Slide 1
Slide 1 text
C-LIS CO., LTD.
#dltfb
https://goo.gl/MX72Bc
Slide 2
Slide 2 text
C-LIS CO., LTD.
༗ࢁܓೋʢ,FJKJ"3*:"."ʣ
C-LIS CO., LTD.
AndroidΞϓϦ։ൃऀ
ػցֶशॳ৺ऀ
ͬͯ·ͤΜ
Photo : Koji MORIGUCHI (AUN CREATIVE FIRM)
Slide 3
Slide 3 text
C-LIS CO., LTD.
IUUQGVLVZVLJOFUQPTU
;͘Ώ͖ϒϩά AlphaGoͷαʔόʔྉۚ࠷60ԯԁ!!?
#dltfb
Slide 4
Slide 4 text
C-LIS CO., LTD.
IUUQGVLVZVLJOFUQPTU
;͘Ώ͖ϒϩά AlphaGoͷαʔόʔྉۚ࠷60ԯԁ!!?
#dltfb
Slide 5
Slide 5 text
C-LIS CO., LTD.
#dltfb
Slide 6
Slide 6 text
5FOTPS'MPXͰ
झຯͷը૾ऩूαʔόʔΛ࡞Δ
݄̐߸
#dltfb
https://goo.gl/MX72Bc
Slide 7
Slide 7 text
C-LIS CO., LTD.
(%(,PCFʢBUେࡕۀେֶʣ
Slide 8
Slide 8 text
C-LIS CO., LTD.
(%(,ZPUPʢBUۙـେֶʣ
Slide 9
Slide 9 text
C-LIS CO., LTD.
"OESPJE#B[BBSBOE$POGFSFODFʢ੨ࢁֶӃେֶʣ
Google TensorFlowͱAndroid͕ܨ͕Δະདྷ
IUUQTTQFBLFSEFDLDPNLFJKJHPPHMFUFOTPSqPXUPBOESPJELBYJLBSVXFJMBJ
Slide 10
Slide 10 text
C-LIS CO., LTD.
ษڧձͰͷൃදςʔϚ
IUUQTHEHLPCFEPPSLFFQFSKQFWFOUT
Slide 11
Slide 11 text
Έͷ؟ڸ່ͬը૾ΛࣗಈͰऩू͍ͨ͠
Slide 12
Slide 12 text
C-LIS CO., LTD.
࣮ݱΛ્Ή̏ͭͷน
σʔλͷน
ܭࢉྔͷน
ػցֶशͷน
Slide 13
Slide 13 text
C-LIS CO., LTD.
࡞ͨ͠σʔληοτ
؟ڸ່ͬը૾ຕ
ඇ؟ڸ່ͬը૾ຕ
؟ڸ່ͬ ඇ؟ڸ່ͬ
ޡݕग़
Slide 14
Slide 14 text
C-LIS CO., LTD.
$*'"34BNQMF
ଟΫϥεྨ
IUUQTXXXDTUPSPOUPFEV_LSJ[DJGBSIUNM
Slide 15
Slide 15 text
C-LIS CO., LTD.
̎Ϋϥεྨ
1 0
Slide 16
Slide 16 text
C-LIS CO., LTD.
ͬͨ͜ͱ
ूΊͨσʔλΛ$*'"3ͷϑΝΠϧܗࣜʹ߹ΘͤͯQBDLͯ͠
αϯϓϧϓϩάϥϜʹ༩͑ͨ
Label Red Green Blue
1
0
Label Red Green Blue
1
Label Red Green Blue
2
:
Slide 17
Slide 17 text
C-LIS CO., LTD.
DJGBSQZͷϞσϧ
̎ͷંΓΈɾϓʔϦϯά
̎ͷશ݁߹
Slide 18
Slide 18 text
C-LIS CO., LTD.
ݕূ݁Ռ
܇࿅σʔλ
ςετσʔλ
1SFDJTJPO
ʙ
Slide 19
Slide 19 text
C-LIS CO., LTD.
՝
ֶशʢςετʣσʔλͷॆ࣮
؟ڸͰͳ͘ɺΩϟϥΫλʔΛݟ͍ͯΔՄೳੑ͕͋Δ
ఆਫ਼Λ্͛Δ
ʢάϥϑͷਂԽʗύϥϝʔλʔௐʣ
Slide 20
Slide 20 text
άϥϑͷਂԽ
Slide 21
Slide 21 text
C-LIS CO., LTD.
