20170419-TFUG

4月19日のTensorFlow User Groupの発表資料です。

Transcript

1. C-LIS CO., LTD.
2. C-LIS CO., LTD.  ༗ࢁ
   ܓೋ
   ʢ,FJKJ
   "3*:"."ʣ $-*4
   $0
   -5%
   "OESPJEΞϓϦ։ൃνϣοτσΩϧ
   ػցֶशॳ৺ऀ
   ͱɺݴ͍ଓ͚ͯૣ̍೥൒ Photo : Koji MORIGUCHI (AUN CREATIVE FIRM)
4.  ݄̐̕೔ʢ೔ʣ ΞΩόɾεΫΤΞ ʰٕज़ॻయ̎ ͓ʔ̍̎ʱʹͯ TensorFlow͸͡Ί·ͨ͠
 Super Resolution ʔ ௒ղ૾ https://goo.gl/Z3Exjo ׬ച͠·ͨ͠
5. ৞ΈࠐΈΦʔτΤϯίʔμʔ  conv1 9x9x3 64 padding: SAME conv2 9x9x64 128 conv4 5x5x128 64 conv3-0 7x7x128 128 conv3-1 7x7x128 128 dconv1 9x9x64 3 padding: SAME dconv2 9x9x128 64 dconv4 5x5x64 128 dconv3-1 7x7x128 128 dconv3-2 7x7x128 128 conv3-2 7x7x128 128 dconv3-2 7x7x128 128 256x256 256x256
7. 
   5FOTPS'MPX
   6TFS
   (SPVQ  5FOTPS'MPX
 (16
   
8.  5FOTPS'MPXͱ(16
9. લఏ৚݅ (16
   $6%"
   $PNQVUF
   $BQBCJMJUZ
   
   
   
   $6%"
   5PPMLJU
   
   DV%//
   W
   
   QJQ
   JOTUBMM
   UFOTPSqPXHQV  https://www.tensorflow.org/install/install_linux
10. (16΁ͷॲཧͷׂΓ౰ͯ XJUI
    UGEFWJDF HQVE
    
    J 

    
    QBTT
 
11. Ϛϧν(16
    UPXFS@HSBET
    
    <>
    
    GPS
    J
    JO
    SBOHF '-"(4OVN@HQVT 

    
    
    
    XJUI
    UGEFWJDF HQVE
    
    J 

    
    
    
    
    
    XJUI
    UGOBNF@TDPQF T@E
    
    508&3@/".&
    J
    BT
    TDPQF

    
    
    
    
    
    
    
    MPTT
    
    @@UPXFS@MPTT TDPQF
    GJMF@MJTU 

    
    
    
    
    
    
    
    
    
    
    
    
    
    
    
    
    
    
    
    
    
    
    
    
    
    
    
    .0%&-*/165@4*;&
    .0%&-065165@4*;& 

    
    
    
    
    
    
    
    
    
    
    
    
    
    
    
    
    
    
    
    
    
    
    
    
    
    
    
    '-"(4CBUDI@TJ[F 
 

    
    
    
    
    
    
    
    UGTVNNBSZTDBMBS UPUBM@MPTT
    MPTT 
 

    
    
    
    
    
    
    
    UGHFU@WBSJBCMF@TDPQF SFVTF@WBSJBCMFT 
 

    
    
    
    
    
    
    
    HSBET
    
    PQUDPNQVUF@HSBEJFOUT MPTT 

    
    
    
    
    
    
    
    UPXFS@HSBETBQQFOE HSBET 
12. Ϛϧν(16 BWH@HSBET
    
    @@BWFSBHF@HSBEJFOUT UPXFS@HSBET 
 
 BQQMZ@HSBEJFOU@PQ
    
    @@BQQMZ@HSBEJFOUT BWH@HSBET
    PQU
    HMPCBM@TUFQ 
 
 WBSJBCMF@BWFSBHFT
    
    UGUSBJO&YQPOFOUJBM.PWJOH"WFSBHF  

    
    
    
    
    
    
    
    
    
    
    
    
    
    
    
    
    
    
    
    
    
    
    
    
    
    
    
    
    
    
    
    
    
    
    
    
    
    
    
    
    
    
    
    
    
    
    
    
    
    
    
    
