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
20170204-meganeco
Search
ARIYAMA Keiji
February 04, 2017
Technology
2
1.6k
20170204-meganeco
「TensorFlowで趣味の画像収集サーバーを作る 2017年2月号」
顔領域検出ネットワークを作成し、さくらの高火力サーバー上で動作させました。
ARIYAMA Keiji
February 04, 2017
Tweet
Share
More Decks by ARIYAMA Keiji
See All by ARIYAMA Keiji
Build with AI
keiji
0
150
DroidKaigi 2023
keiji
0
1.6k
TechFeed Conference 2022
keiji
0
230
Android Bazaar and Conference Diverse 2021 Winter
keiji
0
850
ci-cd-conference-2021
keiji
1
1.2k
Android Bazaar and Conference 2021 Spring
keiji
3
760
TFUG KANSAI 20190928
keiji
0
94
Softpia Japan Seminar 20190724
keiji
1
150
pixiv App Night 20190611
keiji
1
560
Other Decks in Technology
See All in Technology
Wantedly での Datadog 活用事例
bgpat
1
510
ハイテク休憩
sat
PRO
2
160
5分でわかるDuckDB
chanyou0311
10
3.2k
AWS re:Invent 2024で発表された コードを書く開発者向け機能について
maruto
0
190
Google Cloud で始める Cloud Run 〜AWSとの比較と実例デモで解説〜
risatube
PRO
0
110
どちらを使う?GitHub or Azure DevOps Ver. 24H2
kkamegawa
0
830
ゼロから創る横断SREチーム 挑戦と進化の軌跡
rvirus0817
2
270
マルチプロダクト開発の現場でAWS Security Hubを1年以上運用して得た教訓
muziyoshiz
3
2.4k
Oracle Cloudの生成AIサービスって実際どこまで使えるの? エンジニア目線で試してみた
minorun365
PRO
4
280
1等無人航空機操縦士一発試験 合格までの道のり ドローンミートアップ@大阪 2024/12/18
excdinc
0
160
10分で学ぶKubernetesコンテナセキュリティ/10min-k8s-container-sec
mochizuki875
3
350
MLOps の現場から
asei
6
650
Featured
See All Featured
Measuring & Analyzing Core Web Vitals
bluesmoon
4
170
BBQ
matthewcrist
85
9.4k
Embracing the Ebb and Flow
colly
84
4.5k
The Language of Interfaces
destraynor
154
24k
Sharpening the Axe: The Primacy of Toolmaking
bcantrill
38
1.9k
A Philosophy of Restraint
colly
203
16k
XXLCSS - How to scale CSS and keep your sanity
sugarenia
247
1.3M
Typedesign – Prime Four
hannesfritz
40
2.4k
Practical Tips for Bootstrapping Information Extraction Pipelines
honnibal
PRO
10
810
Adopting Sorbet at Scale
ufuk
73
9.1k
KATA
mclloyd
29
14k
Helping Users Find Their Own Way: Creating Modern Search Experiences
danielanewman
29
2.3k
Transcript
C-LIS CO., LTD.
༗ࢁܓೋʢ,FJKJ"3*:"."ʣ C-LIS CO., LTD. Androidアプリ開発者 機械学習初⼼心者 やってません Photo :
Koji MORIGUCHI (AUN CREATIVE FIRM) と、⾔言いながら早1年年……
ຊΛग़ͤ ιϑτɾڥ͕Ξοϓσʔτ͢Δ
None
None
None
C-LIS CO., LTD. IUUQBN[OUPC,3N 7/29発売
C-LIS CO., LTD.
