాத٢࢙, দຊ࠼ق | ೝ஌Պֶʢ2013ʣ
93. • MeTRAbs Absolute 3D Human Pose Estimator | Github • ࠲ඪܥΛ͋ΘͤΔ ઈର࠲ඪͱϩʔΧϧ࠲ඪ - ϓϩάϥϛϯά੔ܗ֎Պҩͷϖʔδ • PythonʹΑΔ࠲ඪม׵ͷϓϩάϥϜ - ϓϩάϥϛϯά੔ܗ֎Պҩͷϖʔδ • ̏࣍ݩ্ۭؒͷͶ͡Εͨ̎௚ઢͷ࠷઀ۙ఺ΛٻΊΔ - Vignette & Clarity • Hue&ToneγεςϜ | Χϥʔઓུͷઐ໳Ո | NCD-WEB Ҏ্ɺ͝੩ௌ͋Γ͕ͱ͏͍͟͝·ͨ͠ɻ SFGFSFODF
     Thank you! • Color Scheme Analysis of Illustrations - Niti Wattanasirichaigoon • Guide to Creating Color Schemes - ART ROCKET
94. • Deep White-Balance Editing | Github • Auto White-Balance Correction for Mixed-Illuminant Scenes | Github • NudeNet | Github **NSFW** • CarveKit | Github • ʮΩϟϥֆඳ͖ΞϧΰϦζϜʯγϦʔζ - osakana.factory | ٕज़ॻయ Ҏ্ɺ͝੩ௌ͋Γ͕ͱ͏͍͟͝·ͨ͠ɻ SFGFSFODF
     Thank you! • Munsell Resources - Paul Centore • Image Color Extraction with Python in 4 Steps - Boriharn K | Medium
95. • σΟʔϓϒϦβʔυ - σΟʔϓϒϦβʔυ | YouTube • Yaki Mayuru drawing channel - ম·͍Δ | YouTube • ֆ༿·͠ΖͷͪΌΜͶΔ - ֆ༿·͠Ζ | Youtube Ҏ্ɺ͝੩ௌ͋Γ͕ͱ͏͍͟͝·ͨ͠ɻ SFGFSFODF
     Thank you! • ͋ͳͨΛԠԉͨ͘͠ͳΔ5ͭͷཁҼͱ͸ʁ ਐԽ৺ཧֶͰߟ࡯ - Ṗ෦͑Ή | Noteʢ2018ʣ
 https://note.com/nasobem/n/n628306e0e6e5 • ϓϩ໺ٿϑΝϯʹؔ͢Δݚڀ(V) : ϑΝϯ৺ཧɺԠԉߦಈɺ͓Αͼूஂॴଐҙࣝͷߏ଄
 - ޿୔ढ़फΒ | ؔ੢ࠃࡍେֶ஍Ҭݚڀॴ૓ॻʢ2006ʣ • ʮ͔Θ͍͍ʯͷ৺ཧֶ - ೝ஌৺ཧੜཧֶݚڀࣨʢ2022/10/12࣌఺ʣ
96. • ༷ʑͳݒ೦΍໰୊Λ๊͑ͭͭ΋ʮ͓ֆ͔͖AIʯͷਐԽ͸ࢭ·Βͣʢ2022/10/4ʣ| Yahoo!χϡʔε
 https://news.yahoo.co.jp/articles/1cb8c63ee8fb7a3bbbb8412aeefcc2bf2217d033 • ΠϥετϨʔλʔͷݸੑΛֶΜͰֆΛ“ແݶੜ੒”͢ΔAIαʔϏεʢ2022/8/29ʣ | ITmedia
 https://www.itmedia.co.jp/news/articles/2208/29/news133.html • AI͕ֆΛඳ͘ʁ ਐԽ͢Δը૾ੜ੒AIͷ࠷લઢʢ2022/10/8ʣ | NHK
 https://www3.nhk.or.jp/news/html/20221008/k10013851401000.html Ҏ্ɺ͝੩ௌ͋Γ͕ͱ͏͍͟͝·ͨ͠ɻ SFGFSFODF
     Thank you! • ʮͱΜͰ΋ͳ͘ϋΠΫΦϦςΟʔʯ࿩୊ͷը૾AIʮNovel AIʯͰͻͨ͢Βೋ࣍ݩඒগঁͱඒগ೥Λੜ੒ͯ͠Έͨ | ITmedia
 https://www.itmedia.co.jp/news/articles/2208/29/news133.html • ʮӺ೫Έ͔ͪʯεέεέεΧʔτ͕େ෺ٞɹ౦ژϝτϩɺ൷൑ड͚ඍົʹʮमਖ਼ʯʢ2016/10/18ʣ | JCASTχϡʔε
 https://www.j-cast.com/2016/10/18280985.html