    
    HMPCBM@TUFQ 
 WBSJBCMFT@BWFSBHFT@PQ
    
    WBSJBCMF@BWFSBHFTBQQMZ UGUSBJOBCMF@WBSJBCMFT 
 
 USBJO@PQ
    
    UGHSPVQ BQQMZ@HSBEJFOU@PQ
    WBSJBCMFT@BWFSBHFT@PQ 
13. 5FOTPS#PBSE
14. (16̍ͭʹׂΓ౰ͯΔॲཧ Input Pipeline tf.train.shuffle_batch Ϟσϧ
 model.inference ޡࠩؔ਺
 __loss ޯ഑ͷܭࢉ
 compute_gradient __tower_loss ޯ഑ ʢgradsʣ ֶश
 σʔλ ڭࢣ
 σʔλ ਪ࿦݁Ռ ޡࠩ
15. શମͷॲཧ TOWER ޯ഑ ʢgradsʣ TOWER ޯ഑ ʢgradsʣ TOWER ޯ഑ ʢgradsʣ TOWER ޯ഑ ʢgradsʣ ޯ഑ͷฏۉΛܭࢉ
 __average_gradients શମͷޯ഑ ʢavg_gradsʣ ࠷దԽ
 __apply_gradients params params params params
16.  %FNP
17. ৞ΈࠐΈΦʔτΤϯίʔμʔ  conv2 9x9x64 128 conv4 5x5x128 64 conv3-0 7x7x128 128 conv3-1 7x7x128 128 dconv2 9x9x128 64 dconv4 5x5x64 128 dconv3-1 7x7x128 128 dconv3-2 7x7x128 128 conv3-2 7x7x128 128 dconv3-2 7x7x128 128 256x256 256x256 conv1 9x9x3 64 padding: SAME dconv1 9x9x64 3 padding: SAME
18. ख࣋ͪͷ(16αʔόʔ
    $16
    *OUFM
    $PSF
    J,
    
    .FNPSZ
    (#
    
    44%
    (#
    
    (F'PSDF
    (59
    
    (#

    
    
    $6%"
    DPSF
     
    
19. ͘͞ΒͷߴՐྗίϯϐϡʔςΟϯάʢ࣮ݧػʣ $16
    9FPO
    $PSF
    ʷ
    
    .FNPSZ
    (#
    44%
    (#
    (F'PSDF
    (59
    5*5"/
    9ʢ1BTDBM
    ΞʔΩςΫνϟʣ
    (#
    ʷ
    

    $6%"
    DPSF
     
    (F'PSDF
    (59
    
    5Jʢ1BTDBM
    ΞʔΩςΫνϟʣ
    (#
    ʷ
    

    $6%"
    DPSF
      
20.  https://blog.keiji.io/2016/05/cuda_error_no_device.html
21. ύλʔϯ"ɿυϥΠόʔͷΞοϓσʔτ 
22. E tensorflow/stream_executor/cuda/cuda_dnn.cc:347] Loaded runtime CuDNN library: 4007 (compatibility version 4000) but source was compiled with 5103 (compatibility version 5100).  ύλʔϯ#ɿ5FOTPS'MPXͷΞοϓσʔτ https://github.com/tensorflow/tensorflow/issues/4251
23.  ύλʔϯ$
26.  खݩͰ࣮ߦՄೳͳϞσϧͱɺ
 ࢴ໘ʹܝࡌՄೳͳϞσϧ͸ҧ͏
27. ։ൃػ
    ͘͞ΒͷߴՐྗαʔόʔʢ2VBE
    (16Ϟσϧʣ $16
    9FPO
    $PSF
    ʷ
    
    .FNPSZ
    (#
    44%
    (#
    (F'PSDF
    (59
    5*5"/
    9ʢ.BYXFMM
    ΞʔΩςΫνϟʣ
    (#
    ʷ
    

    $6%"
    DPSF
     
     128 sample / batch learning rate 0.001
28. https://www.sakura.ad.jp/press/2017/0417_koukaryoku_hourly/
29. ݕূػ
 %FMM
    "-*&/8"3&
    9
    3
    $16
    *OUFM
    $PSF
    J,
    
    .FNPSZ
    (#
    
    44%
    (#
    
    (F'PSDF
    (59
    
    (#

    
    
