{"id":2675,"date":"2019-12-02T15:39:39","date_gmt":"2019-12-02T06:39:39","guid":{"rendered":"http:\/\/research.itplants.com\/?p=2675"},"modified":"2019-12-10T11:34:19","modified_gmt":"2019-12-10T02:34:19","slug":"openvino-movidius","status":"publish","type":"post","link":"https:\/\/research.itplants.com\/?p=2675","title":{"rendered":"OpenVINO+ NCS2"},"content":{"rendered":"

Movidius Neural Compute Stick2(NSC2)\u306f\u3001USB3.0 \u5bfe\u5fdc\u306a\u306e\u3067\u3059\u304c\u3001Raspberry Pi Model 3+\u307e\u3067USB2.0\u306b\u3057\u304b\u5bfe\u5fdc\u3057\u3066\u3044\u307e\u305b\u3093\u3067\u3057\u305f\u3002USB3.0\u306b\u5bfe\u5fdc\u3057\u305fRaspberry Pi Model 4\u304c\u5165\u624b\u3067\u304d\u305f\u306e\u3067\u3001\u6539\u3081\u3066\u3001Movidius Neural Compute Stick2\u3092\u8a66\u3057\u3066\u307f\u307e\u3057\u305f\u3002<\/p>\n

\u5148\u305a\u306f\u3001openVINO\u306e\u30c0\u30a6\u30f3\u30ed\u30fc\u30c9\u304b\u3089\u3067\u3059\u3002<\/p>\n

Intel\u306e\u30da\u30fc\u30b8<\/a>\u304b\u3089\u3001l_openvino_toolkit_runtime_raspbian_p_2019.3.334.tgz<\/a>\u3000\u3092\u30c0\u30a6\u30f3\u30ed\u30fc\u30c9\u3057\u307e\u3059\u3002<\/p>\n

\/opt\/intel\/openvino\u306b\u5c55\u958b\u3057\u307e\u3059\u3002<\/p>\n

\u3053\u308c\u306b\u306f\u3001TBB\u304c\u5165\u3063\u3066\u304a\u3089\u305a\u30a8\u30e9\u30fc\u306b\u306a\u308b\u306e\u3067\u3001TBB\u3082\u30c0\u30a6\u30f3\u30ed\u30fc\u30c9\u3057\u3066\u30b3\u30f3\u30d1\u30a4\u30eb\u3057\u3066\u304a\u304d\u307e\u3059\u3002<\/p>\n

\u3053\u3053\u304b\u3089\u3001<\/a>\u30bd\u30fc\u30b9\u30b3\u30fc\u30c9\u3092\u30c0\u30a6\u30f3\u30ed\u30fc\u30c9<\/a>\u3057\u3066\u30b3\u30f3\u30d1\u30a4\u30eb\u3057\u307e\u3059\u3002<\/p>\n

$\u00a0tar zxvf 2019_U9.tar.gz\u00a0<\/span><\/p>\n

$\u00a0cd tbb-2019_U9\/<\/p>\n

$ make<\/p>\n

$\u00a0cp build\/linux_armv7_gcc_cc8.3.0_libc2.28_kernel4.19.75_release\/libtbb* \/opt\/intel\/openvino\/deployment_tools\/inference_engine\/external\/tbb\/lib\/<\/p>\n

$mkdir ~\/open_sample<\/p>\n

$cd ~open_sample<\/p>\n

$\u00a0cmake -DCMAKE_BUILD_TYPE=Release -DCMAKE_CXX_FLAGS=”-march=armv7-a” \/opt\/intel\/openvino\/deployment_tools\/inference_engine\/samples<\/p>\n

$ make -j 2<\/p>\n

$ cd\u00a0armv7l\/Release<\/p>\n

$.\/benchmark_app -i ~\/president_reagan-62×62.png -m ~\/models\/age-gender-recognition-retail-0013.xml -api async -d MYRIAD<\/p>\n