None
5FOTPS'MPXͰ झຯͷը૾ऩूαʔόʔΛ࡞Δ ݄̎߸
Έͷ؟ڸ່ͬը૾Λ ࣗಈͰऩू͍ͨ͠
4PGUXBSF%FTJHO݄߸ʰ"OESPJE4UVEJPͷελΠϧͰޮΞοϓʱΑΓ ؟ ڸ ͬ ່ ࠜઇΕ͍
ݱࡏͷߏ Downloader Face Detection Megane Detection API 5FOTPS'MPX 確認・修正
認識結果 JSON ܇࿅ λΠϜϥΠϯ ϝσΟΞ データセット ܇࿅
C-LIS CO., LTD. ̎Ϋϥεྨ 1 0
؟ڸ່ͬσʔληοτ
݄ ؟ڸ່ͬը૾ຕ ඇ؟ڸ່ͬຕ ܭɿ ຕ ؟ڸ່ͬ ඇ؟ڸ່ͬ ޡݕग़ ؟ڸ່ͬ
ඇ؟ڸ່ͬ
݄ ؟ڸ່ͬը૾ ຕ ඇ؟ڸ່ͬ ຕ ܭɿ ຕ ؟ڸ່ͬ ඇ؟ڸ່ͬ
ෛྫʢإྖҬͰͳ͍ʣ ຕ
ϞσϧʢωοτϫʔΫʣ
σʔληοτ࡞ʢ5'3FDPSEʣ is_face: 1 is_megane: 1 is_face: 1 is_megane: 0
is_face: 0 is_megane: 0 ࠜઇΕ͍
EFG@DPOWFSU@UGSFDPSET QBUI JT@GBDF JT@NFHBOF PVUQVU@EJS IBTI JOEFY PSJHJOBM@GJMF@OBNF
GJMF@OBNFPTQBUICBTFOBNF QBUI XJUIPQFO QBUI SC BTJNBHF PVUQVU@QBUIPTQBUIKPJO PVUQVU@EJS TEUGSFDPSE IBTI JOEFY XJUIUGQZUIPO@JP5'3FDPSE8SJUFS PVUQVU@QBUI BTXSJUFS FYBNQMFUGUSBJO&YBNQMF GFBUVSFTUGUSBJO'FBUVSFT GFBUVSF\ GJMF@OBNF@CZUFT@GFBUVSF GJMF@OBNFFODPEF PSJHJOBM@GJMF@OBNF@CZUFT@GFBUVSF PSJHJOBM@GJMF@OBNFFODPEF JT@GBDF@JOU@GFBUVSF JT@GBDF JT@NFHBOF@JOU@GFBUVSF JT@NFHBOF JNBHF@CZUFT@GFBUVSF JNBHFSFBE ^ XSJUFSXSJUF FYBNQMF4FSJBMJ[F5P4USJOH σʔληοτ࡞ʢ5'3FDPSEʣ
إೝࣝ༻ͷϞσϧ DPO YY DPO YY GD QPPM Y
DPO YY DPO YY QPPM Y GD PVUQVU MSO MSO Y
SFTIBQFUGSFTIBQF QPPM <CBUDI@TJ[F > EJNSFTIBQFHFU@TIBQF <>WBMVF GD@GD GD
JOQVU@MBZFSSFTIBQF XFJHIUT@TIBQF<EJN > XFJHIU@TUEEFW CJBTFT@TIBQF<> CJBTFT@WBMVF LFFQ@QSPCLFFQ@QSPC શ݁߹ͷೖྗ
܇࿅ 12万ステップ学習後のテストデータによる正答率 96%
؟ڸ່ͬೝࣝ༻ͷϞσϧ 7((/FUΛࢀߟʹΈࠐΈͷ࿈ଓΛ༻͍ͨ $//ʢ$POWPMVUJPOBM/FVSBM/FUXPSLʣϞσϧ DPO YY DPO YY GD
QPPM Y DPO YY DPO YY QPPM Y GD GD PVUQVU
܇࿅ ֶशΞϧΰϦζϜ"EBN ֶश ϛχόον
ݕূ σʔληοτ͔ΒΛςετ༻ͱͯ͠ ਖ਼ʙ
%BUB"VHNFOUBUJPO ը૾Λ ʜ·ͰɺͦΕͧΕճసͨ͠ը૾Λ࡞ ಡΈࠐΈ࣌ͷॲཧ 3BOEPN$SPQʢQYதɺQYྖҬͰ͘Γൈ͘ʣ 3BOEPN'MJQʢԣ࣠ํʹసʣ 3BOEPN6Q%PXOʢॎ࣠ํʹసʣ 3BOEPN#SJHIUOFTT 3BOEPN$POUSBTU
EFG@EJTUPSU JNBHF DSPQ@TJ[F/POF JNBHF@DIBOOFMT CSJHIUOFTT@NBY@EFMUB DPOUSBTU@MPXFS
