OpenModelZoo4 - PukiWiki

Open Model Zoo Demos を動かす４ †

　第11世代 CPU(Core™ i7) を搭載したノートパソコン「DELL Latitude 752」で、OpenVINO™ツールキット付属のデモソフトを動かしその速度を調べる。

Open Model Zoo Demos を動かす４
参考資料

※ 最終更新:2021/05/14　

↑

3D Human Pose Estimation Python* Demo †

↑

デモの実行 †

① 実行例「Ubuntu on Core™ i7-1185G7」+ GPU (FP16)

$ cd ~/run_app/
$ ./_human_pose_estimation_3d_demo_g16.sh
[human_pose_estimation_3d_demog16.sh] 'human_pose_estimation_3d_demo (GPUi16)' Run !!

② 実行例「Ubuntu on Core™ i7-1185G7」+ GPU (FP32)

$ cd ~/run_app/
$ ./_human_pose_estimation_3d_demo_g32.sh 
[human_pose_estimation_3d_demo_g32.sh] 'human_pose_estimation_3d_demo (GPU32)' Run !!

③ 実行例「Ubuntu on Core™ i7-1185G7」

$ cd ~/run_app/
$ ./_human_pose_estimation_3d_demo.sh 
[human_pose_estimation_3d_demo.sh] 'human_pose_estimation_3d_demo' Run !!

④ 実行例「Ubuntu on Core™ i7-1185G7」+ NCS2

$ cd ~/run_app/
$ ./_human_pose_estimation_3d_demo_16.sh 
[human_pose_estimation_3d_demo_16.sh] 'human_pose_estimation_3d_demo (NCS2)' Run !!

↑

速度比較 †

項目	①	②	③	④	Core™i5-10210
fps	41	30.2	13.8	4.1	13.5

↑

Action Recognition Python* Demo †

↑

デモの実行 †

① 実行例「Ubuntu on Core™ i7-1185G7」+ GPU (FP16)

$ cd ~/run_app/
$ ./_action_recognition_g16.sh
[action_recognition_demo_g16.sh] 'action_recognition_demo (GPU16)' Run !!
Reading IR...
Loading IR to the plugin...
Reading IR...
Loading IR to the plugin...
To close the application, press 'CTRL+C' here or switch to the output window and press Esc or Q
Frame 15: Safe driving - 85.58% -- 4.41ms
Frame 16: Safe driving - 87.41% -- 6.60ms
    :
    :
Frame 48: Safe driving - 68.92% -- 5.57ms
Frame 49: Safe driving - 65.85% -- 5.70ms
finishing <action_recognition_demo.steps.RenderStep object at 0x7f55cd420910>
Data total: 1.56ms (+/-: 0.86) 642.31fps
Data   own: 1.54ms (+/-: 0.85) 648.05fps
Encoder total: 5.08ms (+/-: 1.00) 196.72fps
Encoder   own: 5.07ms (+/-: 1.00) 197.41fps
Decoder total: 0.81ms (+/-: 2.69) 1239.07fps
Decoder   own: 0.80ms (+/-: 2.68) 1255.55fps
Render total: 32.92ms (+/-: 23.60) 30.37fps
Render   own: 32.62ms (+/-: 22.11) 30.66fps

② 実行例「Ubuntu on Core™ i7-1185G7」+ GPU (FP32)

$ cd ~/run_app/
$ ./_action_recognition_g32.sh 
[action_recognition_demo_g32.sh] 'action_recognition_demo (GPU32)' Run !!
Reading IR...
Loading IR to the plugin...
Reading IR...
Loading IR to the plugin...
To close the application, press 'CTRL+C' here or switch to the output window and press Esc or Q
Frame 15: Safe driving - 85.45% -- 4.87ms
Frame 16: Safe driving - 87.28% -- 10.16ms
    :
    :
Frame 21: Safe driving - 90.39% -- 15.68ms
Frame 22: Safe driving - 88.57% -- 16.71ms
finishing <action_recognition_demo.steps.RenderStep object at 0x7f3c2f974910>
Data total: 1.89ms (+/-: 1.33) 528.10fps
Data   own: 1.88ms (+/-: 1.33) 532.22fps
Encoder total: 5.36ms (+/-: 0.95) 186.41fps
Encoder   own: 5.34ms (+/-: 0.95) 187.10fps
Decoder total: 13.09ms (+/-: 12.23) 76.40fps
Decoder   own: 13.08ms (+/-: 12.22) 76.48fps
Render total: 46.10ms (+/-: 36.55) 21.69fps
Render   own: 45.37ms (+/-: 33.95) 22.04fps