    $6%"
    DPSF
     
     128 sample / batch learning rate 0.001
30. ஗͍ʜʜ 4UFQ
    
    -PTT
    
    5JNF
    NT
    
    TUFQ
    4UFQ
    
    -PTT
    
    5JNF
    NT
    
    TUFQ
    4UFQ
    
    -PTT
    
    5JNF
    NT
    
    TUFQ
    4UFQ
    
    -PTT
    
    5JNF
    NT
    
    TUFQ
    4UFQ
    
    -PTT
    
    5JNF
    NT
    
    TUFQ
    4UFQ
    
    -PTT
    
    5JNF
    NT
    
    TUFQ  128 sample / batch learning rate 0.001
31. (PPHMF
    $MPVE
    1MBUGPSN W$16
    .FNPSZ
    44%
    (F'PSDF
    5FTMB
    ,
    ʢ(#
    ʷ
    ʣ

    
    $6%"
    DPSF
     
    ʷ
     
32. 
33. 
34.  ( Д ) ʄ ʄŴƅƃŕ
35. ௨ৗ͸ΫΥʔλͰ੍ݶ͞Ε͍ͯΔ 
36.  : :
37.  Hello, Thank you for requesting additional quota. To help us ensure that this is a legitimate request and that the resources you requested are available to you, please do one of the following: Make a payment [1] of $35 or the same amount in your currency from the Transaction History page [2] and reply to this message when the charge clears. Your payment will be applied to any charges you incur in the future and will be visible as a credit in your account. Alternatively, reply to this message with the project ID of another project that you own that has cleared a charge of at least the amount mentioned. To learn more about project quota requests and cores quota requests, check out the Project Quota Request FAQ page at [3] and the Request cores quota increase FAQs page at [4]. We appreciate your patience. Sincerely, Cloud Platform Support [1] - https://support.google.com/cloud/answer/6294016 [2] - https://console.cloud.google.com/billing [3] - https://support.google.com/cloud/answer/6330231 [4] - https://support.google.com/cloud/answer/6376374
38.  Hello, Your quota request for Project '632906615582' has been approved and your project quota has been adjusted accordingly. Changed Quota: +--------------------+-----------------+ | Region: asia-east1 | NVIDIA_K80_GPUS | +--------------------+-----------------+ | Changes | 0 -> 1 | +--------------------+-----------------+ To verify the quota change, please navigate to https://console.developers.google.com/project/632906615582/compute/quotas and verify what are your current project quotas. Happy Computing! Google for Work Support http://support.google.com/enterprisehelp/
39. (PPHMF
    $MPVE
    1MBUGPSN W$16
    
    .FNPSZ
    (#
    44%
    (#
    (F'PSDF
    5FTMB
    ,
    ʢ(#
    ʷ
    ʣ

    
    $6%"
    DPSF
     
    ʷ
      ͋·ΓมΘΒͣ……
40.  ݪҼ͸ʁ
41. 
    OWJEJBTNJ 
    ]
    /7*%*"4.*
    
    
    
    
    
    
    
    
    
    
    
    
    
    
    
    
    
    %SJWFS
    7FSTJPO
    
    
    
    
    
    
    
    
    
    
    
    
    
    
    
    
    
    
    
    
    ]
    ]  
    ]
    (16
    
    /BNF
    
    
    
    
    
    
    
    1FSTJTUFODF.]
    #VT*E
    
    
    
    
    
    
    
    %JTQ"
    ]
    7PMBUJMF
    6ODPSS
    &$$
    ]
    ]
    'BO
    
    5FNQ
    
    1FSG
    
    1XS6TBHF$BQ]
    
    
    
    
    
    
    
    
    .FNPSZ6TBHF
    ]
    (166UJM
    
    $PNQVUF
    .
    ]
    ]  ]
    ]
    
    
    
    
    (F'PSDF
    (59
    
    
    
    
    
    0GG
    
    ]
    
    
    
    
    
    
    0O
    ]
    
    
    
    
    
    
    
    
    
    
    
    
    
    
    
    
    
    /"
    ]
    ]
    
    
    
    $
    
    
    
    1
    
    
    
    8
    
    8
    ]
    
    
    .J#
    
    
    .J#
    ]
    
    
    
    
    
    
    
    
    
    
    %FGBVMU
    ]
      
    
    
    
    
    
    
    
    
    
    
    
    
    
    
    
    
    
    
    
    
    
    
    
    
    
    
    
    
    
    
    
    
    
    
    
    
    
    
    
    
    
    
    
    
    
    
    
    
    
    
    
    
    
    
    
    
    
    
    
    
    
    
    
    
    
    
    
    
    
    
    
    