DPOUSBTU@VQQFS XJUIUGOBNF@TDPQF EJTUPSU BTTDPQF EJTUPSUFE@JNBHFUGDBTU JNBHF UGGMPBU JGDSPQ@TJ[F EJTUPSUFE@JNBHFUGSBOEPN@DSPQ EJTUPSUFE@JNBHF <DSPQ@TJ[F DSPQ@TJ[F > EJTUPSUFE@JNBHFUGJNBHFSBOEPN@GMJQ@MFGU@SJHIU EJTUPSUFE@JNBHF EJTUPSUFE@JNBHFUGJNBHFSBOEPN@GMJQ@VQ@EPXO EJTUPSUFE@JNBHF EJTUPSUFE@JNBHFUGJNBHFSBOEPN@CSJHIUOFTT EJTUPSUFE@JNBHF NBY@EFMUBCSJHIUOFTT@NBY@EFMUB EJTUPSUFE@JNBHFUGJNBHFSBOEPN@DPOUSBTU EJTUPSUFE@JNBHF MPXFSDPOUSBTU@MPXFS VQQFSDPOUSBTU@VQQFS SFUVSOEJTUPSUFE@JNBHF
ʮީิྖҬʯͷΓग़͕͠ඞཁ
C-LIS CO., LTD. ࠜઇΕ͍
C-LIS CO., LTD. ࠜઇΕ͍ 4MJEJOH8JOEPX
C-LIS CO., LTD. 4FMFDUJWF4FBSDI ࠜઇΕ͍
C-LIS CO., LTD. 4FMFDUJWF4FBSDI ʢҾ༻4FMFDUJWF4FBSDIGPS0CKFDU3FDPHOJUJPOIUUQTJWJGOXJVWBOMJTJTQVCMJDBUJPOTCJCUFYCSPXTFSQIQ LFZ6JKMJOHT*+$7CJCBMMCJCʣ
C-LIS CO., LTD. 4FMFDUJWF4FBSDI "MQBDBࣾʹΑΔ࣮ IUUQCMPHKQBMQBDBBJFOUSZ EMJCͷ࣮ IUUQTHJUIVCDPNEBWJTLJOHEMJCCMPCNBTUFS QZUIPO@FYBNQMFTpOE@DBOEJEBUF@PCKFDU@MPDBUJPOTQZ
ݱࡏͷߏ Downloader Face Detection Megane Detection API 5FOTPS'MPX 確認・修正
認識結果 JSON ܇࿅ λΠϜϥΠϯ ϝσΟΞ データセット ܇࿅
إఆʢ'BDF%FUFDUJPOʣͷ Λ্͍͛ͨ
'BTU3$// 'BTUFS3$//
σʔληοτʢ5'3FDPSEʣ ࠜઇΕ͍
ΦʔτΤϯίʔμʢࣗݾූ߸ثʣ DPOW YY DPOW YY DPOW YY DPOW YY
DPOW YY EDPOW YY EDPOW YY EDPOW YY EFDPOW@MBTU YY EDPOW YY ࠜઇΕ͍
EFG@@WBSJBCMF@PO@DQV OBNF TIBQF JOJUJBMJ[FS XJUIUGEFWJDF DQV WBSUGHFU@WBSJBCMF OBNF
TIBQF JOJUJBMJ[FSJOJUJBMJ[FS SFUVSOWBS EFG@HFU@XFJHIUT TIBQF TUEEFW WBS@@WBSJBCMF@PO@DQV XFJHIUT TIBQF UGUSVODBUFE@OPSNBM@JOJUJBMJ[FS TUEEFWTUEEFW SFUVSOWBS EFG@HFU@CJBTFT TIBQF WBMVF WBS@@WBSJBCMF@PO@DQV CJBTFT TIBQF UGDPOTUBOU@JOJUJBMJ[FS WBMVF SFUVSOWBS
EFG@DPOW OBNF JOQVU@MBZFS XFJHIUT@TIBQF XFJHIU@TUEEFW CJBTFT@TIBQF CJBTFT@WBMVF QBEEJOH7"-*%
XJUIUGWBSJBCMF@TDPQF OBNF BTTDPQF XFJHIUT@HFU@XFJHIUT XFJHIUT@TIBQF TUEEFWXFJHIU@TUEEFW CJBTFT@HFU@CJBTFT CJBTFT@TIBQF WBMVFCJBTFT@WBMVF DPOWUGOODPOWE JOQVU@MBZFS XFJHIUT < > QBEEJOHQBEEJOH CJBTUGOOCJBT@BEE DPOW CJBTFT DPOWUGOOSFMV CJBT OBNFTDPQFOBNF @BDUJWBUJPO@TVNNBSZ DPOW SFUVSODPOW