③ 実行例「Ubuntu on Core™ i7-1185G7」

$ cd ~/run_app/
$ ./_action_recognition.sh 
[action_recognition_demo.sh] 'action_recognition_demo' Run !!
Reading IR...
Loading IR to the plugin...
Reading IR...
Loading IR to the plugin...
To close the application, press 'CTRL+C' here or switch to the output window and press Esc or Q
Frame 15: Safe driving - 85.45% -- 3.75ms
Frame 16: Safe driving - 87.28% -- 7.56ms
    :
    :
Frame 28: Safe driving - 92.08% -- 25.57ms
Frame 29: Safe driving - 95.27% -- 26.71ms
finishing <action_recognition_demo.steps.RenderStep object at 0x7f590a860910>
Data total: 1.81ms (+/-: 1.65) 551.52fps
Data   own: 1.80ms (+/-: 1.65) 555.47fps
Encoder total: 5.43ms (+/-: 3.87) 184.19fps
Encoder   own: 5.41ms (+/-: 3.87) 184.84fps
Decoder total: 15.19ms (+/-: 9.64) 65.81fps
Decoder   own: 15.18ms (+/-: 9.63) 65.88fps
Render total: 42.39ms (+/-: 31.83) 23.59fps
Render   own: 40.99ms (+/-: 30.48) 24.40fps

④ 実行例「Ubuntu on Core™ i7-1185G7」+ NCS2

$ cd ~/run_app/
$ ./_action_recognition_16.sh 
[action_recognition_demo_16.sh] 'action_recognition_demo (NCS2)' Run !!
Reading IR...
Loading IR to the plugin...
[Warning][VPU][Config] Deprecated option was used : VPU_HW_STAGES_OPTIMIZATION
Reading IR...
Loading IR to the plugin...
To close the application, press 'CTRL+C' here or switch to the output window and press Esc or Q
Frame 15: Safe driving - 84.79% -- 9.88ms
Frame 16: Safe driving - 86.75% -- 13.42ms
    :
    :
Frame 30: Safe driving - 96.93% -- 12.22ms
Frame 31: Safe driving - 97.43% -- 12.16ms
finishing <action_recognition_demo.steps.RenderStep object at 0x7fd2dc778af0>
Data total: 2.30ms (+/-: 1.59) 434.61fps
Data   own: 2.29ms (+/-: 1.58) 437.57fps
Encoder total: 7.99ms (+/-: 4.21) 125.20fps
Encoder   own: 7.97ms (+/-: 4.20) 125.54fps
Decoder total: 1.72ms (+/-: 4.97) 579.88fps
Decoder   own: 1.71ms (+/-: 4.97) 585.08fps
Render total: 31.41ms (+/-: 41.04) 31.84fps
Render   own: 30.80ms (+/-: 36.48) 32.47fps

↑

速度比較 †

項目		①	②	③	④	Core™i5-10210
Data totai	fps	642	528	552	435	1152
Data totai	ms	1.56	1.89	1.81	2.30	0.87
Encoder total	fps	197	186	184	125	235
Encoder total	ms	5.1	5.38	5.43	7.99	4.3
Decoder total	fps	1239	76.4	65.8	580	44
Decoder total	ms	0.81	13.1	15.2	1.72	23
Render total	fps	30.4	21.7	23.6	31.8	27
Render total	ms	33	46.1	42.4	31.4	37