$*'"3ʹ͍ͭͯ
ΘΕΘΕͬͱৄ͘͠Δඞཁ͕͋Δ
IUUQTXXXUFOTPSqPXPSHWFSTJPOTSUVUPSJBMTEFFQ@DOOJOEFYIUNM
Slide 22
Slide 22 text
-PDBMMZ$POOFDUFE-BZFSJTԿ
Slide 23
Slide 23 text
C-LIS CO., LTD.
# local3
with tf.variable_scope('local3') as scope:
# Move everything into depth so we can perform a single matrix multiply.
dim = 1
for d in pool2.get_shape()[1:].as_list():
dim *= d
reshape = tf.reshape(pool2, [FLAGS.batch_size, dim])
weights = _variable_with_weight_decay('weights', shape=[dim, 384],
stddev=0.04, wd=0.004)
biases = _variable_on_cpu('biases', [384], tf.constant_initializer(0.1))
local3 = tf.nn.relu(tf.matmul(reshape, weights) + biases, name=scope.name)
_activation_summary(local3)
# local4
with tf.variable_scope('local4') as scope:
weights = _variable_with_weight_decay('weights', shape=[384, 192],
stddev=0.04, wd=0.004)
biases = _variable_on_cpu('biases', [192], tf.constant_initializer(0.1))
local4 = tf.nn.relu(tf.matmul(local3, weights) + biases, name=scope.name)
_activation_summary(local4)
DJGBSQZ
Slide 24
Slide 24 text
C-LIS CO., LTD.
Slide 25
Slide 25 text
C-LIS CO., LTD.
Slide 26
Slide 26 text
C-LIS CO., LTD.
"This kind of layer is just like a convolutional layer, but without any
weight-sharing. That is to say, a different set of filters is applied at
every (x, y) location in the input image. Aside from that, it behaves
exactly as a convolutional layer."
IUUQTDPEFHPPHMFDPNQDVEBDPOWOFUXJLJ-BZFS1BSBNT-PDBMMZ
DPOOFDUFE@MBZFS@XJUI@VOTIBSFE@XFJHIUT
Slide 27
Slide 27 text
C-LIS CO., LTD.
Ͱɺ݁ہ
-PDBMMZ$POOFDUFE-BZFSJTԿ
ਫ਼্͕͕Δͷʁ
্͕͕Δͷʁ
ͲΜͳ͍͍͜ͱ͕͋Δͷʁ
Slide 28
Slide 28 text
C-LIS CO., LTD.
ંΓΈΛ૿ͯ͠Έͨ
ˍύϥϝʔλʔΛௐ
# conv0
with tf.variable_scope('conv0') as scope:
kernel = _variable_with_weight_decay('weights', shape=[32, 32, 3, 32],
stddev=1e-4, wd=0.0)
conv = tf.nn.conv2d(images, kernel, [1, 1, 1, 1], padding='SAME')
biases = _variable_on_cpu('biases', [32], tf.constant_initializer(0.0))
bias = tf.nn.bias_add(conv, biases)
conv0 = tf.nn.relu(bias, name=scope.name)
_activation_summary(conv0)
# pool0
pool0 = tf.nn.max_pool(conv0, ksize=[1, 3, 3, 1], strides=[1, 2, 2, 1],
padding='SAME', name='pool0')
# norm0
norm0 = tf.nn.lrn(pool0, 4, bias=1.0, alpha=0.001 / 9.0, beta=0.75,
name='norm0')
# conv1
with tf.variable_scope('conv1') as scope:
kernel = _variable_with_weight_decay('weights', shape=[16, 16, 32, 64],
stddev=1e-4, wd=0.0)
conv = tf.nn.conv2d(norm0, kernel, [1, 1, 1, 1], padding='SAME')
biases = _variable_on_cpu('biases', [64], tf.constant_initializer(0.0))
bias = tf.nn.bias_add(conv, biases)
conv1 = tf.nn.relu(bias, name=scope.name)
_activation_summary(conv1)
Slide 29
Slide 29 text
C-LIS CO., LTD.
Slide 30
Slide 30 text
C-LIS CO., LTD.