EFG@EDPOW OBNF JOQVU@MBZFS PVUQVU@TIBQFT XFJHIUT@TIBQF XFJHIU@TUEEFW CJBTFT@TIBQF CJBTFT@WBMVF
QBEEJOH7"-*% BDUJWBUF@GVODUJPOSFMV XJUIUGWBSJBCMF@TDPQF OBNF BTTDPQF XFJHIUT@HFU@XFJHIUT XFJHIUT@TIBQF TUEEFWXFJHIU@TUEEFW CJBTFT@HFU@CJBTFT CJBTFT@TIBQF WBMVFCJBTFT@WBMVF EDPOWUGOODPOWE@USBOTQPTF JOQVU@MBZFS XFJHIUT PVUQVU@TIBQFT < > QBEEJOHQBEEJOH CJBTUGOOCJBT@BEE DPOW CJBTFT JGBDUJWBUF@GVODUJPOTJHNPJE EDPOWUGOOTJHNPJE CJBT OBNFTDPQFOBNF FMJGBDUJWBUF@GVODUJPOTPGUTJHO EDPOWUGOOTPGUTJHO CJBT OBNFTDPQFOBNF FMTF EDPOWUGOOSFMV CJBT OBNFTDPQFOBNF @BDUJWBUJPO@TVNNBSZ EDPOW SFUVSOEDPOW
EFGJOGFSFODF JNBHF@OPEF JNBHF@TJ[F DIBOOFMT CBUDI@TJ[F DPOW@DPOW DPOW JOQVU@MBZFSJNBHF@OPEF
XFJHIUT@TIBQF< DIBOOFMT > XFJHIU@TUEEFWF CJBTFT@TIBQF<> CJBTFT@WBMVF QBEEJOH7"-*% DPOW@DPOW DPOW JOQVU@MBZFSDPOW XFJHIUT@TIBQF< > XFJHIU@TUEEFWF CJBTFT@TIBQF<> CJBTFT@WBMVF QBEEJOH7"-*% DPOW@DPOW DPOW JOQVU@MBZFSDPOW XFJHIUT@TIBQF< > XFJHIU@TUEEFWF CJBTFT@TIBQF<> CJBTFT@WBMVF QBEEJOH7"-*% DPOW@DPOW DPOW JOQVU@MBZFSDPOW XFJHIUT@TIBQF< > XFJHIU@TUEEFWF CJBTFT@TIBQF<> CJBTFT@WBMVF QBEEJOH7"-*% DPOW@DPOW DPOW JOQVU@MBZFSDPOW XFJHIUT@TIBQF< > XFJHIU@TUEEFWF CJBTFT@TIBQF<> CJBTFT@WBMVF QBEEJOH7"-*%
TIBQFTDPOWHFU@TIBQF EDPOW@EDPOW EFDPOW JOQVU@MBZFSDPOW PVUQVU@TIBQFT<CBUDI@TJ[F JOU TIBQFT<>
JOU TIBQFT<> > XFJHIUT@TIBQF< > XFJHIU@TUEEFWF CJBTFT@TIBQF<> CJBTFT@WBMVF QBEEJOH7"-*% TIBQFTDPOWHFU@TIBQF EDPOW@EDPOW EFDPOW JOQVU@MBZFSEDPOW PVUQVU@TIBQFT<CBUDI@TJ[F JOU TIBQFT<> JOU TIBQFT<> > XFJHIUT@TIBQF< > XFJHIU@TUEEFWF CJBTFT@TIBQF<> CJBTFT@WBMVF QBEEJOH7"-*% TIBQFTDPOWHFU@TIBQF EDPOW@EDPOW EFDPOW JOQVU@MBZFSEDPOW PVUQVU@TIBQFT<CBUDI@TJ[F JOU TIBQFT<> JOU TIBQFT<> > XFJHIUT@TIBQF< > XFJHIU@TUEEFWF CJBTFT@TIBQF<> CJBTFT@WBMVF QBEEJOH7"-*%