↑

Object Detection Python* Demo †

↑

デモの実行 †

① 実行例「Ubuntu on Core™ i7-1185G7」+ GPU (FP16)

$ cd ~/run_app/
$ ./_object_detection_python_demo_g16.sh 
[object_detection_demo/_g16.sh] 'object_detection_demo (GPU16)' Run !!
[ INFO ] Initializing Inference Engine...
[ INFO ] Loading network...
[ INFO ] Reading network from IR...
[ INFO ] Loading network to GPU plugin...
[ INFO ] Starting inference...
To close the application, press 'CTRL+C' here or switch to the output window and press ESC key
Latency: 93.0 ms
FPS: 10.5

② 実行例「Ubuntu on Core™ i7-1185G7」+ GPU (FP32)

$ cd ~/run_app/
$ ./_object_detection_python_demo_g32.sh 
[object_detection_demo/_g32.sh] 'object_detection_demo (GPU32)' Run !!
[ INFO ] Initializing Inference Engine...
[ INFO ] Loading network...
[ INFO ] Reading network from IR...
[ INFO ] Loading network to GPU plugin...
[ INFO ] Starting inference...
To close the application, press 'CTRL+C' here or switch to the output window and press ESC key
Latency: 124.0 ms
FPS: 7.9

③ 実行例「Ubuntu on Core™ i7-1185G7」

$ cd ~/run_app/
$ ./_object_detection_python_demo.sh 
[object_detection_demo.sh] 'object_detection_demo' Run !!
[ INFO ] Initializing Inference Engine...
[ INFO ] Loading network...
[ INFO ] Reading network from IR...
[ INFO ] Loading network to CPU plugin...
[ INFO ] Starting inference...
To close the application, press 'CTRL+C' here or switch to the output window and press ESC key
Latency: 234.8 ms
FPS: 4.2

④ 実行例「Ubuntu on Core™ i7-1185G7」+ NCS2

$ cd ~/run_app/
$ ./_object_detection_python_demo_16.sh 
[object_detection_demo/_16.sh] 'object_detection_demo (NCS2)' Run !!
[ INFO ] Initializing Inference Engine...
[ INFO ] Loading network...
[ INFO ] Reading network from IR...
[ INFO ] Loading network to MYRIAD plugin...
[ INFO ] Starting inference...
To close the application, press 'CTRL+C' here or switch to the output window and press ESC key
Latency: 466.3 ms
FPS: 2.1

↑

速度比較 †

項目	①	②	③	④	Core™i5-10210
Latency(ms)	33.0	124	235	466	219.2
fps	10.5	7.9	4.2	2.1	4.5

↑

Human Pose Estimation Python* Demo †

↑

デモの実行 †

① 実行例「Ubuntu on Core™ i7-1185G7」+ GPU (FP16)

$ cd ~/run_app/
$ ./_human_pose_estimation_g16.sh 
[human_pose_estimation_demo_g16.sh] 'human_pose_estimation_demo (GPU16)' Run !!
[ INFO ] Initializing Inference Engine...
[ INFO ] Loading network...
[ INFO ] Reading network from IR...
[ INFO ] Reshape net to {'data': [1, 3, 256, 456]}
[ INFO ] Loading network to GPU plugin...
[ INFO ] Starting inference...
To close the application, press 'CTRL+C' here or switch to the output window and press ESC key
Latency: 23.2 ms
FPS: 38.8

② 実行例「Ubuntu on Core™ i7-1185G7」+ GPU (FP32)

$ cd ~/run_app/
$ ./_human_pose_estimation_g32.sh 
[human_pose_estimation_demo_g32.sh] 'human_pose_estimation_demo (GPU32)' Run !!
[ INFO ] Initializing Inference Engine...
[ INFO ] Loading network...
[ INFO ] Reading network from IR...
[ INFO ] Reshape net to {'data': [1, 3, 256, 456]}
[ INFO ] Loading network to GPU plugin...
[ INFO ] Starting inference...
To close the application, press 'CTRL+C' here or switch to the output window and press ESC key
Latency: 28.5 ms
FPS: 32.2

