モデル高速化百選

モデル高速化百選内田祐介 AIシステム部株式会社ディー・エヌ・エー

લఏ • ओʹԼهͷ৚݅Λຬͨ͢ख๏Λ঺հ • ಛఆͷϋʔυ΢ΣΞʹґଘͤͣʹ࣮ݱՄೳ • ৞ΈࠐΈχϡʔϥϧωοτϫʔΫ $// ͕ର৅ •
ਪ࿦࣌ͷߴ଎Խ͕ର৅ • ඦબ͠·͕ͨ͠Ұ෦͚ͩ঺հ͠·͢ • "QQFOEJYʹϦετ͕͋Γ·͢

ߴ଎Խʁ • Ϟσϧύϥϝʔλ਺ͷ࡟ݮ • '-01T ."$T ਺ͷ࡟ݮ • ϞσϧϑΝΠϧαΠζͷ࡟ݮ •
ਪ࿦࣌ؒͷ࡟ݮ • ܇࿅࣌ؒͷ࡟ݮ ඍົʹҧ͏ͷͰɺ࢖͏ͱ͖͸ԿΛॏࢹ͢΂͖͔ɺ ࿦จΛಡΉͱ͖͸Կ͕վળ͍ͯ͠Δͷ͔Λؾʹ͢Δ

Ϟσϧߴ଎Խ • ৞ΈࠐΈͷ෼ղ 'BDUPSJ[BUJPO • ࢬמΓ 1SVOJOH • ΞʔΩςΫνϟ୳ࡧ /FVSBM"SDIJUFDUVSF4FBSDI/"4
• ૣظऴྃɺಈతܭࢉάϥϑ &BSMZ5FSNJOBUJPO %ZOBNJD$PNQVUBUJPO(SBQI • ৠཹ %JTUJMMBUJPO • ྔࢠԽ 2VBOUJ[BUJPO

畳み込みの分解 (Factorization)

৞ΈࠐΈ૚ͷܭࢉྔ • ೖྗϨΠϠαΠζɿ)Y8Y/ • ৞ΈࠐΈΧʔωϧɿ,Y,Y/Y. DPOW,Y, .ͱදه FHDPOWY •
ग़ྗϨΠϠαΠζɿ)Y8Y. • ৞ΈࠐΈͷܭࢉྔɿ)ɾ8ɾ/ɾ,ɾ.ʢόΠΞε߲Λແࢹʣ 8 ) / . , , 8 ) ⼊⼒特徴マップ畳み込みカーネル / 出⼒特徴マップ ˎ ࿨ ཁૉੵ × . DPOW,º, . 畳み込み層の計算量は • 画像/特徴マップのサイズ（HW） • ⼊出⼒チャネル数（NM） • カーネルサイズ（K2）に⽐例

ۭؒํ޲ͷ෼ղ • େ͖ͳ৞ΈࠐΈΧʔωϧΛখ͞ͳ৞ΈࠐΈΧʔωϧʹ෼ղ • ྫ͑͹Yͷ৞ΈࠐΈΛYͷ৞ΈࠐΈͭʹ෼ղ • ͜ΕΒ͸ಉ͡αΠζͷड༰໺Λ͕࣋ͭ෼ղ͢Δͱܭࢉྔ͸ • *ODFQUJPOW<>Ͱ͸࠷ॳͷY৞ΈࠐΈΛY৞ΈࠐΈͭʹ෼ղ •
Ҏ߱ͷ4&/FU΍4IV⒐F/FU7౳ͷ࣮૷Ͱ΋ར༻͞Ε͍ͯΔ<> ಛ௃Ϛοϓ conv5x5 conv3x3 - conv3x3 [4] C. Szegedy, et al., "Rethinking the Inception Architecture for Computer Vision," in Proc. of CVPR, 2016. [18] T. He, et al., "Bag of Tricks for Image Classification with Convolutional Neural Networks," in Proc. of CVPR, 2019.

ۭؒํ޲ͷ෼ղ • OYOΛYOͱOYʹ෼ղ͢Δ͜ͱ΋ [4] C. Szegedy, et al., "Rethinking
the Inception Architecture for Computer Vision," in Proc. of CVPR, 2016.

ۭؒํ޲ͱνϟωϧํ޲ͷ෼ղ TFQBSBCMFDPOW • ۭؒํ޲ͱνϟωϧํ޲ͷ৞ΈࠐΈΛಠཱʹߦ͏ • %FQUIXJTF৞ΈࠐΈʢۭؒํ޲ʣ • ಛ௃Ϛοϓʹର͠νϟωϧຖʹ৞ΈࠐΈ • ܭࢉྔɿ)ɾ8ɾ/ɾ,ɾ.
./ )ɾ8ɾ,ɾ/ • 1PJOUXJTF৞ΈࠐΈʢνϟωϧํ޲ʣ • Yͷ৞ΈࠐΈ • ܭࢉྔɿ)ɾ8ɾ/ɾ,ɾ. , )ɾ8ɾ/ɾ. • %FQUIXJTF QPJOUXJTF TFQBSBCMF • ܭࢉྔɿ)ɾ8ɾ/ɾ , . 㲈)ɾ8ɾ/ɾ. ˞., • )ɾ8ɾ/ɾ,ɾ.͔Βେ෯ʹܭࢉྔΛ࡟ݮ W H W H N 1 1 M W H W H N K K N W H W H N M K K 通常 depthwise pointwise

9DFQUJPO<> • 4FQBSBCMFDPOWΛଟ༻ͨ͠Ϟσϧ [6] F. Chollet, "Xception: Deep learning
with depthwise separable convolutions," in Proc. of CVPR, 2017.