TIBQFTDPOWHFU@TIBQF EDPOW@EDPOW EFDPOW JOQVU@MBZFSEDPOW PVUQVU@TIBQFT<CBUDI@TJ[F JOU TIBQFT<>
JOU TIBQFT<> > XFJHIUT@TIBQF< > XFJHIU@TUEEFWF CJBTFT@TIBQF<> CJBTFT@WBMVF QBEEJOH7"-*% EDPOW@MBTU@EDPOW EDPOW@MBTU JOQVU@MBZFSEDPOW PVUQVU@TIBQFT<CBUDI@TJ[F JNBHF@TJ[F JNBHF@TJ[F DIBOOFMT> XFJHIUT@TIBQF< DIBOOFMT > XFJHIU@TUEEFWF CJBTFT@TIBQF<DIBOOFMT> CJBTFT@WBMVF QBEEJOH7"-*% SFUVSOEDPOW@MBTU
σʔληοτʢ5'3FDPSEʣ ࠜઇΕ͍
EFG@@DPOWFSU@UGSFDPSET JNBHF@QBUI NBTL@QBUI PVUQVU@QBUI GJMF@OBNFPTQBUICBTFOBNF JNBHF@QBUI XJUIPQFO
JNBHF@QBUI SC BTJNBHF JNBHF@EBUBJNBHFSFBE XJUIPQFO NBTL@QBUI SC BTJNBHF NBTL@EBUBJNBHFSFBE XJUIUGQZUIPO@JP5'3FDPSE8SJUFS PVUQVU@QBUI BTXSJUFS FYBNQMFUGUSBJO&YBNQMF GFBUVSFTUGUSBJO'FBUVSFT GFBUVSF\ GJMF@OBNF@CZUFT@GFBUVSF GJMF@OBNFFODPEF JNBHF@CZUFT@GFBUVSF JNBHF@EBUB NBTL@CZUFT@GFBUVSF NBTL@EBUB ^ XSJUFSXSJUF FYBNQMF4FSJBMJ[F5P4USJOH σʔληοτʢ5'3FDPSEʣ
EFG@@EJTUPSU JNBHF NBTL@JNBHF CSJHIUOFTT@NBY@EFMUB DPOUSBTU@MPXFS DPOUSBTU@VQQFS
XJUIUGOBNF@TDPQF EJTUPSU BTTDPQF EJTUPSUFE@JNBHFUGDBTU JNBHF UGGMPBU EJTUPSUFE@JNBHFUGJNBHFSBOEPN@CSJHIUOFTT EJTUPSUFE@JNBHF NBY@EFMUBCSJHIUOFTT@NBY@EFMUB EJTUPSUFE@JNBHFUGJNBHFSBOEPN@DPOUSBTU EJTUPSUFE@JNBHF MPXFSDPOUSBTU@MPXFS VQQFSDPOUSBTU@VQQFS %BUB"VHNFOUBUJPO
%BUB"VHNFOUBUJPO ࠜઇΕ͍
XJUIUGOBNF@TDPQF SBOEPN@GMJQ@MFGU@SJHIU BTTDPQF SBOEPNUGSBOEPN@VOJGPSN EUZQFUGGMPBU EJTUPSUFE@JNBHFUGDPOE SBOEPN
MBNCEBUGJNBHFGMJQ@MFGU@SJHIU EJTUPSUFE@JNBHF MBNCEBEJTUPSUFE@JNBHF NBTL@JNBHFUGDPOE SBOEPN MBNCEBUGJNBHFGMJQ@MFGU@SJHIU NBTL@JNBHF MBNCEBNBTL@JNBHF XJUIUGOBNF@TDPQF SBOEPN@GMJQ@VQ@EPXO BTTDPQF SBOEPNUGSBOEPN@VOJGPSN EUZQFUGGMPBU EJTUPSUFE@JNBHFUGDPOE SBOEPN MBNCEBUGJNBHFGMJQ@VQ@EPXO EJTUPSUFE@JNBHF MBNCEBEJTUPSUFE@JNBHF NBTL@JNBHFUGDPOE SBOEPN MBNCEBUGJNBHFGMJQ@VQ@EPXO NBTL@JNBHF MBNCEBNBTL@JNBHF SFUVSOEJTUPSUFE@JNBHF NBTL@JNBHF