\n[Step 1\/11] Parsing and validating input arguments
\n[ INFO ] Parsing input parameters
\n[ INFO ] Files were added: 1
\n[ INFO ] \/home\/pi\/president_reagan-62x62.png
\n[ WARNING ] -nstreams default value is determined automatically for a device. Although the automatic selection usually provides a reasonable performance,but it still may be non-optimal for some cases, for more information look at README.<\/code>
\n
\n[Step 2\/11] Loading Inference Engine
\n[ INFO ] InferenceEngine:
\nAPI version ............ 2.1
\nBuild .................. custom_releases\/2019\/R3_cb6cad9663aea3d282e0e8b3e0bf359df665d5d0
\nDescription ....... API
\n[ INFO ] Device info:
\nMYRIAD
\nmyriadPlugin version ......... 2.1
\nBuild ........... 30677<\/code>
\n
\n[Step 3\/11] Reading the Intermediate Representation network
\n[ INFO ] Loading network files
\n[ INFO ] Read network took 35.00 ms
\n[Step 4\/11] Resizing network to match image sizes and given batch
\n[ INFO ] Network batch size: 1, precision: FP16
\n[Step 5\/11] Configuring input of the model
\n[Step 6\/11] Setting device configuration
\n[Step 7\/11] Loading the model to the device
\n[ INFO ] Load network took 1918.22 ms
\n[Step 8\/11] Setting optimal runtime parameters
\n[Step 9\/11] Creating infer requests and filling input blobs with images
\n[ INFO ] Network input 'data' precision U8, dimensions (NCHW): 1 3 62 62
\n[ WARNING ] Some image input files will be duplicated: 4 files are required but only 1 are provided
\n[ INFO ] Infer Request 0 filling
\n[ INFO ] Prepare image \/home\/pi\/president_reagan-62x62.png
\nlibpng warning: iCCP: known incorrect sRGB profile
\n[ INFO ] Infer Request 1 filling
\n[ INFO ] Prepare image \/home\/pi\/president_reagan-62x62.png
\nlibpng warning: iCCP: known incorrect sRGB profile
\n[ INFO ] Infer Request 2 filling
\n[ INFO ] Prepare image \/home\/pi\/president_reagan-62x62.png
\nlibpng warning: iCCP: known incorrect sRGB profile
\n[ INFO ] Infer Request 3 filling
\n[ INFO ] Prepare image \/home\/pi\/president_reagan-62x62.png
\nlibpng warning: iCCP: known incorrect sRGB profile
\n[Step 10\/11] Measuring performance (Start inference asyncronously, 4 inference requests, limits: 60000 ms duration)
\n<\/code>
\n[Step 11\/11] Dumping statistics report
\nCount: 27720 iterations
\nDuration: 60013.63 ms
\nLatency: 8.43 ms
\nThroughput: 461.90 FPS
\n<\/code><\/p>\n

\u4f55\u3092\u3084\u3063\u3066\u3044\u308b\u306e\u304b\u5206\u304b\u3089\u3093\u304c\u3001\u591a\u5206\u3001\u3059\u3054\u304f\u65e9\u3044\u306e\u3067\u3057\u3087\u3046\u306d\u3002\u3002\u3002<\/p>\n

 <\/p>\n

pi@rpi4:~\/open_sample $ time\u00a0 <\/span>.\/armv7l\/Release\/object_detection_sample_ssd -m ..\/models\/face-detection-adas-0001.xml -d MYRIAD -i ..\/president_reagan-62×62.png\u00a0<\/span><\/p>\n

[ INFO ] InferenceEngine:\u00a0<\/span><\/p>\n

API version ………… 2.1<\/p>\n

Build ……………… custom_releases\/2019\/R3_cb6cad9663aea3d282e0e8b3e0bf359df665d5d0<\/p>\n