.PCJMF/FU<> • EFQUIXJTFQPJOUXJTFDPOWΛଟ༻ • վྑ൛ͷ.PCJMF/FU7<>7<>΋͋Δ 通常の畳み込み MobileNetの1要素 [7] A.
Howard, et al., "MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications," in arXiv:1704.04861, 2017. [13] M. Sandler, et al., "MobileNetV2: Inverted Residuals and Linear Bottlenecks," in Proc. of CVPR, 2018. [20] A. Howard, et al., "Searching for MobileNetV3," in arXiv:1905.02244, 2019.

4IV⒐F/FU<> • .PCJMF/FUͷϘτϧωοΫͱͳ͍ͬͯΔDPOWYΛ HSPVQDPOWY DIBOOFMTIV⒐Fʹஔ׵ • HSPVQDPOWೖྗͷಛ௃ϚοϓΛ(ݸʹάϧʔϓԽ͠ ֤άϧʔϓ಺Ͱݸผʹ৞ΈࠐΈΛߦ͏ ʢܭࢉྔ)ɾ8ɾ/ɾ,ɾ.ˠ)ɾ8ɾ/ɾ,ɾ.(ʣ •
DIBOOFMTIV⒐FνϟωϧͷॱংΛೖΕସ͑Δ SFTIBQF USBOTQPTFͷૢ࡞Ͱ࣮ݱՄೳ DTIVGGMF EFQUIXJTFDPOW HDPOWY spatial channel HDPOWY [8] X. Zhang, et al., "ShuffleNet: An Extremely Efficient Convolutional Neural Network for Mobile Devices," in arXiv:1707.01083, 2017.

$IBOOFM/FU<> • νϟωϧํ޲ʹ࣍ݩͷ৞ΈࠐΈΛߦ͏ [11] H. Gao, Z. Wang, and
S. Ji, "ChannelNets: Compact and Efficient Convolutional Neural Networks via Channel-Wise Convolutions", in Proc. of NIPS, 2018.

枝刈り (Pruning)

ࢬמΓ 1SVOJOH • ৞ΈࠐΈ૚΍શ݁߹૚ͷॏΈͷҰ෦Λʹ͢Δ͜ͱͰ ύϥϝʔλ਺ɾܭࢉྔΛ࡟ݮ ωοτϫʔΫΛֶश ࢬמΓʢਫ਼౓௿Լʣ
ωοτϫʔΫΛ࠶ֶशʢਫ਼౓Λ͋Δఔ౓ճ෮ʣ ͱ͍͏ϑϩʔ͕Ұൠత

6OTUSVDUVSFEWT4USVDUVSFE1SVOJOH • 1SVOJOHલͷ৞ΈࠐΈϑΟϧλ • 6OTUSVDUVSFEQSVOJOH • 4USVDUVSFEQSVOJOHʢϑΟϧλʢνϟωϧʣQSVOJOH͕Ұൠతʣ K K
… … … M（出⼒チャネル）個計算量vs.精度のtrade-oﬀは優れているが専⽤のハードウェアでないと⾼速化できない単にチャネル数が減少したネットワークに再構築が可能で⾼速化の恩恵を受けやすい

%FFQ$PNQSFTTJPO< > • 6OTUSVDUVSFEͳQSVOJOH • - ਖ਼ଇԽΛՃֶ͑ͯश͠ɺઈର஋͕খ͍͞XFJHIUΛʹ • ࣮ࡍʹߴ଎ʹಈ͔͢ʹ͸ઐ༻ϋʔυ͕ඞཁ<>
[23] S. Han, et al., "Learning both Weights and Connections for Efficient Neural Networks," in Proc. of NIPS, 2015. [25] S. Han, et al., "Deep Compression: Compressing Deep Neural Networks with Pruning, Trained Quantization and Huffman Coding," in Proc. of ICLR, 2016. [26] S. Han, et al., "EIE: Efficient Inference Engine on Compressed Deep Neural Network," in Proc. of ISCA, 2016.

1SVOJOH'JMUFSTGPS&⒏DJFOU$POW/FUT<> • 4USVDUVSFEQSVOJOHʢνϟωϧϨϕϧͷQSVOJOHʣ • ֤ϨΠϠʹ͍ͭͯɺϑΟϧλͷॏΈͷઈର஋ͷ૯࿨͕ খ͍͞΋ͷ͔ΒQSVOJOH • ֤ϨΠϠͷQSVOJOH཰͸QSVOJOH΁ͷTFOTJUJWJUZ͔Β ਓखͰௐ੔ •
1SVOJOHޙʹGJOFUVOF [30] H. Li, et al., "Pruning Filters for Efficient ConvNets," in Proc. of ICLR, 2017.

/FUXPSL4MJNNJOH<> • #BUDIOPSNͷύϥϝʔλЍʹ- ϩεΛֶ͔͚ͯश • ֶशޙɺЍ͕খ͍͞νϟωϧΛ࡟আ͠ɺpOFUVOF νϟωϧຖʹೖྗΛฏۉ0෼ࢄ1ʹਖ਼نԽɺγͱβͰscale & shift
νϟωϧi … … Batch normalization [33] Z. Liu, et al., "Learning Efficient Convolutional Networks through Network Slimming," in Proc. of ICCV, 2017.

L0 Ͱ͸ͳ͘Lasso ʹ؇࿨ͯ͠ղ͘ $IBOOFM1SVOJOH<> • ͋ΔGFBUVSFNBQͷνϟωϧ࡟আͨ͠৔߹ʹ ࣍ͷGFBUVSFNBQͷޡ͕ࠩ࠷খͱͳΔΑ͏νϟωϧΛબ୒ [34] Y.
He, et al., "Channel Pruning for Accelerating Very Deep Neural Networks," in Proc. of ICCV, 2017.