③ 実行例「Ubuntu on Core™ i7-1185G7」

$ cd ~/run_app/
$ ./_human_pose_estimation.sh 
[human_pose_estimation_demo.sh] 'human_pose_estimation_demo' Run !!
[ INFO ] Initializing Inference Engine...
[ INFO ] Loading network...
[ INFO ] Reading network from IR...
[ INFO ] Reshape net to {'data': [1, 3, 256, 456]}
[ INFO ] Loading network to CPU plugin...
[ INFO ] Starting inference...
To close the application, press 'CTRL+C' here or switch to the output window and press ESC key
Latency: 51.4 ms
FPS: 18.5

④ 実行例「Ubuntu on Core™ i7-1185G7」+ NCS2

$ cd ~/run_app/
$ ./_human_pose_estimation_16.sh 
[human_pose_estimation_demo_16.sh] 'human_pose_estimation_demo (NCS2)' Run !!
[ INFO ] Initializing Inference Engine...
[ INFO ] Loading network...
[ INFO ] Reading network from IR...
[ INFO ] Reshape net to {'data': [1, 3, 256, 456]}
[ INFO ] Loading network to MYRIAD plugin...
[ INFO ] Starting inference...
To close the application, press 'CTRL+C' here or switch to the output window and press ESC key
Latency: 212.1 ms
FPS: 4.5

↑

速度比較 †

項目	①	②	③	④	Core™i5-10210
Latency (ms)	23.2	28.5	51.4	212	44.1
FPS	38.8	32.2	18.5	4.5	17.3

↑

Gesture Recognition Python* Demo †

↑

デモの実行 †

① 実行例「Ubuntu on Core™ i7-1185G7」+ GPU (FP16)

$ cd ~/run_app/
$ ./_gesture_recognition_demo_g16.sh
[gesture_recognition_demo_g16.sh] 'gesture_recognition_demo (GPU16)' Run !!

$ ./_gesture_recognition_demo_g16.sh ~/Videos/ASL_TankYou.mp4
[gesture_recognition_demo_g16.sh] 'gesture_recognition_demo (GPU16)' Run !!

② 実行例「Ubuntu on Core™ i7-1185G7」+ GPU (FP32)

$ cd ~/run_app/
$ ./_gesture_recognition_demo_g32.sh 
[gesture_recognition_demo_g32.sh] 'gesture_recognition_demo (GPU32)' Run !!

$ ./_gesture_recognition_demo_g32.sh  ~/Videos/ASL_TankYou.mp4
[gesture_recognition_demo_g32.sh] 'gesture_recognition_demo (GPU32)' Run !!

③ 実行例「Ubuntu on Core™ i7-1185G7」

$ cd ~/run_app/
$ ./_gesture_recognition_demo.sh 
[gesture_recognition_demo.sh] 'gesture_recognition_demo' Run !!

$ ./_gesture_recognition_demo.sh ~/Videos/ASL_TankYou.mp4
[gesture_recognition_demo.sh] 'gesture_recognition_demo' Run !!

↑

速度比較 †

項目	①	②	③	④	Core™i5-10210
fps	13.5	13.5	14.3	X	14.3
fps	13.5	13.5	14.5	X	14.5

↑

Handwritten Text Recognition Demo †

↑

デモの実行 †

① 実行例「Ubuntu on Core™ i7-1185G7」+ GPU (FP16)

$ cd ~/run_app/
$ ./_handwritten_text_recognition_demo_g16.sh
[handwritten_text_recognition_demo_g16.sh] 'handwritten_text_recognition_demo (GPU16)' Run !!
[ INFO ] Loading network
[ INFO ] Preparing input/output blobs
[ INFO ] Loading model to the plugin
[ INFO ] Starting inference (1 iterations)
['菊池朋子']
[ INFO ] Average throughput: 52.72960662841797 ms

② 実行例「Ubuntu on Core™ i7-1185G7」+ GPU (FP32)