લճͱಉ͡σʔλͰݕূ
Λ૿͢ʢύϥϝʔλʔΛௐʣͱ࠷ॳ͔Β
ϩε͕ͷ̍ʹԼͨ͠ɻ
ΘΓʹεςοϓʹ͔͔Δ͕࣌ؒ̏ഒʹͳͬͨɻ
Slide 31
Slide 31 text
σʔλͷॆ࣮
Slide 32
Slide 32 text
C-LIS CO., LTD.
࡞σʔλ༁
؟ڸ່ͬը૾ຕ
ඇ؟ڸ່ͬը૾ຕ
؟ڸ່ͬ
ඇ؟ڸ່ͬ
؟ڸ່ͬ
ඇ؟ڸ່ͬ
Slide 33
Slide 33 text
C-LIS CO., LTD.
ݕূσʔλͷྨΛखͰߦ͏
ҰຕֆͷΩϟϥΫλʔʹݶఆ͢Δ
ʢෳຕଘࡏ͠ʹ͍͘ֆΛબఆʣ
D
ࠜઇΕ͍
Slide 34
Slide 34 text
C-LIS CO., LTD.
࡞σʔλ༁
܇࿅σʔλ
ςετσʔλ
Slide 35
Slide 35 text
C-LIS CO., LTD.
܇࿅σʔλը૾ʹϊΠζΛՃ͑ͯ૿ྔ
΅͔͠
ΨγΞϯϊΠζ
ΠϯύϧεϊΠζ
Slide 36
Slide 36 text
Slide 37
Slide 37 text
C-LIS CO., LTD.
ֶशͱݕূ
܇࿅σʔλ
ςετσʔλ
1SFDJTJPO
Slide 38
Slide 38 text
C-LIS CO., LTD.
ൃੜ
ΦϑΟεͷαʔόʔϚγϯͷ(16͕͑ͳ͘ͳΔ
$ python3 megane_co/cifar10_train.py
I tensorflow/stream_executor/dso_loader.cc:105] successfully opened CUDA library libcublas.so
locally
I tensorflow/stream_executor/dso_loader.cc:105] successfully opened CUDA library libcudnn.so locally
I tensorflow/stream_executor/dso_loader.cc:105] successfully opened CUDA library libcufft.so locally
I tensorflow/stream_executor/dso_loader.cc:105] successfully opened CUDA library libcuda.so.1
locally
I tensorflow/stream_executor/dso_loader.cc:105] successfully opened CUDA library libcurand.so
locally
Filling queue with 400 CIFAR images before starting to train. This will take a few minutes.
E tensorflow/stream_executor/cuda/cuda_driver.cc:481] failed call to cuInit: CUDA_ERROR_NO_DEVICE
Slide 39
Slide 39 text
C-LIS CO., LTD.
ͷൺֱ
$16
2016-04-13 10:40:51.188290: step 0, loss = 11.15 (65.8 examples/sec; 1.946 sec/batch)
2016-04-13 10:41:10.546296: step 10, loss = 10.67 (74.0 examples/sec; 1.731 sec/batch)
2016-04-13 10:41:29.646204: step 20, loss = 10.29 (74.0 examples/sec; 1.729 sec/batch)
(16
2016-03-06 00:42:54.454566: step 90, loss = 10.39 (286.9 examples/sec; 0.446 sec/batch)
2016-03-06 00:42:59.533350: step 100, loss = 10.32 (290.1 examples/sec; 0.441 sec/batch)
2016-03-06 00:43:04.834940: step 110, loss = 10.27 (292.9 examples/sec; 0.437 sec/batch)
Slide 40
Slide 40 text
ൃੜ
Slide 41
Slide 41 text
(PPHMF$MPVE.BDIJOF-FBSOJOH
Slide 42
Slide 42 text
C-LIS CO., LTD.
(PPHMF$MPVE.BDIJOF-FBSOJOH
($1/&95Ͱൃද͞Εͨ
ΫϥυϕʔεͷػցֶशϓϥοτϑΥʔϜ
Slide 43
Slide 43 text
C-LIS CO., LTD.
(PPHMF$MPVE.BDIJOF-FBSOJOH
1SPKFDU/BNFNFHBOF@DP
Slide 44
Slide 44 text
C-LIS CO., LTD.
(PPHMF$MPVE.BDIJOF-FBSOJOH
ฦࣄɺདྷͯ·ͤΜͰͨ͠ʂ
Slide 45
Slide 45 text
͔͜͜Β$16ͷΈͰ͓ૹΓ͠·͢
Slide 46
Slide 46 text
C-LIS CO., LTD.