5IJ/FU<> • લड़ͷख๏ͱಉ͡Α͏ʹɺ࣍ͷGFBUVSFNBQͷޡ͕ࠩ ࠷খͱͳΔϨΠϠΛHSFFEZ࡟আ • ࡟আޙʹɺ৞ΈࠐΈͷॏΈΛޡ͕ࠩ࠷খʹͳΔΑ͏ʹ ௐ੔ˠpOFUVOF [35] J.
Luo, et al., "ThiNet: A Filter Level Pruning Method for Deep Neural Network Compression," in Proc. of ICCV, 2017.

"VUP.-GPS.PEFM$PNQSFTTJPOBOE"DDFMFSBUJPO ".$ <> • ڧԽֶशʢP⒎QPMJDZBDUPSDSJUJDʣʹΑΓ ֤ϨΠϠຖͷ࠷దͳQSVOJOH཰Λֶश • ೖྗ͸ର৅ϨΠϠͷ৘ใͱͦΕ·ͰͷQSVOJOH݁Ռɺ ใु͸rΤϥʔ཰ºMPH '-01T
PSMPH 1BSBNT [41] Y. He, et al., "AMC - AutoML for Model Compression and Acceleration on Mobile Devices," in Proc. of ECCV, 2018.

-PUUFSZ5JDLFU)ZQPUIFTJT *$-3`#FTU1BQFS <> • //ʹ͸ɺʮ෦෼ωοτϫʔΫߏ଄ʯͱʮॳظ஋ʯͷ ૊Έ߹Θͤʹʮ౰ͨΓʯ͕ଘࡏ͠ɺͦΕΛҾ͖౰ͯΔͱ ޮ཰తʹֶश͕Մೳͱ͍͏Ծઆ • 6OTUSVDUVSFEͳQSVOJOHͰͦͷߏ଄ͱॳظ஋Λݟ͚ͭΔ͜ͱ͕Ͱ͖ͨ
https://www.slideshare.net/YosukeShinya/the-lottery-ticket-hypothesis-finding-small-trainable-neural-networks [44] Jonathan Frankle, Michael Carbin, "The Lottery Ticket Hypothesis: Finding Sparse, Trainable Neural Networks," in Proc. of ICLR, 2019.

/FUXPSL1SVOJOHBT"SDIJUFDUVSF4FBSDI<> • 4USVDUVSFEͳQSVOJOHޙͷωοτϫʔΫΛTDSBUDI͔Βֶशͤͯ͞΋ pOFUVOFͱಉ౳͔ͦΕΑΓྑ͍݁Ռ͕ಘΒΕΔͱ͍͏ओு • ͭ·ΓQSVOJOH͸ɺॏཁͳॏΈΛ୳ࡧ͍ͯ͠ΔͷͰ͸ͳ͘ ֤ϨΠϠʹͲͷఔ౓ͷνϟωϧ਺ΛׂΓ౰ͯΔ͔ͱ͍͏ /FVSBM"SDIJUFDUVSF4FBSDI /"4 Λ͍ͯ͠ΔͱΈͳͤΔ
• -PUUFSZ5JDLFU)ZQPUIFTJTͰ͸VOTUSVDUVSFEͰɺ௿-3ͷΈɺ ࣮ݧ΋খن໛ωοτϫʔΫͷΈ [45] Z. Liu, et al., "Rethinking the Value of Network Pruning," in Proc. of ICLR, 2019.

アーキテクチャ探索 (Neural Architecture Search; NAS)

ΞʔΩςΫνϟ୳ࡧ /"4 • //ͷΞʔΩςΫνϟΛࣗಈઃܭ͢Δख๏ • ୳ࡧۭؒɺ୳ࡧख๏ɺਫ਼౓ධՁख๏Ͱେ·͔ʹ෼ྨ͞ΕΔ • ୳ࡧۭؒ • (MPCBM
DFMMCBTFE • ୳ࡧख๏ • ڧԽֶशɺਐԽతΞϧΰϦζϜɺHSBEJFOUϕʔεɺSBOEPN • ਫ਼౓ଌఆख๏ • શֶशɺ෦෼ֶशɺXFJHIUTIBSFɺࢬמΓ୳ࡧ T. Elsken, J. Metzen, and F. Hutter, "Neural Architecture Search: A Survey," in JMLR, 2019. M. Wistuba, A. Rawat, and T. Pedapati, "A Survey on Neural Architecture Search," in arXiv:1905.01392, 2019. https://github.com/D-X-Y/awesome-NAS

/"4/FU<> • ୳ࡧۭؒɿDFMMɺ ୳ࡧख๏ɿڧԽֶश 1SPYJNBM1PMJDZ0QUJNJ[BUJPO • (MPCBMͳઃܭʹυϝΠϯ஌ࣝΛ׆༻ɺ ߏ੒͢ΔDFMMͷΈΛࣗಈઃܭ ˠ୳ࡧۭؒΛେ෯ʹ࡟ݮ •
/PSNBMDFMMY/ͱSFEVDUJPODFMMͷελοΫ • 3FEVDUJPODFMM͸࠷ॳʹTUSJEF෇͖ͷ01Ͱ ಛ௃ϚοϓΛμ΢ϯαϯϓϧ • 3FEVDUJPODFMMҎ߱ͰνϟωϧΛഒʹ [52] B. Zoph, V. Vasudevan, J. Shlens, and Q. V. Le, "Learning transferable architectures for scalable image recognition," in Proc. of CVPR, 2018.

/"4/FUͷίϯτϩʔϥͷಈ࡞ )JEEFOTUBUF˞ Λબ୒ ͦΕΒ΁ͷ01TΛબ୒˞ ͦΕΒΛ݁߹͢Δ01 BEEPSDPODBU Λબ୒͠৽ͨͳIJEEFOTUBUFͱ͢Δ
˞)JEEFOTUBUF྘ͷϒϩοΫͱIJ IJ* ˞)JEEFOTUBUF΁ͷ01ީิ [52] B. Zoph, V. Vasudevan, J. Shlens, and Q. V. Le, "Learning transferable architectures for scalable image recognition," in Proc. of CVPR, 2018.