Description ……. API<\/p>\n

Parsing input parameters<\/p>\n

[ INFO ] Files were added: 1<\/p>\n

[ INFO ] \u00a0 \u00a0 <\/span>..\/president_reagan-62×62.png<\/p>\n

[ INFO ] Loading Inference Engine<\/p>\n

[ INFO ] Device info:\u00a0<\/span><\/p>\n

MYRIAD<\/p>\n

myriadPlugin version ……… 2.1<\/p>\n

Build ……….. 30677<\/p>\n

[ INFO ] Loading network files:<\/p>\n

..\/models\/face-detection-adas-0001.xml<\/p>\n

..\/models\/face-detection-adas-0001.bin<\/p>\n

[ INFO ] Preparing input blobs<\/p>\n

[ INFO ] Batch size is 1<\/p>\n

[ INFO ] Preparing output blobs<\/p>\n

[ INFO ] Loading model to the device<\/p>\n

[ INFO ] Create infer request<\/p>\n

libpng warning: iCCP: known incorrect sRGB profile<\/p>\n

[ WARNING ] Image is resized from (62, 62) to (672, 384)<\/p>\n

[ INFO ] Batch size is 1<\/p>\n

[ INFO ] Start inference<\/p>\n

[ INFO ] Processing output blobs<\/p>\n

[0,1] element, prob = 0.998047\u00a0 \u00a0 <\/span>(26,14)-(47,43) batch id : 0 WILL BE PRINTED!<\/p>\n

[1,1] element, prob = 0.103516\u00a0 \u00a0 <\/span>(14,15)-(19,22) batch id : 0<\/p>\n

[2,1] element, prob = 0.078125\u00a0 \u00a0 <\/span>(30,54)-(33,62) batch id : 0<\/p>\n

[3,1] element, prob = 0.0517578\u00a0 \u00a0 <\/span>(15,17)-(18,21) batch id : 0<\/p>\n

[4,1] element, prob = 0.0483398\u00a0 \u00a0 <\/span>(14,16)-(17,21) batch id : 0<\/p>\n

[5,1] element, prob = 0.0405273\u00a0 \u00a0 <\/span>(31,43)-(37,52) batch id : 0<\/p>\n

[6,1] element, prob = 0.0395508\u00a0 \u00a0 <\/span>(30,58)-(32,62) batch id : 0<\/p>\n

[7,1] element, prob = 0.0375977\u00a0 \u00a0 <\/span>(15,15)-(17,18) batch id : 0<\/p>\n

[8,1] element, prob = 0.0375977\u00a0 \u00a0 <\/span>(15,20)-(17,23) batch id : 0<\/p>\n

[9,1] element, prob = 0.0375977\u00a0 \u00a0 <\/span>(31,48)-(36,58) batch id : 0<\/p>\n

[10,1] element, prob = 0.0375977\u00a0 \u00a0 <\/span>(0,0)-(7,35) batch id : 0<\/p>\n

[11,1] element, prob = 0.0366211\u00a0 \u00a0 <\/span>(1,0)-(5,14) batch id : 0<\/p>\n

[12,1] element, prob = 0.0366211\u00a0 \u00a0 <\/span>(12,14)-(19,22) batch id : 0<\/p>\n

[13,1] element, prob = 0.0356445\u00a0 \u00a0 <\/span>(17,15)-(19,18) batch id : 0<\/p>\n

[14,1] element, prob = 0.034668\u00a0 \u00a0 <\/span>(17,17)-(19,21) batch id : 0<\/p>\n

[15,1] element, prob = 0.034668\u00a0 \u00a0 <\/span>(30,56)-(32,60) batch id : 0<\/p>\n

[16,1] element, prob = 0.034668\u00a0 \u00a0 <\/span>(29,0)-(34,4) batch id : 0<\/p>\n

[17,1] element, prob = 0.0341797\u00a0 \u00a0 <\/span>(14,15)-(16,18) batch id : 0<\/p>\n