JNBHF NBTL@JNBHF@@MPBE@JNBHF GJMF@MJTU JNBHF@TJ[FJNBHF@TJ[F EJTUPSU5SVF TIVGGMF5SVF
JNBHF@CBUDI MBCFM@CBUDIUGUSBJOTIVGGMF@CBUDI <JNBHF NBTL@JNBHF> CBUDI@TJ[F'-"(4CBUDI@TJ[F DBQBDJUZDBQBDJUZ NJO@BGUFS@EFRVFVF'-"(4NJO@BGUFS@EFRVFVF OVN@UISFBET'-"(4OVN@UISFBET JNBHF@CBUDIJNBHF@CBUDI MBCFM@CBUDIMBCFM@CBUDI σʔλͷಡΈࠐΈ
EFG@@MPTT MPHJUT MBCFMT MPTTUGOOM@MPTT MPHJUTMBCFMT '-"(4CBUDI@TJ[F UGBEE@UP@DPMMFDUJPO MPTTFT MPTT
MPTTFTUGHFU@DPMMFDUJPO MPTTFT UPUBM@MPTTUGBEE@O MPTTFT OBNFUPUBM@MPTT ޡࠩ
ֶशʢ܇࿅ʣ ֶशΞϧΰϦζϜ"EBN0QUJNJ[FS ֶश ϛχόοναΠζ
ֶशʢ܇࿅ʣ
ݕূ
ࠜઇΕ͍
C-LIS CO., LTD. 4FMFDUJWF4FBSDI MCQDBTDBEF@BOJNFGBDFYNM ࠜઇΕ͍
ࠜઇΕ͍
ࠜઇΕ͍
͏·͍ͬͨ͘ɻ ͱ͜ΖͰʜʜ
݄ σΟʔϓϥʔχϯάʹΑΔࣗવݴޠॲཧͱνϟοτ#05ͷجૅ http://ascii.jp/elem/000/001/418/1418261/ ɹߨࢣɺʰ1ZUIPOͰମݧ͢ΔਂֶशʱʢίϩφࣾʣɺʰσΟʔϓϥʔχϯ άɺϏοάσʔλɺػցֶश͋Δ͍ͦͷ৺ཧֶʱʢ৽༵ࣾʣͷஶऀͰ͋Γɺ ਓೳֶձݚڀձ༏लʢ4*(-4&͜ͱֶݚڀձʮχϡʔϥϧ ωοτϫʔΫޠੜϞσϧʯ୯ஶʣΛडͷઙ৳Ұࢯɺʰ5FOTPS'MPX ͡Ί·࣮ͨ͠ફʂ࠷৽(PPHMFϚγϯϥʔχϯάʱʢΠϯϓϨε3%ɾ /FYU1VCMJTIJOHʣͷ༗ࢁܓೋࢯͰ͢ɻ
:0-03FBM5JNF0CKFDU%FUFDUJPO You only look once (YOLO) is a state-of-the-art, real-time
object detection system. On a Titan X it processes images at 40-90 FPS and has a mAP on VOC 2007 of 78.6% and a mAP of 44.0% on COCO test-dev. http://pjreddie.com/darknet/yolo/
ୈճશΞʔΩςΫνϟษڧձ ʙࣦޠΛΊ͙ͬͯʙ ɹ࣌ɿ݄ʢʣʢ։ʣ ɹॴɿגࣜձࣾϦΫϧʔτςΫϊϩδʔζΞΧσϛʔϗʔϧ ౦ژઍాؙ۠ͷάϥϯτΩϣαελϫʔ' IUUQXXXSFDSVJUKQDPNQBOZBCPVUP⒏DFIUNM ʢגࣜձࣾϦΫϧʔτςΫϊϩδʔζ༷ͷ͝ްҙʹΑΔձ͝ఏڙʣ ఆɹһɿҰൠʢࣾձਓ͓Αͼֶੜͷํʣ໊ɹֶੜ໊ ˞ఆһʹୡ࣍͠ୈకΊΒ͖ͤͯ·͢ ˞ֶੜͷํઌֶͣੜ͔Β͓ਃ͠ࠐΈԼ͍͞ɻֶੜ͕ຬ੮ͷ߹Ұൠ͔Βਃ͠ࠐΊ·͢ɻ
ࢀՃඅɿແྉ ओɹ࠵ɿ/10๏ਓશΞʔΩςΫνϟɾΠχγΞςΟϒ ޙɹԉɿגࣜձࣾυϫϯΰ https://wba-meetup.doorkeeper.jp/events/57007/
͜ͷํ๏ͷ՝
ֶशʹ͕͔͔࣌ؒΔ
ࠜઇΕ͍
ೖྗը૾͕খ͗͢͞Δ 192x192 ࠜઇΕ͍
ೖྗΛେ͖͘͢Δͱ 0VU0G.FNPSZ&SSPS
ݱࡏͷ(16 Graphic Memory: 2 GB compute capability: 5.2 (F'PSDF(59
όοναΠζΛେ͖͘͢Δͱ00.