    
    
    
    
    
    
    
    
    
    ]
    1SPDFTTFT
    
    
    
    
    
    
    
    
    
    
    
    
    
    
    
    
    
    
    
    
    
    
    
    
    
    
    
    
    
    
    
    
    
    
    
    
    
    
    
    
    
    
    
    
    
    
    
    
    
    
    
    
    
    
    (16
    .FNPSZ
    ]
    ]
    
    (16
    
    
    
    
    
    
    1*%
    
    5ZQF
    
    1SPDFTT
    OBNF
    
    
    
    
    
    
    
    
    
    
    
    
    
    
    
    
    
    
    
    
    
    
    
    
    
    
    
    
    
    
    6TBHF
    
    
    
    
    
    ]
    ]]
    ]
    
    
    
    
    
    
    
    
    
    
    
    
    
    
    (
    
    
    VTSMJCYPSH9PSH
    
    
    
    
    
    
    
    
    
    
    
    
    
    
    
    
    
    
    
    
    
    
    
    
    
    
    
    
    
    .J#
    ]
    ]
    
    
    
    
    
    
    
    
    
    
    
    
    $
    
    
    QZUIPO
    
    
    
    
    
    
    
    
    
    
    
    
    
    
    
    
    
    
    
    
    
    
    
    
    
    
    
    
    
    
    
    
    
    
    
    
    
    
    .J#
    ]
    