[18,1] element, prob = 0.0332031\u00a0 \u00a0 <\/span>(14,21)-(16,26) batch id : 0<\/p>\n

[19,1] element, prob = 0.0332031\u00a0 \u00a0 <\/span>(0,0)-(5,7) batch id : 0<\/p>\n

[20,1] element, prob = 0.0332031\u00a0 \u00a0 <\/span>(43,31)-(49,41) batch id : 0<\/p>\n

[21,1] element, prob = 0.0332031\u00a0 \u00a0 <\/span>(14,7)-(22,21) batch id : 0<\/p>\n

[22,1] element, prob = 0.0332031\u00a0 \u00a0 <\/span>(12,14)-(20,27) batch id : 0<\/p>\n

[23,1] element, prob = 0.0322266\u00a0 \u00a0 <\/span>(26,6)-(29,11) batch id : 0<\/p>\n

[24,1] element, prob = 0.0322266\u00a0 \u00a0 <\/span>(14,17)-(16,20) batch id : 0<\/p>\n

[25,1] element, prob = 0.0322266\u00a0 \u00a0 <\/span>(14,12)-(19,20) batch id : 0<\/p>\n

[26,1] element, prob = 0.0322266\u00a0 \u00a0 <\/span>(6,4)-(22,40) batch id : 0<\/p>\n

[27,1] element, prob = 0.03125\u00a0 \u00a0 <\/span>(17,20)-(19,23) batch id : 0<\/p>\n

[28,1] element, prob = 0.03125\u00a0 \u00a0 <\/span>(12,22)-(15,26) batch id : 0<\/p>\n

[29,1] element, prob = 0.03125\u00a0 \u00a0 <\/span>(46,34)-(48,39) batch id : 0<\/p>\n

[30,1] element, prob = 0.03125\u00a0 \u00a0 <\/span>(13,12)-(17,18) batch id : 0<\/p>\n

[31,1] element, prob = 0.03125\u00a0 \u00a0 <\/span>(13,16)-(16,22) batch id : 0<\/p>\n

[32,1] element, prob = 0.03125\u00a0 \u00a0 <\/span>(30,52)-(35,60) batch id : 0<\/p>\n

[33,1] element, prob = 0.03125\u00a0 \u00a0 <\/span>(7,9)-(12,25) batch id : 0<\/p>\n

[34,1] element, prob = 0.03125\u00a0 \u00a0 <\/span>(10,12)-(16,24) batch id : 0<\/p>\n

[35,1] element, prob = 0.03125\u00a0 \u00a0 <\/span>(7,16)-(12,31) batch id : 0<\/p>\n

[36,1] element, prob = 0.0302734\u00a0 \u00a0 <\/span>(45,32)-(47,37) batch id : 0<\/p>\n

[37,1] element, prob = 0.0292969\u00a0 \u00a0 <\/span>(30,0)-(33,2) batch id : 0<\/p>\n

[38,1] element, prob = 0.0292969\u00a0 \u00a0 <\/span>(45,35)-(47,39) batch id : 0<\/p>\n

[39,1] element, prob = 0.0292969\u00a0 \u00a0 <\/span>(30,53)-(32,59) batch id : 0<\/p>\n

[40,1] element, prob = 0.0292969\u00a0 \u00a0 <\/span>(14,0)-(19,6) batch id : 0<\/p>\n

[41,1] element, prob = 0.0292969\u00a0 \u00a0 <\/span>(26,13)-(30,20) batch id : 0<\/p>\n

[42,1] element, prob = 0.0292969\u00a0 \u00a0 <\/span>(28,14)-(32,21) batch id : 0<\/p>\n

[43,1] element, prob = 0.0292969\u00a0 \u00a0 <\/span>(14,17)-(17,23) batch id : 0<\/p>\n

[44,1] element, prob = 0.0292969\u00a0 \u00a0 <\/span>(11,19)-(16,28) batch id : 0<\/p>\n