˞)JEEFOTUBUF྘ͷϒϩοΫͱIJ IJ* ˞)JEEFOTUBUF΁ͷ01ީิ sep 3x3 avg 3x3 [52] B. Zoph, V. Vasudevan, J. Shlens, and Q. V. Le, "Learning transferable architectures for scalable image recognition," in Proc. of CVPR, 2018.

˞)JEEFOTUBUF྘ͷϒϩοΫͱIJ IJ* ˞)JEEFOTUBUF΁ͷ01ީิ concat sep 3x3 avg 3x3 [52] B. Zoph, V. Vasudevan, J. Shlens, and Q. V. Le, "Learning transferable architectures for scalable image recognition," in Proc. of CVPR, 2018.

&/"4<> • ୳ࡧۭؒɿDFMMɺ୳ࡧख๏ɿڧԽֶश 3&*/'03$& • $FMMͷߏ଄Λग़ྗ͢Δ3//ίϯτϩʔϥͱɺ ίϯτϩʔϥʔ͕ग़ྗ͢ΔશͯͷωοτϫʔΫΛαϒάϥϑͱͯ͠อ ࣋Ͱ͖ΔڊେͳܭࢉάϥϑʢωοτϫʔΫʣΛಉ࣌ʹֶश ˠੜ੒ͨ͠ωοτϫʔΫͷֶश͕ෆཁʹʢ(16GPSEBZTʣ •
4JOHMFTIPU XFJHIUTIBSF • ৄࡉ͸ਆࢿྉ Λࢀর [54] H. Pham, M. Y. Guan, B. Zoph, Q. V. Le, and Jeff Dean, "Efficient Neural Architecture Search via Parameter Sharing," in Proc. of ICML, 2018. * https://www.slideshare.net/tkatojp/efficient-neural-architecture-search-via-parameters- sharing-icml2018

&/"4ͷֶश • ίϯτϩʔϥʔͷύϥϝʔλВͱ ڊେͳωοτϫʔΫͷύϥϝʔλXΛަޓʹֶश • Xͷֶश • ВΛݻఆ͠ɺαϒάϥϑΛαϯϓϦϯά • αϒάϥϑΛGPSXBSECBDLXBSE͠XΛߋ৽
• Вͷֶश • XΛݻఆ͠ɺαϒάϥϑΛαϯϓϦϯά • WBMJEBUJPOσʔλͰਫ਼౓Λଌఆ͠ใुΛऔಘɺ3&*/'03$&ͰВΛߋ৽

%"354<> • ୳ࡧۭؒɿDFMMɺ୳ࡧख๏ɿHSBEJFOU • άϥϑͷ઀ଓ΍01ͷબ୒ΛTPGUNBYͰ࣮ݱ͢Δ͜ͱͰɺ ߏ଄୳ࡧ΋GPSXBSECBDLXBSEͰ࣮ݱ • &/"4ͱಉ͘͡TIBSFEQBSBNɺXͱߏ଄Λަޓʹ࠷దԽ [57]
H. Liu, K. Simonyan, and Y. Yang, "DARTS: Differentiable Architecture Search," in Proc. of ICLR, 2019.

'#/FU<> • %"354ͱಉ͘͡HSBEJFOUCBTFE • ֤01ͷ࣮σόΠε্Ͱͷॲཧ࣌ؒΛMPPLVQUBCMFʹอ࣋ • ॲཧ࣌ؒΛߟྀͨ͠ϩεΛ͔͚Δ [61] B.
Wu, et al., "FBNet: Hardware-Aware Efficient ConvNet Design via Differentiable Neural Architecture Search", in Proc. of CVPR, 2019. ΫϩεΤϯτϩϐʔ ॲཧ࣌ؒ

ଞʹ΋ <>)$BJ -;IV BOE4)BO 1SPYZMFTT/"4%JSFDU/FVSBM"SDIJUFDUVSF 4FBSDIPO5BSHFU5BTLBOE)BSEXBSF JO1SPDPG*$-3 <>.5BO #$IFO
31BOH 77BTVEFWBO .4BOEMFS ")PXBSE BOE27 -F .OBT/FU1MBUGPSN"XBSF/FVSBM"SDIJUFDUVSF4FBSDIGPS.PCJMF JO 1SPDPG$713 <>9%BJ FUBM $IBN/FU5PXBSET&⒏DJFOU/FUXPSL%FTJHOUISPVHI 1MBUGPSN"XBSF.PEFM"EBQUBUJPO JO1SPDPG$713 <>%4UBNPVMJT FUBM 4JOHMF1BUI/"4%FWJDF"XBSF&⒏DJFOU$POW/FU %FTJHO JO1SPDPG*$.-8

早期終了、動的計算グラフ (Early Termination, Dynamic Computation Graph)

ૣظऴྃ &BSMZUFSNJOBUJPO • ೖྗʹԠͯ͡ωοτϫʔΫͷ్தͰ݁ՌΛग़ྗ͠ɺ ͦΕҎ߱ͷॲཧΛߦΘͳ͍ʢૣظऴྃʣ • ೖྗʹԠͯ͡ωοτϫʔΫͷߏ଄Λಈతʹม͑Δ ʢಈతܭࢉάϥϑEZOBNJDDPNQVUBUJPOHSBQIʣ • ʮฏۉॲཧ࣌ؒʯΛ࡟ݮ͢Δ

#SBODIZ/FU<> • ωοτϫʔΫͷ్தʹ݁Ռͷग़ྗ૚Λ௥Ճ • ֶश࣌ʹ͸͢΂ͯͷग़ྗ૚ʹద౰ͳXFJHIUΛֶ͔͚ͯश • ͦͷTPGUNBYͷΤϯτϩϐʔ͕ᮢ஋ҎԼͷ৔߹ʹ&YJU [65] S.
Teerapittayanon, et al., "BranchyNet: Fast Inference via Early Exiting from Deep Neural Networks," in Proc. of ICPR, 2016.