$ cd ~/run_app_16/
$ ./_handwritten_text_recognition_demo_g32.sh
[handwritten_text_recognition_demo_g32.sh] 'handwritten_text_recognition_demo (GPU32)' Run !!
[ INFO ] Loading network
[ INFO ] Preparing input/output blobs
[ INFO ] Loading model to the plugin
[ INFO ] Starting inference (1 iterations)
['菊池朋子']
[ INFO ] Average throughput: 91.24350547790527 ms

③ 実行例「Ubuntu on Core™ i7-1185G7」

$ cd ~/run_app/
$ ./_handwritten_text_recognition_demo.sh 
[handwritten_text_recognition_demo.sh] 'handwritten_text_recognition_demo' Run !!
[ INFO ] Loading network
[ INFO ] Preparing input/output blobs
[ INFO ] Loading model to the plugin
[ INFO ] Starting inference (1 iterations)
['菊池朋子']
[ INFO ] Average throughput: 373.03948402404785 ms

④ 実行例「Ubuntu on Core™ i7-1185G7」+ NCS2

$ cd ~/run_app_16/
$ ./_handwritten_text_recognition_demo_16.sh 
[handwritten_text_recognition_demo_16.sh] 'handwritten_text_recognition_demo (NCS)' Run !!
[ INFO ] Loading network
[ INFO ] Preparing input/output blobs
[ INFO ] Loading model to the plugin
[ INFO ] Starting inference (1 iterations)
['菊池朋子']
[ INFO ] Average throughput: 914.8960113525391 ms

↑

速度比較 †

項目	①	②	③	④	Core™i5-10210
Average throughput(ms)	52.7	91.2	373	314	277

↑

Text Detection C++ Demo †

↑

デモの実行 †

① 実行例「Ubuntu on Core™ i7-1185G7」+ GPU (FP16)

$ cd ~/run_app/
$ ./_text_detection_demo_g16.sh
[text_detection_demo_g16.sh] 'text_detection_demo (GPU16)' Run !!
InferenceEngine: 	API version ......... 2.1
	Build ........... 2021.3.0-2787-60059f2c755-releases/2021/3
[ INFO ] Parsing input parameters
[ INFO ] Loading Inference Engine
[ INFO ] Device info: 
[ INFO ] 	GPU
	clDNNPlugin version ......... 2.1
	Build ........... 2021.3.0-2787-60059f2c755-releases/2021/3

[ INFO ] Loading network files
[ INFO ] Starting inference
To close the application, press 'CTRL+C' here or switch to the output window and press ESC or Q
text detection model inference (ms) (fps): 40.8947 24.453
text detection postprocessing (ms) (fps): 73.7368 13.5617

text recognition model inference (ms) (fps): 54.3045 18.4147
text recognition postprocessing (ms) (fps): 0.00914286 109375

text crop (ms) (fps): 0.0830639 12038.9

※ 起動までに大変時間を要する。(約11分)

② 実行例「Ubuntu on Core™ i7-1185G7」+ GPU (FP32)

$ cd ~/run_app/
$ ./_text_detection_demo_g32.sh
[text_detection_demo_g32.sh] 'text_detection_demo (GPU32)' Run !!
InferenceEngine: 	API version ......... 2.1
	Build ........... 2021.3.0-2787-60059f2c755-releases/2021/3
[ INFO ] Parsing input parameters
[ INFO ] Loading Inference Engine
[ INFO ] Device info: 
[ INFO ] 	GPU
	clDNNPlugin version ......... 2.1
	Build ........... 2021.3.0-2787-60059f2c755-releases/2021/3

[ INFO ] Loading network files
[ INFO ] Starting inference
To close the application, press 'CTRL+C' here or switch to the output window and press ESC or Q
text detection model inference (ms) (fps): 62 16.129
text detection postprocessing (ms) (fps): 90.7273 11.022

text recognition model inference (ms) (fps): 59.0325 16.9398
text recognition postprocessing (ms) (fps): 0.00918831 108834

text crop (ms) (fps): 0.0831818 12021.9

※ 起動までに大変時間を要する。(約11分)