[45,1] element, prob = 0.0292969\u00a0 \u00a0 <\/span>(30,32)-(38,41) batch id : 0<\/p>\n

[46,1] element, prob = 0.0292969\u00a0 \u00a0 <\/span>(24,1)-(32,14) batch id : 0<\/p>\n

[47,1] element, prob = 0.0283203\u00a0 \u00a0 <\/span>(2,0)-(4,3) batch id : 0<\/p>\n

[48,1] element, prob = 0.0283203\u00a0 \u00a0 <\/span>(25,14)-(28,19) batch id : 0<\/p>\n

[49,1] element, prob = 0.0283203\u00a0 \u00a0 <\/span>(15,24)-(18,29) batch id : 0<\/p>\n

[50,1] element, prob = 0.0283203\u00a0 \u00a0 <\/span>(29,57)-(31,62) batch id : 0<\/p>\n

[51,1] element, prob = 0.0283203\u00a0 \u00a0 <\/span>(27,4)-(31,12) batch id : 0<\/p>\n

[52,1] element, prob = 0.0283203\u00a0 \u00a0 <\/span>(13,14)-(16,19) batch id : 0<\/p>\n

[53,1] element, prob = 0.0283203\u00a0 \u00a0 <\/span>(8,15)-(11,22) batch id : 0<\/p>\n

[54,1] element, prob = 0.0283203\u00a0 \u00a0 <\/span>(10,21)-(14,28) batch id : 0<\/p>\n

[55,1] element, prob = 0.0283203\u00a0 \u00a0 <\/span>(31,45)-(35,52) batch id : 0<\/p>\n

[56,1] element, prob = 0.0283203\u00a0 \u00a0 <\/span>(10,6)-(15,19) batch id : 0<\/p>\n

[57,1] element, prob = 0.0273438\u00a0 \u00a0 <\/span>(33,0)-(35,3) batch id : 0<\/p>\n

[58,1] element, prob = 0.0273438\u00a0 \u00a0 <\/span>(2,6)-(4,11) batch id : 0<\/p>\n

[59,1] element, prob = 0.0273438\u00a0 \u00a0 <\/span>(8,9)-(10,14) batch id : 0<\/p>\n

[60,1] element, prob = 0.0273438\u00a0 \u00a0 <\/span>(11,15)-(13,18) batch id : 0<\/p>\n

[61,1] element, prob = 0.0273438\u00a0 \u00a0 <\/span>(11,17)-(13,21) batch id : 0<\/p>\n

[62,1] element, prob = 0.0273438\u00a0 \u00a0 <\/span>(14,19)-(16,23) batch id : 0<\/p>\n

[63,1] element, prob = 0.0273438\u00a0 \u00a0 <\/span>(11,22)-(13,26) batch id : 0<\/p>\n

[64,1] element, prob = 0.0273438\u00a0 \u00a0 <\/span>(14,24)-(16,29) batch id : 0<\/p>\n

[65,1] element, prob = 0.0273438\u00a0 \u00a0 <\/span>(27,57)-(30,62) batch id : 0<\/p>\n

[66,1] element, prob = 0.0273438\u00a0 \u00a0 <\/span>(0,0)-(4,4) batch id : 0<\/p>\n

[67,1] element, prob = 0.0273438\u00a0 \u00a0 <\/span>(32,0)-(35,5) batch id : 0<\/p>\n

[68,1] element, prob = 0.0273438\u00a0 \u00a0 <\/span>(27,5)-(30,10) batch id : 0<\/p>\n

[69,1] element, prob = 0.0273438\u00a0 \u00a0 <\/span>(14,8)-(17,13) batch id : 0<\/p>\n

[70,1] element, prob = 0.0273438\u00a0 \u00a0 <\/span>(8,12)-(11,19) batch id : 0<\/p>\n

[71,1] element, prob = 0.0273438\u00a0 \u00a0 <\/span>(16,13)-(21,21) batch id : 0<\/p>\n