̏νϟϯωϧʹ͢Δͱʢུ
৽͍͠(16Λߪೖ͢Δʁ (16ͷՁ֨ (16ΛΠϯετʔϧ͢Δ1$ 1$Λஔ͘ॴ Քಇ͓ͤͯ͘͞ిؾ
͘͞ΒͷߴՐྗίϯϐϡʔςΟϯά https://blog.keiji.io/2016/12/tensorflow_advent_calendar.html 「さくらの⾼高⽕火⼒力力」でTensorFlow
τϥΠΞϧ൛ʢ.BYXFMMΞʔΩςΫνϟʣ https://www.sakura.ad.jp/koukaryoku/ 9FPO$PSFʷ .FNPSZ(# 44%(#ʷ̎ 3"*% (F'PSDF(595*5"/9ʢ.BYXFMM (SBQIJD.FNPSZ(#ʣʷ̐
+-----------------------------------------------------------------------------+ | NVIDIA-SMI 367.57 Driver Version: 367.57 | |-------------------------------+----------------------+----------------------+ |
GPU Name Persistence-M| Bus-Id Disp.A | Volatile Uncorr. ECC | | Fan Temp Perf Pwr:Usage/Cap| Memory-Usage | GPU-Util Compute M. | |===============================+======================+======================| | 0 GeForce GTX TIT... Off | 0000:02:00.0 Off | N/A | | 22% 43C P2 144W / 250W | 11688MiB / 12206MiB | 88% Default | +-------------------------------+----------------------+----------------------+ | 1 GeForce GTX TIT... Off | 0000:03:00.0 Off | N/A | | 22% 35C P5 20W / 250W | 11605MiB / 12206MiB | 0% Default | +-------------------------------+----------------------+----------------------+ | 2 GeForce GTX TIT... Off | 0000:83:00.0 Off | N/A | | 22% 35C P5 19W / 250W | 11605MiB / 12206MiB | 0% Default | +-------------------------------+----------------------+----------------------+ | 3 GeForce GTX TIT... Off | 0000:84:00.0 Off | N/A | | 22% 34C P5 19W / 250W | 11603MiB / 12206MiB | 0% Default | +-------------------------------+----------------------+----------------------+ ͬͦͬͯ͘͞ΈΔ
EFG@@MPTT MPHJUT MBCFMT MPTTUGOOM@MPTT MPHJUTMBCFMT '-"(4CBUDI@TJ[F UGBEE@UP@DPMMFDUJPO MPTTFT MPTT
MPTTFTUGHFU@DPMMFDUJPO MPTTFT UPUBM@MPTTUGBEE@O MPTTFT OBNFUPUBM@MPTT MPTT@BWFSBHFTUGUSBJO&YQPOFOUJBM.PWJOH"WFSBHF OBNFBWH MPTT@BWFSBHFT@PQMPTT@BWFSBHFTBQQMZ MPTTFT <UPUBM@MPTT> XJUIUGDPOUSPM@EFQFOEFODJFT <MPTT@BWFSBHFT@PQ> UPUBM@MPTTUGJEFOUJUZ UPUBM@MPTT SFUVSOUPUBM@MPTT .VMUJ(16ରԠ https://blog.keiji.io/2016/12/tensorflow_advent_calendar.html