4QBUJBMMZ"EBQUJWF$PNQVUBUJPO5JNF 4"$5 <> • "$5֤3FT#MPDL͕IBMUJOHTDPSFΛग़ྗɺ߹ܭ͕Λ௒͑Δͱ Ҏ߱ͷॲཧΛεΩοϓʢۭؒྖҬͰ΋ߦ͏ͱ4"$5ʣ ܭࢉྔʹؔ͢Δޯ഑Λ௥Ճ [66] M.
Figurnov, et al., "Spatially Adaptive Computation Time for Residual Networks," in Proc. of CVPR, 2017.

3VOUJNF/FVSBM1SVOJOH<> • ֤ϨΠϠຖʹɺ௚લ·Ͱͷಛ௃ϚοϓΛೖྗͱ͢Δ3//͕ ར༻͢Δ৞ΈࠐΈϑΟϧλू߹Λܾఆ • ,FFQͨ͠৞ΈࠐΈϑΟϧλ਺ͱݩλεΫͷଛࣦؔ਺ʢ࠷ऴ૚ͷ৔߹ ʣΛෛͷใुͱͯ͠2ֶशͰ3//Λֶश [68] J.
Lin, et al., "Runtime Neural Pruning," in Proc. of NIPS, 2017.

#MPDL%SPQ<> • 1PMJDZOFUXPSLʹը૾ΛೖྗɺͲͷ#MPDLΛεΩοϓ͢Δ͔Λग़ྗ • ,FFQͱͳͬͨ3FT#MPDLͷΈΛGPSXBSE • ೝ͕ࣦࣝഊͨ͠৔߹͸ෛͷใुΛɺ੒ޭͨ͠৔߹ʹ͸εΩοϓ཰ʹԠ ͨ͡ਖ਼ͷใुΛ༩͑Δ͜ͱͰQPMJDZOFUXPSLΛֶश [73]
Z. Wu, et al., "BlockDrop: Dynamic Inference Paths in Residual Networks," in Proc. of CVPR, 2018.

蒸留 (Distillation)

ৠཹ %JTUJMMBUJPO • େ͖ͳϞσϧ΍ɺෳ਺ͷωοτϫʔΫͷΞϯαϯϒϧΛ ʮڭࢣϞσϧʯͱ͠ɺখ͞ͳʮੜెϞσϧʯΛֶश • ڭࢣͷग़ྗ΍தؒಛ௃Λੜె͕໛ٖ͢ΔΑ͏ͳϩεΛ͔͚Δ 1. アンサンブルモデルや⼤
きなモデルを学習 2. 学習済みモデルを利⽤して⼩さなモデルを学習

%JTUJMMJOHUIF,OPXMFEHFJOB/FVSBM/FUXPSL<> … … 学習画像学習済みモデル学習するモデル … 正解ラベル（ハード
ターゲット） ௨ৗT = 1ͷsoftmaxͷTΛେ͖ͨ͘͠ ιϑτλʔήοτΛར༻ … ソフトターゲットソフトターゲットハードターゲット ਖ਼ղϥϕϧͱ ֶशϞσϧग़ྗͷ ྆ํΛར༻ [77] G. Hinton, et al., "Distilling the Knowledge in a Neural Network," in Proc. of NIPS Workshop, 2014.

'JU/FU<> • ڭࢣΑΓ΋EFFQ͔ͭUIJOͳੜెΛֶश͢Δ • ੜెͷHVJEFEMBZFS͕ɺڭࢣͷIJUMBZFSͷग़ྗΛ ਖ਼֬ʹ໛ٖ͢Δ SFHSFTTJPO ϩεΛ௥Ճ [79]
A. Romero, et al., "FitNets: Hints for Thin Deep Nets," in Proc. of ICLR, 2015.

量子化 (Quantization)

ྔࢠԽ • ωοτϫʔΫͷύϥϝʔλ౳ΛྔࢠԽ͢Δ͜ͱͰ ϞσϧαΠζΛ࡟ݮɺֶश΍ਪ࿦Λߴ଎Խ • ྔࢠԽର৅ • ॏΈɺΞΫςΟϕʔγϣϯʢಛ௃Ϛοϓʣɺޯ഑ɺΤϥʔ • ྔࢠԽख๏
• ઢܗɺMPHɺඇઢܗεΧϥɺϕΫτϧɺ௚ੵྔࢠԽ • ྔࢠԽϏοτ • CJUʢόΠφϦʣɺ஋ ɺCJUɺCJUɺ೚ҙCJU • ઐ༻ϋʔυ͕ͳ͍ͱԸܙΛड͚ΒΕͳ͍ࣄ͕ଟ͍ • ൒ਫ਼౓ࠞ߹ਫ਼౓ ͸൚༻ϋʔυˍϑϨʔϜϫʔΫͰ΋αϙʔτ * https://github.com/NVIDIA/apex

8"(&<> • XFJHIUT 8 BDUJWBUJPOT " HSBEJFOUT ( FSSPST &
ͷશͯΛྔࢠԽ [96] S. Wu, et al., "Training and Inference with Integers in Deep Neural Networks," in Proc. of ICLR, 2018.

8"(&<> • XFJHIUT 8 BDUJWBUJPOT " HSBEJFOUT ( FSSPST &
バイナリ [96] S. Wu, et al., "Training and Inference with Integers in Deep Neural Networks," in Proc. of ICLR, 2018.