[72,1] element, prob = 0.0273438\u00a0 \u00a0 <\/span>(24,12)-(29,21) batch id : 0<\/p>\n

[73,1] element, prob = 0.0273438\u00a0 \u00a0 <\/span>(10,17)-(14,26) batch id : 0<\/p>\n

[74,1] element, prob = 0.0273438\u00a0 \u00a0 <\/span>(12,18)-(15,24) batch id : 0<\/p>\n

[75,1] element, prob = 0.0273438\u00a0 \u00a0 <\/span>(15,20)-(18,27) batch id : 0<\/p>\n

[76,1] element, prob = 0.0273438\u00a0 \u00a0 <\/span>(12,23)-(15,30) batch id : 0<\/p>\n

[77,1] element, prob = 0.0273438\u00a0 \u00a0 <\/span>(43,30)-(47,38) batch id : 0<\/p>\n

[78,1] element, prob = 0.0273438\u00a0 \u00a0 <\/span>(29,49)-(34,59) batch id : 0<\/p>\n

[79,1] element, prob = 0.0273438\u00a0 \u00a0 <\/span>(31,50)-(34,57) batch id : 0<\/p>\n

[80,1] element, prob = 0.0268555\u00a0 \u00a0 <\/span>(29,1)-(32,5) batch id : 0<\/p>\n

[81,1] element, prob = 0.0268555\u00a0 \u00a0 <\/span>(31,1)-(34,5) batch id : 0<\/p>\n

[82,1] element, prob = 0.0268555\u00a0 \u00a0 <\/span>(26,15)-(28,18) batch id : 0<\/p>\n

[83,1] element, prob = 0.0268555\u00a0 \u00a0 <\/span>(11,20)-(13,23) batch id : 0<\/p>\n

[84,1] element, prob = 0.0268555\u00a0 \u00a0 <\/span>(16,22)-(17,26) batch id : 0<\/p>\n

[85,1] element, prob = 0.0268555\u00a0 \u00a0 <\/span>(43,30)-(46,34) batch id : 0<\/p>\n

[86,1] element, prob = 0.0268555\u00a0 \u00a0 <\/span>(45,30)-(47,34) batch id : 0<\/p>\n

[87,1] element, prob = 0.0268555\u00a0 \u00a0 <\/span>(46,31)-(49,36) batch id : 0<\/p>\n

[88,1] element, prob = 0.0268555\u00a0 \u00a0 <\/span>(43,35)-(46,39) batch id : 0<\/p>\n

[89,1] element, prob = 0.0268555\u00a0 \u00a0 <\/span>(3,3)-(6,13) batch id : 0<\/p>\n

[90,1] element, prob = 0.0268555\u00a0 \u00a0 <\/span>(26,7)-(29,14) batch id : 0<\/p>\n

[91,1] element, prob = 0.0268555\u00a0 \u00a0 <\/span>(12,11)-(15,16) batch id : 0<\/p>\n

[92,1] element, prob = 0.0268555\u00a0 \u00a0 <\/span>(26,11)-(30,18) batch id : 0<\/p>\n

[93,1] element, prob = 0.0268555\u00a0 \u00a0 <\/span>(11,19)-(13,24) batch id : 0<\/p>\n

[94,1] element, prob = 0.0268555\u00a0 \u00a0 <\/span>(16,17)-(19,23) batch id : 0<\/p>\n

[95,1] element, prob = 0.0268555\u00a0 \u00a0 <\/span>(33,17)-(41,26) batch id : 0<\/p>\n

[96,1] element, prob = 0.0268555\u00a0 \u00a0 <\/span>(8,23)-(11,29) batch id : 0<\/p>\n

[97,1] element, prob = 0.0268555\u00a0 \u00a0 <\/span>(13,18)-(18,27) batch id : 0<\/p>\n

[98,1] element, prob = 0.0268555\u00a0 \u00a0 <\/span>(29,0)-(36,7) batch id : 0<\/p>\n