    
42. ˈUPQ 
43.  (16͕ಈ͍ͯͳ͍
44. DPOGJH
    
    UG$POGJH1SPUP 

    
    BMMPX@TPGU@QMBDFNFOU5SVF 

    
    MPH@EFWJDF@QMBDFNFOU'-"(4MPH@EFWJDF@QMBDFNFOU 
 XJUI
    UG4FTTJPO DPOGJHDPOGJH
    BT
    TFTT

    
    DIFDLQPJOU
    
    UGUSBJOHFU@DIFDLQPJOU@TUBUF USBJO@EJS 
  MPH@EFWJDF@QMBDFNFOU
45. I tensorflow/core/common_runtime/simple_placer.cc:841] save/RestoreV2_26: (RestoreV2)/ job:localhost/replica:0/task:0/cpu:0 save/RestoreV2_25: (RestoreV2): /job:localhost/replica:0/task:0/cpu:0 I tensorflow/core/common_runtime/simple_placer.cc:841] save/RestoreV2_25: (RestoreV2)/ job:localhost/replica:0/task:0/cpu:0 save/RestoreV2_24: (RestoreV2): /job:localhost/replica:0/task:0/cpu:0 I tensorflow/core/common_runtime/simple_placer.cc:841] save/RestoreV2_24: (RestoreV2)/ job:localhost/replica:0/task:0/cpu:0 save/RestoreV2_23: (RestoreV2): /job:localhost/replica:0/task:0/cpu:0 I tensorflow/core/common_runtime/simple_placer.cc:841] save/RestoreV2_23: (RestoreV2)/ job:localhost/replica:0/task:0/cpu:0 save/RestoreV2_22: (RestoreV2): /job:localhost/replica:0/task:0/cpu:0 I tensorflow/core/common_runtime/simple_placer.cc:841] save/RestoreV2_22: (RestoreV2)/ job:localhost/replica:0/task:0/cpu:0 save/RestoreV2_21: (RestoreV2): /job:localhost/replica:0/task:0/cpu:0 I tensorflow/core/common_runtime/simple_placer.cc:841] save/RestoreV2_21: (RestoreV2)/ job:localhost/replica:0/task:0/cpu:0 save/RestoreV2_20: (RestoreV2): /job:localhost/replica:0/task:0/cpu:0 
46. I tensorflow/core/common_runtime/simple_placer.cc:841] save/RestoreV2_8: (RestoreV2)/ job:localhost/replica:0/task:0/cpu:0 save/RestoreV2_7: (RestoreV2): /job:localhost/replica:0/task:0/cpu:0 I tensorflow/core/common_runtime/simple_placer.cc:841] save/RestoreV2_7: (RestoreV2)/ job:localhost/replica:0/task:0/cpu:0 save/RestoreV2_6: (RestoreV2): /job:localhost/replica:0/task:0/cpu:0 I tensorflow/core/common_runtime/simple_placer.cc:841] save/RestoreV2_6: (RestoreV2)/ job:localhost/replica:0/task:0/cpu:0 save/RestoreV2_5: (RestoreV2): /job:localhost/replica:0/task:0/cpu:0 I tensorflow/core/common_runtime/simple_placer.cc:841] save/RestoreV2_5: (RestoreV2)/ job:localhost/replica:0/task:0/cpu:0 save/RestoreV2_4: (RestoreV2): /job:localhost/replica:0/task:0/cpu:0 I tensorflow/core/common_runtime/simple_placer.cc:841] save/RestoreV2_4: (RestoreV2)/ job:localhost/replica:0/task:0/cpu:0 save/RestoreV2_3: (RestoreV2): /job:localhost/replica:0/task:0/cpu:0 I tensorflow/core/common_runtime/simple_placer.cc:841] save/RestoreV2_3: (RestoreV2)/ job:localhost/replica:0/task:0/cpu:0 save/RestoreV2_2: (RestoreV2): /job:localhost/replica:0/task:0/cpu:0 
47. I tensorflow/core/common_runtime/simple_placer.cc:841] save/RestoreV2_2: (RestoreV2)/ job:localhost/replica:0/task:0/cpu:0 save/RestoreV2_1: (RestoreV2): /job:localhost/replica:0/task:0/cpu:0 I tensorflow/core/common_runtime/simple_placer.cc:841] save/RestoreV2_1: (RestoreV2)/ job:localhost/replica:0/task:0/cpu:0 save/RestoreV2: (RestoreV2): /job:localhost/replica:0/task:0/cpu:0 I tensorflow/core/common_runtime/simple_placer.cc:841] save/RestoreV2: (RestoreV2)/ job:localhost/replica:0/task:0/cpu:0 conv3/biases/ExponentialMovingAverage: (VariableV2): /job:localhost/replica:0/task:0/ cpu:0 I tensorflow/core/common_runtime/simple_placer.cc:841] conv3/biases/ ExponentialMovingAverage: (VariableV2)/job:localhost/replica:0/task:0/cpu:0 save/Assign_22: (Assign): /job:localhost/replica:0/task:0/cpu:0 I tensorflow/core/common_runtime/simple_placer.cc:841] save/Assign_22: (Assign)/ job:localhost/replica:0/task:0/cpu:0 conv3/biases/ExponentialMovingAverage/read: (Identity): /job:localhost/replica:0/task: 0/cpu:0 I tensorflow/core/common_runtime/simple_placer.cc:841] conv3/biases/  ҎԼུ
48. ΦϖϨʔγϣϯ͕࣮ߦ͞ΕΔσόΠε (16
    
    $16
     
49. I tensorflow/core/common_runtime/simple_placer.cc:841] tower_0/image_loader_vvv/ ReaderReadV2: (ReaderReadV2)/job:localhost/replica:0/task:0/cpu:0 tower_0/image_loader_vvv/DecodeJpeg: (DecodeJpeg): /job:localhost/replica:0/task: 0/cpu:0 I tensorflow/core/common_runtime/simple_placer.cc:841] tower_0/image_loader_vvv/ DecodeJpeg: (DecodeJpeg)/job:localhost/replica:0/task:0/cpu:0 tower_0/image_loader_vvv/random_crop/Shape: (Shape): /job:localhost/replica:0/ task:0/gpu:0  EFDPEF@KQFH
50. 
51. 
52. 
53. 
54. I tensorflow/core/common_runtime/simple_placer.cc:841] tower_0/image_loader_vvv/ ReaderReadV2: (ReaderReadV2)/job:localhost/replica:0/task:0/cpu:0 tower_0/image_loader_vvv/DecodeJpeg: (DecodeJpeg): /job:localhost/replica:0/task: 0/cpu:0 I tensorflow/core/common_runtime/simple_placer.cc:841] tower_0/image_loader_vvv/ DecodeJpeg: (DecodeJpeg)/job:localhost/replica:0/task:0/cpu:0 tower_0/image_loader_vvv/random_crop/Shape: (Shape): /job:localhost/replica:0/ task:0/gpu:0  EFDPEF@KQFH
55. DPOGJH
    