2VBOUJ[BUJPOBOE5SBJOJOHPG/FVSBM/FUXPSLTGPS&⒏DJFOU*OUFHFS"SJUINFUJD0OMZ *OGFSFODF<> • ਪ࿦࣌ʹVJOUͷԋࢉ͕ϝΠϯͱͳΔΑ͏ʹ ֶश࣌ʹྔࢠԽΛγϛϡϨʔγϣϯ͠ͳ͕Βֶश • 5FOTPS'MPXެࣜʹ࣮૷͕ଘࡏ [97] B.
Jacob, et al., "Quantization and Training of Neural Networks for Efficient Integer-Arithmetic-Only Inference," in Proc. of CVPR, 2018. * https://github.com/tensorflow/tensorflow/blob/master/tensorflow/contrib/quantize/README.md

まとめ

൚༻తͳߴ଎Խख๏Λ঺հ • ৞ΈࠐΈͷ෼ղ 'BDUPSJ[BUJPO • ࢬמΓ 1SVOJOH • ΞʔΩςΫνϟ୳ࡧ /FVSBM"SDIJUFDUVSF4FBSDI/"4
• ૣظऴྃɺಈతܭࢉάϥϑ &BSMZ5FSNJOBUJPO %ZOBNJD$PNQVUBUJPO(SBQI • ৠཹ %JTUJMMBUJPO • ྔࢠԽ 2VBOUJ[BUJPO

5BLFIPNF.FTTBHF • ܰྔͳϞσϧʢ৞ΈࠐΈͷ෼ղʣΛ1SVOJOH͢Δͷ͕ खͬऔΓૣ͍ • /"4͕ॸຽͷखʹ • ΞʔΩςΫνϟͱϞσϧͷಉֶ࣌शʢ4JOHMFTIPUԽʣ • '-01TͰ͸ͳ࣮͘σόΠεͰͷ଎౓ΛϑΟʔυόοΫ
• ࠓޙ • 1SVOJOHͱ/"4ͷҰମԽ • ࢀߟ • ୈճεςΞϥϘਓ޻஌ೳηϛφʔ ʮ৞ΈࠐΈχϡʔϥϧωοτϫʔΫͷߴਫ਼౓Խͱߴ଎Խʯ

百選

৞ΈࠐΈͷ෼ղ <>-4JGSFBOE4.BMMBU 3PUBUJPO 4DBMJOHBOE%FGPSNBUJPO*OWBSJBOU4DBUUFSJOHGPS5FYUVSF%JTDSJNJOBUJPO JO1SPDPG$713 <>-4JGSF 3JHJENPUJPO4DBUUFSJOHGPS*NBHF$MBTTJpDBUJPO JO1I%UIFTJT
<>.-JO 2$IFO BOE4:BO /FUXPSLJO/FUXPSL JO1SPDPG*$-3 <>$4[FHFEZ FUBM 3FUIJOLJOHUIF*ODFQUJPO"SDIJUFDUVSFGPS$PNQVUFS7JTJPO JO1SPDPG$713 <>'/*BOEPMB 4)BO .8.PTLFXJD[ ,"TISBG 8+%BMMZ BOE,,FVU[FS 4RVFF[F/FU"MFY/FUMFWFMBDDVSBDZXJUIYGFXFSQBSBNFUFSTBOE.# NPEFMTJ[F JOBS9JW <>'$IPMMFU 9DFQUJPO%FFQMFBSOJOHXJUIEFQUIXJTFTFQBSBCMFDPOWPMVUJPOT JO1SPDPG$713 <>")PXBSE FUBM .PCJMF/FUT&⒏DJFOU$POWPMVUJPOBM/FVSBM/FUXPSLTGPS.PCJMF7JTJPO"QQMJDBUJPOT JOBS9JW <>9;IBOH FUBM 4IV⒐F/FU"O&YUSFNFMZ&⒏DJFOU$POWPMVUJPOBM/FVSBM/FUXPSLGPS.PCJMF%FWJDFT JOBS9JW <>#8V FUBM 4IJGU";FSP'-01 ;FSP1BSBNFUFS JOBS9JW <>/.B 9;IBOH );IFOH BOE+4VO 4IV⒐F/FU71SBDUJDBM(VJEFMJOFTGPS&⒏DJFOU$//"SDIJUFDUVSF%FTJHO JO1SPDPG&$$7 <>)(BP ;8BOH BOE4+J $IBOOFM/FUT$PNQBDUBOE&⒏DJFOU$POWPMVUJPOBM/FVSBM/FUXPSLTWJB$IBOOFM8JTF$POWPMVUJPOT JO1SPDPG/*14 <>()VBOH 4-JV -.BBUFO BOE,8FJOCFSHFS $POEFOTF/FU"O&⒏DJFOU%FOTF/FUVTJOH-FBSOFE(SPVQ$POWPMVUJPOT JO1SPDPG$713 <>.4BOEMFS FUBM .PCJMF/FU7*OWFSUFE3FTJEVBMTBOE-JOFBS#PUUMFOFDLT JO1SPDPG$713 <>(9JF +8BOH 5;IBOH +-BJ 3)POH BOE(2J *($7*OUFSMFBWFE4USVDUVSFE4QBSTF$POWPMVUJPOBM/FVSBM/FUXPSLT JO1SPDPG$713