[99,1] element, prob = 0.0268555\u00a0 \u00a0 <\/span>(30,39)-(37,49) batch id : 0<\/p>\n

[100,1] element, prob = 0.0268555\u00a0 \u00a0 <\/span>(3,0)-(13,34) batch id : 0<\/p>\n

[101,1] element, prob = 0.0268555\u00a0 \u00a0 <\/span>(39,-1)-(61,19) batch id : 0<\/p>\n

[102,1] element, prob = 0.0258789\u00a0 \u00a0 <\/span>(28,0)-(32,3) batch id : 0<\/p>\n

[103,1] element, prob = 0.0258789\u00a0 \u00a0 <\/span>(27,5)-(29,8) batch id : 0<\/p>\n

[104,1] element, prob = 0.0258789\u00a0 \u00a0 <\/span>(14,7)-(16,11) batch id : 0<\/p>\n

[105,1] element, prob = 0.0258789\u00a0 \u00a0 <\/span>(14,9)-(16,13) batch id : 0<\/p>\n

[106,1] element, prob = 0.0258789\u00a0 \u00a0 <\/span>(9,12)-(11,15) batch id : 0<\/p>\n

[107,1] element, prob = 0.0258789\u00a0 \u00a0 <\/span>(14,12)-(16,16) batch id : 0<\/p>\n

[108,1] element, prob = 0.0258789\u00a0 \u00a0 <\/span>(24,12)-(26,16) batch id : 0<\/p>\n

[ INFO ] Image out_0.bmp created!<\/p>\n

[ INFO ] Execution successful<\/p>\n

[ INFO ] This sample is an API example, for any performance measurements please use the dedicated benchmark_app tool<\/p>\n

real 0m4.920s<\/p>\n

user 0m2.755s<\/p>\n

sys 0m0.539s<\/p>\n","protected":false},"excerpt":{"rendered":"

Movidius Neural Compute Stick2(NSC2)\u306f\u3001USB3.0 \u5bfe\u5fdc\u306a\u306e\u3067\u3059\u304c\u3001Raspberry Pi Model 3+\u307e\u3067USB2.0\u306b\u3057\u304b\u5bfe\u5fdc\u3057\u3066\u3044\u307e\u305b\u3093\u3067\u3057\u305f\u3002USB3.0\u306b\u5bfe\u5fdc\u3057\u305fRa…<\/p>\n

Read more →<\/a><\/p>\n","protected":false},"author":1,"featured_media":0,"comment_status":"closed","ping_status":"closed","sticky":false,"template":"","format":"standard","meta":[],"categories":[1],"tags":[],"_links":{"self":[{"href":"https:\/\/research.itplants.com\/index.php?rest_route=\/wp\/v2\/posts\/2675"}],"collection":[{"href":"https:\/\/research.itplants.com\/index.php?rest_route=\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/research.itplants.com\/index.php?rest_route=\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/research.itplants.com\/index.php?rest_route=\/wp\/v2\/users\/1"}],"replies":[{"embeddable":true,"href":"https:\/\/research.itplants.com\/index.php?rest_route=%2Fwp%2Fv2%2Fcomments&post=2675"}],"version-history":[{"count":7,"href":"https:\/\/research.itplants.com\/index.php?rest_route=\/wp\/v2\/posts\/2675\/revisions"}],"predecessor-version":[{"id":2696,"href":"https:\/\/research.itplants.com\/index.php?rest_route=\/wp\/v2\/posts\/2675\/revisions\/2696"}],"wp:attachment":[{"href":"https:\/\/research.itplants.com\/index.php?rest_route=%2Fwp%2Fv2%2Fmedia&parent=2675"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/research.itplants.com\/index.php?rest_route=%2Fwp%2Fv2%2Fcategories&post=2675"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/research.itplants.com\/index.php?rest_route=%2Fwp%2Fv2%2Ftags&post=2675"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}