    UG$POGJH1SPUP 

    
    BMMPX@TPGU@QMBDFNFOU5SVF 

    
    MPH@EFWJDF@QMBDFNFOU'-"(4MPH@EFWJDF@QMBDFNFOU 
 XJUI
    UG4FTTJPO DPOGJHDPOGJH
    BT
    TFTT

    
    DIFDLQPJOU
    
    UGUSBJOHFU@DIFDLQPJOU@TUBUF USBJO@EJS 
  BMMPX@TPGU@QMBDFNFOU
56. BMMPX@TPGU@QMBDFNFOU  If you would like TensorFlow to automatically choose an existing and supported device to run the operations in case the specified one doesn't exist, you can set allow_soft_placement to True in the configuration option when creating the session. https://www.tensorflow.org/tutorials/using_gpu
57. EFG
    @MPBE@JNBHF GJMF@MJTU
    JOQVU@TJ[F
    PVUQVU@TJ[F
    DIBOOFMT
    TDBMF 

    
    XJUI
    UGOBNF@TDPQF JNBHF@MPBEFS@WWW 

    
    
    
    GJMFOBNF@RVFVF
    
    UGUSBJOTUSJOH@JOQVU@QSPEVDFS GJMF@MJTU 

    
    
    
    
    
    
    
    
    
    
    
    
    
    
    
    
    
    
    
    
    
    
    
    
    
    
    
    
    
    
    
    
    
    
    
    
    
    
    
    
    
    
    
    
    
    
    
    
    
    
    
    TIVGGMF5SVF 

    
    
    
    SFBEFS
    
    UG8IPMF'JMF3FBEFS 

    
    
    
    @
    WBMVF
    
    SFBEFSSFBE GJMFOBNF@RVFVF 
 

    
    
    
    JNBHF
    
    UGJNBHFEFDPEF@KQFH WBMVF
    DIBOOFMTDIBOOFMT 

    
    
    
    DSPQQFE@JNBHF
    
    UGSBOEPN@DSPQ JNBHF
    JOQVU@TJ[F
    JOQVU@TJ[F
    DIBOOFMT 
 

    
    
    
    MS@JNBHF
    
    UGJNBHFSFTJ[F@JNBHFT DSPQQFE@JNBHF
    JOQVU@TJ[F
    
    TDBMF 

    
    
    
    
    
    
    
    
    
    
    
    
    
    
    
    
    
    
    
    
    
    
    
    
    
    
    
    
    
    
    
    
    
    
    
    
    
    
    
    
    
    
    
    
    
    
    
    
    
    
    
    
    JOQVU@TJ[F
    
    TDBMF 

    
    
    
    
    
    
    
    
    
    
    
    
    
    
    
    
    
    
    
    
    
    
    
    
    
    
    
    
    
    
    
    
    
    
    
    
    
    NFUIPEUGJNBHF3FTJ[F.FUIPE#*$6#*$ 
 

    
    
    
    MS@JNBHF
    
    UGJNBHFSFTJ[F@JNBHFT MS@JNBHF
    JOQVU@TJ[F
    JOQVU@TJ[F 

    
    
    
    
    
    
    
    
    
    
    
    
    
    
    
    
    
    
    
    
    
    
    
    
    
    
    
    
    
    
    
    
    
    
    
    
    
    NFUIPEUGJNBHF3FTJ[F.FUIPE#*$6#*$ 
 

    
    
    
    PGGTFU@MFGU
    
    JOQVU@TJ[F
    
    PVUQVU@TJ[F
    
    

    
    
    
    PGGTFU@UPQ
    
    JOQVU@TJ[F
    
    PVUQVU@TJ[F
    
    

    
    
    
    HSPVOE@USVUI
    
    UGJNBHFDSPQ@UP@CPVOEJOH@CPY DSPQQFE@JNBHF 

    
    
    
    
    
    
    
    
    
    
    
    
    
    
    
    
    
    
    
    
    
    
    
    
    
    
    
    
    
    
    
    
    
    
    
    
    
    
    
    
    
    
    
    
    
    
    
    
    PGGTFU@UPQ
    PGGTFU@MFGU 

    
    
    
    
    
    
    
    
    
    
    
    
    
    
    
    
    
    
    
    
    
    
    
    
    
    
    
    
    
    
    
    
    
    
    
    
    
    
    
    
    
    
    
    
    
    
    
    
    PVUQVU@TJ[F
    PVUQVU@TJ[F 
 

    
    SFUVSO
    MS@JNBHF
    
    
    HSPVOE@USVUI
    
     
58.  510x510 decode_jpeg random_crop
59.  όονʹ͖ͭɺ
 ϑΝΠϧͷಡΈࠐΈɾσίʔυ͕
 ճൃੜ͢Δ
60. EFG
    @MPBE@JNBHF GJMF@MJTU
    JOQVU@TJ[F
    PVUQVU@TJ[F
    DIBOOFMT
    TDBMF
    CBUDI@TJ[F 