৞ΈࠐΈͷ෼ղ <>5;IBOH (2J #9JBP BOE+8BOH *OUFSMFBWFEHSPVQDPOWPMVUJPOTGPSEFFQOFVSBMOFUXPSLT JO1SPDPG*$$7 <>;2JO ;;IBOH
9$IFO BOE:1FOH '%.PCJMF/FU*NQSPWFE.PCJMF/FUXJUIB'BTU%PXOTBNQMJOH4USBUFHZ JO1SPDPG*$*1 <>,4VO .-J %-JV BOE+8BOH *($7*OUFSMFBWFE-PX3BOL(SPVQ$POWPMVUJPOTGPS&⒏DJFOU%FFQ/FVSBM/FUXPSLT JO#.7$ <>5)F FUBM #BHPG5SJDLTGPS*NBHF$MBTTJpDBUJPOXJUI$POWPMVUJPOBM/FVSBM/FUXPSLT JO1SPDPG$713 <>:$IFO FUBM %SPQBO0DUBWF3FEVDJOH4QBUJBM3FEVOEBODZJO$POWPMVUJPOBM/FVSBM/FUXPSLTXJUI0DUBWF$POWPMVUJPO JOBS9JW <>")PXBSE FUBM 4FBSDIJOHGPS.PCJMF/FU7 JOBS9JW <>+;IBOH 4FFTBX/FU$POWPMVUJPO/FVSBM/FUXPSL8JUI6OFWFO(SPVQ$POWPMVUJPO JOBS9JW

ࢬמΓ <>:-F$VO +%FOLFS BOE44PMMB 0QUJNBM#SBJO%BNBHF JO1SPDPG/*14 <>4)BO +1PPM +5SBO
BOE8%BMMZ -FBSOJOHCPUI8FJHIUTBOE$POOFDUJPOTGPS&⒏DJFOU/FVSBM/FUXPSLT JO1SPDPG/*14 <>88FO $8V :8BOH :$IFO BOE)-J -FBSOJOH4USVDUVSFE4QBSTJUZJO%FFQ/FVSBM/FUXPSLT JO1SPDPG/*14 <>4)BO FUBM %FFQ$PNQSFTTJPO$PNQSFTTJOH%FFQ/FVSBM/FUXPSLTXJUI1SVOJOH 5SBJOFE2VBOUJ[BUJPOBOE)V⒎NBO$PEJOH JO1SPDPG*$-3 <>4)BO +1PPM +5SBO BOE8%BMMZ &*&&⒏DJFOU*OGFSFODF&OHJOFPO$PNQSFTTFE%FFQ/FVSBM/FUXPSL JO1SPDPG*4$" <>4"OXBS ,)XBOH BOE84VOH 4USVDUVSFE1SVOJOHPG%FFQ$POWPMVUJPOBM/FVSBM/FUXPSLT JO+&5$ <>4$IBOHQJOZP .4BOEMFS BOE";INPHJOPW 5IF1PXFSPG4QBSTJUZJO$POWPMVUJPOBM/FVSBM/FUXPSLT JOBS9JW <>44DBSEBQBOF %$PNNJOJFMMP ")VTTBJO BOE"6ODJOJ (SPVQ4QBSTF3FHVMBSJ[BUJPOGPS%FFQ/FVSBM/FUXPSLT JO/FVSPDPNQVUJOH <>)-J FUBM 1SVOJOH'JMUFSTGPS&⒏DJFOU$POW/FUT JO1SPDPG*$-3 <>1.PMDIBOPW 45ZSFF 5,BSSBT 5"JMB BOE+,BVU[ 1SVOJOH$POWPMVUJPOBM/FVSBM/FUXPSLTGPS3FTPVSDF&⒏DJFOU*OGFSFODF JO1SPDPG*$-3 <>%.PMDIBOPW ""TIVLIB BOE%7FUSPW 7BSJBUJPOBM%SPQPVU4QBSTJpFT%FFQ/FVSBM/FUXPSLT JO1SPDPG*$.- <>;-JV FUBM -FBSOJOH&⒏DJFOU$POWPMVUJPOBM/FUXPSLTUISPVHI/FUXPSL4MJNNJOH JO1SPDPG*$$7 <>:)F FUBM $IBOOFM1SVOJOHGPS"DDFMFSBUJOH7FSZ%FFQ/FVSBM/FUXPSLT JO1SPDPG*$$7 <>+-VP FUBM 5IJ/FU"'JMUFS-FWFM1SVOJOH.FUIPEGPS%FFQ/FVSBM/FUXPSL$PNQSFTTJPO JO1SPDPG*$$7 <>$-PVJ[PT ,6MMSJDI BOE.8FMMJOH #BZFTJBO$PNQSFTTJPOGPS%FFQ-FBSOJOH JO1SPDPG/*14

ࢬמΓ <>,JSJMM/FLMZVEPW %NJUSZ.PMDIBOPW "STFOJJ"TIVLIB %NJUSZ7FUSPW 4USVDUVSFE#BZFTJBO1SVOJOHWJB-PH/PSNBM.VMUJQMJDBUJWF/PJTF JO1SPDPG/*14 <>.;IVBOE4(VQUB 5PQSVOF
PSOPUUPQSVOFFYQMPSJOHUIFF⒏DBDZPGQSVOJOHGPSNPEFMDPNQSFTTJPO JO1SPDPG*$-38 <>5:BOH :$IFO BOE74[F %FTJHOJOH&OFSHZ&⒏DJFOU$POWPMVUJPOBM/FVSBM/FUXPSLT6TJOH&OFSHZ"XBSF1SVOJOH JO1SPDPG$713 <>:)F (,BOH 9%POH :'V BOE::BOH 4PGU'JMUFS1SVOJOHGPS"DDFMFSBUJOH%FFQ$POWPMVUJPOBM/FVSBM/FUXPSLT JO1SPDPG*+$"* <>:)F FUBM ".$"VUP.-GPS.PEFM$PNQSFTTJPOBOE"DDFMFSBUJPOPO.PCJMF%FWJDFT JO1SPDPG&$$7 <>5:BOH ")PXBSE #$IFO 9;IBOH "(P .4BOEMFS 74[F BOE)"EBN /FU"EBQU1MBUGPSN"XBSF/FVSBM/FUXPSL"EBQUBUJPOGPS.PCJMF "QQMJDBUJPOT JO1SPDPG&$$7 <>+-VPBOE+8V "VUP1SVOFS"O&OEUP&OE5SBJOBCMF'JMUFS1SVOJOH.FUIPEGPS&⒏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