ݕূʢ৽Ϟσϧʴ৽σʔληοτʣ
܇࿅σʔλ
ςετσʔλ
1SFDJTJPO
ʙ
Slide 47
Slide 47 text
C-LIS CO., LTD.
5SBJOJOHʢ৽Ϟσϧʴ৽σʔληοτʣ
CBUDI
4UFQ
Slide 48
Slide 48 text
C-LIS CO., LTD.
5SBJOJOHʢچϞσϧʴچσʔληοτʣ
CBUDI
4UFQ
Slide 49
Slide 49 text
C-LIS CO., LTD.
ݕূʢچϞσϧʴ৽σʔληοτʣ
܇࿅σʔλ
ςετσʔλ
1SFDJTJPO
ʙ
Slide 50
Slide 50 text
C-LIS CO., LTD.
5SBJOJOHʢچϞσϧʴ৽σʔληοτʣ
CBUDI
4UFQ
Slide 51
Slide 51 text
C-LIS CO., LTD.
՝
ֶशʢςετʣσʔλʹదԠ͢ΔϑΟϧλʔͷ
छྨͱڧΛݕ౼
ఆਫ਼Λ্͛Δɹˠɹ$*'"3ͷσʔλͰ֬ೝ
ʢάϥϑͷਂԽʗύϥϝʔλʔௐʗޡఆύλʔϯΛׂΓग़͢ʣ
Slide 52
Slide 52 text
C-LIS CO., LTD.
࣍ճ༧ࠂ
$MPVE7JTJPO"QJ5FOTPS'MPXษڧձ
(%(,PCF
IUUQTHEHLPCFEPPSLFFQFSKQFWFOUT
Slide 53
Slide 53 text
C-LIS CO., LTD.
5FOTPS'MPXΛͬͨػցֶश͜ͱ͡ΊCZ5PSV6&/0:"."
IUUQXXXTMJEFTIBSFOFU5PSV6FOPZBNBUFOTPSqPXHEH
σΟʔϓϥʔχϯάͰ͓ͦদ͞Μͷͭࢠݟ͚ΒΕΔͷ͔ʁɹʙ४උฤʙ
IUUQCPIFNJBIBUFOBCMPHDPNFOUSZ
ػցֶशͷσʔληοτը૾ຕΛ૿͢ํ๏
IUUQRJJUBDPNCPIFNJBOJUFNTDEGD
5FOTPS'MPX
IUUQTHJUIVCDPNUFOTPSqPXUFOTPSqPX
ࢀߟ
Slide 54
Slide 54 text
C-LIS CO., LTD.
C-LIS CO., LTD.
Slide 55
Slide 55 text
ຊࢿྉɺ༗ݶձࣾγʔϦεͷஶ࡞Ͱ͢ɻܝࡌ͞Ε͍ͯΔΠϥετɺಛʹهࡌ͕ͳ͍߹ࠜઇΕ͍ͷஶ࡞Ͱ͢ɻ
ຊࢿྉͷશ෦ɺ·ͨҰ෦ʹ͍ͭͯɺஶ࡞ऀ͔ΒจॻʹΑΔڐΛಘͣʹෳ͢Δ͜ͱې͡ΒΕ͍ͯ·͢ɻ
5IF"OESPJE4UVEJPJDPOJTSFQSPEVDFEPSNPEJpFEGSPNXPSLDSFBUFEBOETIBSFECZ(PPHMFBOEVTFE
BDDPSEJOHUPUFSNTEFTDSJCFEJOUIF$SFBUJWF$PNNPOT"UUSJCVUJPO-JDFOTF
໊֤ɾϒϥϯυ໊ɺձ໊ࣾͳͲɺҰൠʹ֤ࣾͷඪ·ͨొඪͰ͢ɻຊࢿྉதͰɺɺɺäΛׂѪͯ͠
͍·͢ɻ
5IF"OESPJESPCPUJTSFQSPEVDFEPSNPEJpFEGSPNXPSLDSFBUFEBOETIBSFECZ(PPHMFBOEVTFEBDDPSEJOH
UPUFSNTEFTDSJCFEJOUIF$SFBUJWF$PNNPOT"UUSJCVUJPO-JDFOTF