    
    XJUI
    UGOBNF@TDPQF JNBHF@MPBEFS@WWW 

    
    
    
    GJMFOBNF@RVFVF
    
    UGUSBJOTUSJOH@JOQVU@QSPEVDFS GJMF@MJTU 

    
    
    
    
    
    
    
    
    
    
    
    
    
    
    
    
    
    
    
    
    
    
    
    
    
    
    
    
    
    
    
    
    
    
    
    
    
    
    
    
    
    
    
    
    
    
    
    
    
    
    
    TIVGGMF5SVF 

    
    
    
    SFBEFS
    
    UG8IPMF'JMF3FBEFS 

    
    
    
    @
    WBMVF
    
    SFBEFSSFBE GJMFOBNF@RVFVF 

    
    
    
    JNBHF
    
    UGJNBHFEFDPEF@KQFH WBMVF
    DIBOOFMTDIBOOFMT 
 
61. 
    
    
    
    MS@JNBHFT
    
    <>

    
    
    
    HSPVOE@USVUIT
    
    <>
 

    
    
    
    GPS
    J
    JO
    SBOHF CBUDI@TJ[F 

    
    
    
    
    
    DSPQQFE@JNBHF
    
    UGSBOEPN@DSPQ JNBHF
    JOQVU@TJ[F
    JOQVU@TJ[F
    DIBOOFMT 

    
    
    
    
    
    MS@JNBHF
    
    UGJNBHFSFTJ[F@JNBHFT DSPQQFE@JNBHF
    JOQVU@TJ[F
    
    TDBMF 

    
    
    
    
    
    
    
    
    
    
    
    
    
    
    
    
    
    
    
    
    
    
    
    
    
    
    
    
    
    
    
    
    
    
    
    
    
    
    
    
    
    
    
    
    
    
    
    
    
    
    
    
    
    
    JOQVU@TJ[F
    
    TDBMF 

    
    
    
    
    
    
    
    
    
    
    
    
    
    
    
    
    
    
    
    
    
    
    
    
    
    
    
    
    
    
    
    
    
    
    
    
    
    
    
    NFUIPEUGJNBHF3FTJ[F.FUIPE#*$6#*$ 

    
    
    
    
    
    MS@JNBHF
    
    UGJNBHFSFTJ[F@JNBHFT MS@JNBHF
    JOQVU@TJ[F
    JOQVU@TJ[F 

    
    
    
    
    
    
    
    
    
    
    
    
    
    
    
    
    
    
    
    
    
    
    
    
    
    
    
    
    
    
    
    
    
    
    
    
    
    
    
    NFUIPEUGJNBHF3FTJ[F.FUIPE#*$6#*$ 

    
    
    
    
    
    MS@JNBHF
    
    UGFYQBOE@EJNT MS@JNBHF
    EJN 

    
    
    
    
    
    MS@JNBHFTBQQFOE MS@JNBHF 
 

    
    
    
    
    
    PGGTFU@MFGU
    
    JOQVU@TJ[F
    
    PVUQVU@TJ[F
    
    

    
    
    
    
    
    PGGTFU@UPQ
    
    JOQVU@TJ[F
    
    PVUQVU@TJ[F
    
    

    
    
    
    
    
    HSPVOE@USVUI
    
    UGJNBHFDSPQ@UP@CPVOEJOH@CPY DSPQQFE@JNBHF 

    
    
    
    
    
    
    
    
    
    
    
    
    
    
    
    
    
    
    
    
    
    
    
    
    
    
    
    
    
    
    
    
    
    
    
    
    
    
    
    
    
    
    
    
    
    
    
    
    
    
    PGGTFU@UPQ
    PGGTFU@MFGU 

    
    
    
    
    
    
    
    
    
    
    
    
    
    
    
    
    
    
    
    
    
    
    
    
    
    
    
    
    
    
    
    
    
    
    
    
    
    
    
    
    
    
    
    
    
    
    
    
    
    
    PVUQVU@TJ[F
    PVUQVU@TJ[F 

    
    
    
    
    
    HSPVOE@USVUI
    
    UGFYQBOE@EJNT HSPVOE@USVUI
    EJN 

    
    