DJGBS@NVMUJ@HQV@USBJOQZCSFBLTXJUINPSFUIBO(16 https://github.com/tensorflow/tensorflow/issues/5652
EFG@@MPTT MPHJUT MBCFMT MPTTUGOOM@MPTT MPHJUTMBCFMT '-"(4CBUDI@TJ[F UGBEE@UP@DPMMFDUJPO MPTTFT MPTT
MPTTFTUGHFU@DPMMFDUJPO MPTTFT UPUBM@MPTTUGBEE@O MPTTFT OBNFUPUBM@MPTT IUUQTHJUIVCDPNUFOTPSGMPXUFOTPSGMPXJTTVFT SFUVSOUPUBM@MPTT .VMUJ(16ରԠ https://github.com/tensorflow/tensorflow/issues/5652
+-----------------------------------------------------------------------------+ | NVIDIA-SMI 367.57 Driver Version: 367.57 | |-------------------------------+----------------------+----------------------+ |
GPU Name Persistence-M| Bus-Id Disp.A | Volatile Uncorr. ECC | | Fan Temp Perf Pwr:Usage/Cap| Memory-Usage | GPU-Util Compute M. | |===============================+======================+======================| | 0 GeForce GTX TIT... Off | 0000:02:00.0 Off | N/A | | 22% 40C P2 100W / 250W | 11688MiB / 12206MiB | 46% Default | +-------------------------------+----------------------+----------------------+ | 1 GeForce GTX TIT... Off | 0000:03:00.0 Off | N/A | | 22% 40C P2 121W / 250W | 11688MiB / 12206MiB | 35% Default | +-------------------------------+----------------------+----------------------+ | 2 GeForce GTX TIT... Off | 0000:83:00.0 Off | N/A | | 22% 38C P2 111W / 250W | 11688MiB / 12206MiB | 24% Default | +-------------------------------+----------------------+----------------------+ | 3 GeForce GTX TIT... Off | 0000:84:00.0 Off | N/A | | 22% 38C P2 132W / 250W | 11687MiB / 12206MiB | 40% Default | +-------------------------------+----------------------+----------------------+ .VMUJ(16ରԠޙͷOWJEJBTNJ
̍࣌ؒͰ̍ສεςοϓ
̐Ͱ̒ສ̓ઍεςοϓ
Oഒͷεϐʔυʂ
ೖྗը૾ΛQYʹͯ͠ 00.͕ൃੜ͠ͳ͍ʂ
࣍ճ༧ࠂ QYͷը૾Ͱֶशʢ܇࿅ʣ͠ɺإྖҬͷݕग़ਫ਼ͷมԽΛ֬ೝ͢Δɻ ϞσϧͷΈࠐΈͷϑΟϧλʔαΠζΛௐ͢Δ ʢೖྗը૾ʹରͯ͠ϑΟϧλʔ͕খ͗͢͞Δʣ ʮإྖҬݕग़ʯͱʮ؟ڸ່ͬఆʯΛಉ࣌ʹߦ͏Α͏ʹมߋ͢Δɻ
ٕज़ॻయ̎ 5FOTPS'MPXຊΛ൦͠·͢ https://goo.gl/JXXGkg ݄̐̕ʢʣ ΞΩόɾεΫΤΞ ͓ʵ
C-LIS CO., LTD. ໊֤ɾϒϥϯυ໊ɺձ໊ࣾͳͲɺҰൠʹ֤ࣾͷඪ·ͨొඪͰ͢ɻຊࢿྉதͰɺɺɺäΛׂѪ͍ͯ͠·͢ɻ ຊࢿྉɺ༗ݶձࣾγʔϦεͷஶ࡞Ͱ͢ɻܝࡌ͞Ε͍ͯΔΠϥετɺಛʹهࡌ͕ͳ͍߹ࠜઇΕ͍ͷஶ࡞Ͱ͢ɻ ຊࢿྉͷશ෦ɺ·ͨҰ෦ʹ͍ͭͯɺஶ࡞ऀ͔ΒจॻʹΑΔڐΛಘͣʹෳ͢Δ͜ͱې͡ΒΕ͍ͯ·͢ɻ