ΞʔΩςΫνϟ୳ࡧ <>#;PQIBOE27-F /FVSBMBSDIJUFDUVSFTFBSDIXJUISFJOGPSDFNFOUMFBSOJOH JO1SPDPG*$-3 <>#;PQI 77BTVEFWBO +4IMFOT BOE27-F -FBSOJOHUSBOTGFSBCMFBSDIJUFDUVSFTGPSTDBMBCMFJNBHFSFDPHOJUJPO
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

ૣظऴྃɺಈతܭࢉάϥϑ <>:(VP ":BP BOE:$IFO %ZOBNJD/FUXPSL4VSHFSZGPS&⒏DJFOU%//T JO1SPDPG/*14 <>45FFSBQJUUBZBOPO FUBM #SBODIZ/FU'BTU*OGFSFODFWJB&BSMZ&YJUJOHGSPN%FFQ/FVSBM/FUXPSLT
JO1SPDPG*$13 <>.'JHVSOPW FUBM 4QBUJBMMZ"EBQUJWF$PNQVUBUJPO5JNFGPS3FTJEVBM/FUXPSLT JO1SPDPG$713 <>5#PMVLCBTJ +8BOH 0%FLFM BOE74BMJHSBNB "EBQUJWF/FVSBM/FUXPSLTGPS&⒏DJFOU*OGFSFODF JO1SPDPG*$.- <>+-JO FUBM 3VOUJNF/FVSBM1SVOJOH JO1SPDPG/*14 <>()VBOH %$IFO 5-J '8V -.BBUFO BOE,8FJOCFSHFS .VMUJ4DBMF%FOTF/FUXPSLTGPS3FTPVSDF&⒏DJFOU*NBHF$MBTTJpDBUJPO JO1SPDPG *$-3 <>98BOH ':V ;%PV 5%BSSFMM BOE+(PO[BMF[ 4LJQ/FU-FBSOJOH%ZOBNJD3PVUJOHJO$POWPMVUJPOBM/FUXPSLT JO1SPDPG&$$7 <>"7FJUBOE 4#FMPOHJF $POWPMVUJPOBM/FUXPSLTXJUI"EBQUJWF*OGFSFODF(SBQIT JO1SPDPG&$$7 <>--JVBOE+%FOH %ZOBNJD%FFQ/FVSBM/FUXPSLT0QUJNJ[JOH"DDVSBDZ&⒏DJFODZ5SBEF0⒎TCZ4FMFDUJWF&YFDVUJPO JO1SPDPG"""* <>;8V FUBM #MPDL%SPQ%ZOBNJD*OGFSFODF1BUITJO3FTJEVBM/FUXPSLT JO1SPDPG$713 <>3 :V FUBM /*411SVOJOH/FUXPSLTVTJOH/FVSPO*NQPSUBODF4DPSF1SPQBHBUJPO JO1SPDPG$713 <>+,VFO 9,POH ;-JO (8BOH +:JO 44FF BOE:5BO 4UPDIBTUJD%PXOTBNQMJOHGPS$PTU"EKVTUBCMF*OGFSFODFBOE*NQSPWFE3FHVMBSJ[BUJPOJO $POWPMVUJPOBM/FUXPSLT JO1SPDPG$713 <>9(BP :;IBP -%VE[JBL 3.VMMJOT BOE$9V %ZOBNJD$IBOOFM1SVOJOH'FBUVSF#PPTUJOHBOE4VQQSFTTJPO JO1SPDPG*$-3

ৠཹ <>()JOUPO FUBM %JTUJMMJOHUIF,OPXMFEHFJOB/FVSBM/FUXPSL JO1SPDPG/*148PSLTIPQ <>+#BBOE3$BSVBOB %P%FFQ/FUT3FBMMZ/FFEUPCF%FFQ JO1SPDPG/*14
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

ྔࢠԽ <>.$PVSCBSJBVY :#FOHJP BOE+%BWJE #JOBSZ$POOFDU5SBJOJOH%FFQ/FVSBM/FUXPSLTXJUICJOBSZXFJHIUTEVSJOHQSPQBHBUJPOT JO1SPDPG/*14 <>*)VCBSB .$PVSCBSJBVY
%4PVESZ 3&M:BOJW BOE:#FOHJP #JOBSJ[FE/FVSBM/FUXPSLT JO1SPDPG/*14 <>.3BTUFHBSJ 70SEPOF[+PTFQI BOE3'BSIBEJ 9/03/FU*NBHF/FU$MBTTJp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⒏DJFOU*OUFHFS"SJUINFUJD0OMZ*OGFSFODF JO1SPDPG$713 <>;-JV #8V 8-VP 9:BOH 8-JV BOE,$IFOH #J3FBM/FU&OIBODJOHUIF1FSGPSNBODFPGCJU$//T8JUI*NQSPWFE3FQSFTFOUBUJPOBM$BQBCJMJUZ BOE"EWBODFE5SBJOJOH"MHPSJUIN JO1SPDPG&$$7 <>/8BOH +$IPJ %#SBOE $$IFO BOE,(PQBMBLSJTIOBO 5SBJOJOH%FFQ/FVSBM/FUXPSLTXJUICJU'MPBUJOH1PJOU/VNCFST JO1SPDPG/*14 <>(:BOH FUBM 48"-14UPDIBTUJD8FJHIU"WFSBHJOHJO-PX1SFDJTJPO5SBJOJOH JO1SPDPG*$.-

モデル高速化百選

モデル高速化百選

More Decks by yu4u

Other Decks in Technology

Featured

Transcript