    
    
    
    HSPVOE@USVUITBQQFOE HSPVOE@USVUI 
 

    
    
    
    MS@JNBHFT
    
    UGDPODBU MS@JNBHFT
    BYJT 

    
    
    
    HSPVOE@USVUIT
    
    UGDPODBU HSPVOE@USVUIT
    BYJT 
 

    
    SFUVSO
    MS@JNBHFT
    
    
    HSPVOE@USVUIT
    
    
 
62.  510x510 decode_jpeg random_crop
63. MPBE@JNBHF  [batch_size, height, width, channels] [height, width, channels]
64. MS@JNBHF@CBUDI
    HSPVOE@USVUI@CBUDI
    
    UGUSBJOTIVGGMF@CBUDI 

    
    <JNBHFT
    HSPVOE@USVUIT> 

    
    CBUDI@TJ[F'-"(4CBUDI@TJ[F 

    
    DBQBDJUZDBQBDJUZ 

    
    FORVFVF@NBOZ5SVF 

    
    NJO@BGUFS@EFRVFVF'-"(4NJO@BGUFS@EFRVFVF 

    
    OVN@UISFBET'-"(4OVN@UISFBET 
  UGUSBJOTIV⒐F@CBUDI
65.  4UFQ
    
    -PTT
    
    5JNF
    NT
    
    TUFQ
    4UFQ
    
    -PTT
    
    5JNF
    NT
    
    TUFQ
    4UFQ
    
    -PTT
    
    5JNF
    NT
    
    TUFQ
    4UFQ
    
    -PTT
    
    5JNF
    NT
    
    TUFQ
    4UFQ
    
    -PTT
    
    5JNF
    NT
    
    TUFQ
    4UFQ
    
    -PTT
    
    5JNF
    NT
    
    TUFQ 4UFQ
    
    -PTT
    
    5JNF
    NT
    
    TUFQ
    4UFQ
    
    -PTT
    
    5JNF
    NT
    
    TUFQ
    4UFQ
    
    -PTT
    
    5JNF
    NT
    
    TUFQ
    4UFQ
    
    -PTT
    
    5JNF
    NT
    
    TUFQ
    4UFQ
    
    -PTT
    
    5JNF
    NT
    
    TUFQ
    4UFQ
    
    -PTT
    
    5JNF
    NT
    
    TUFQ 128 sample / batch learning rate 0.001
66.  ύλʔϯ$ɿ$16ͷΦʔόʔϔου
67. ·ͱΊ (16͸଎͍ɻίʔυ͕গ͠൥ࡶʹͳΔ͚ͲɺಘΒΕΔ଎͞͸ັྗ
    ͘͞ΒͷߴՐྗ͸շదɻଟগɺඇޮ཰తͳίʔυΛॻ͍ͯ΋ؾ͔ͮͳ͍͘Β͍
    ($&ͷ(16Πϯελϯε΋଎͍ɻW$16ͷ਺ͱ͔ϝϞϦ༰ྔͱ͔ɺ՝୊ʹର͢ Δ࠷దεϖοΫΛಋ͘ϊ΢ϋ΢͕ཉ͍͠
    .-
    &OHJOFʜʜʁ 
68. Impress R&DࣾΑΓ
 Print On Demand ˍ ిࢠॻ੶Ͱ ݄̑Լ० ൃചܾఆ ݄̐̕೔ʢ೔ʣ ΞΩόɾεΫΤΞ ʰٕज़ॻయ̎ ͓ʔ̍̎ʱʹͯ TensorFlow͸͡Ί·ͨ͠
 Super Resolution ʔ ௒ղ૾ ׬ച͠·ͨ͠
69. C-LIS CO., LTD. ֤੡඼໊ɾϒϥϯυ໊ɺձ໊ࣾͳͲ͸ɺҰൠʹ֤ࣾͷ঎ඪ·ͨ͸ొ࿥঎ඪͰ͢ɻຊࢿྉதͰ͸ɺ˜ɺšɺäΛׂѪ͍ͯ͠·͢ɻ ຊࢿྉ͸ɺ༗ݶձࣾγʔϦεͷஶ࡞෺Ͱ͋ΓɺΫϦΤΠςΟϒίϞϯζͷදࣔඇӦརܧঝ
    
    6OQPSUFE
    ϥΠηϯεͷݩͰެ։͍ͯ͠·͢ɻ