③ 実行例「Ubuntu on Core™ i7-1185G7」

$ cd ~/run_app/
$ ./_text_detection_demo.sh 
[text_detection_demo.sh] 'text_detection_demo' Run !!
InferenceEngine: 	API version ......... 2.1
	Build ........... 2021.3.0-2787-60059f2c755-releases/2021/3
[ INFO ] Parsing input parameters
[ INFO ] Loading Inference Engine
[ INFO ] Device info: 
[ INFO ] 	CPU
	MKLDNNPlugin version ......... 2.1
	Build ........... 2021.3.0-2787-60059f2c755-releases/2021/3

[ INFO ] Loading network files
[ INFO ] Starting inference
To close the application, press 'CTRL+C' here or switch to the output window and press ESC or Q
text detection model inference (ms) (fps): 103.35 9.67586
text detection postprocessing (ms) (fps): 56.9 17.5747

text recognition model inference (ms) (fps): 8.13571 122.915
text recognition postprocessing (ms) (fps): 0.00943214 106020

text crop (ms) (fps): 0.0743107 13457

④ 実行例「Ubuntu on Core™ i7-1185G7」+ NCS2

$ cd ~/run_app/
$ ./_text_detection_demo_16.sh 
[text_detection_demo_16.sh] 'text_detection_demo (NCS2)' Run !!
InferenceEngine: 	API version ......... 2.1
	Build ........... 2021.3.0-2787-60059f2c755-releases/2021/3
[ INFO ] Parsing input parameters
[ INFO ] Loading Inference Engine
[ INFO ] Device info: 
[ INFO ] 	MYRIAD
	myriadPlugin version ......... 2.1
	Build ........... 2021.3.0-2787-60059f2c755-releases/2021/3

[ INFO ] Loading network files
[ INFO ] Starting inference
To close the application, press 'CTRL+C' here or switch to the output window and press ESC or Q
text detection model inference (ms) (fps): 647.625 1.5441
text detection postprocessing (ms) (fps): 86.625 11.544

text recognition model inference (ms) (fps): 76.5583 13.0619
text recognition postprocessing (ms) (fps): 0.0169917 58852.4

text crop (ms) (fps): 0.133542 7488.3

↑

速度比較 †

項目		①	②	③	④	Core™i5-10210
detection model inference	ms	40.9	62	103	648	102
detection model inference	fps	24.5	16.1	9.68	1.54	9.8
detection model postprocessing	ms	73.7	90.7	56.9	86.6	40.4
detection model postprocessing	fps	13.6	11.0	17.6	11.5	24.7
recognition model inference	ms	54.3	59.0	8.14	76.6	7.1
recognition model inference	fps	18.4	16.9	122.9	13.1	140
recognition model postprocessing	ms	0.0091	0.0091	0.0094	0.018	0.007
recognition model postprocessing	fps	109375	108834	106020	58852	136364

↑

Crossroad Camera C++ Demo †

↑

デモの実行] †

① 実行例「Ubuntu on Core™ i7-1185G7」+ GPU (FP16)

$ cd ~/run_app/
$ ./_crossroad_camera_demo_g16.sh 
[crossroad_camera_demo_g16.sh] 'crossroad_camera_demo (GPU16)' Run !!
InferenceEngine: 	API version ......... 2.1
	Build ........... 2021.3.0-2787-60059f2c755-releases/2021/3
[ INFO ] Parsing input parameters
[ INFO ] Person Attributes Recognition detection DISABLED
[ INFO ] Person Reidentification Retail detection DISABLED
[ INFO ] Loading device GPU
[ INFO ] 	GPU
	clDNNPlugin version ......... 2.1
	Build ........... 2021.3.0-2787-60059f2c755-releases/2021/3

[ INFO ] Loading network files for PersonDetection
[ INFO ] Batch size is forced to  1
[ INFO ] Checking Person Detection inputs
[ INFO ] Checking Person Detection outputs
[ INFO ] Loading Person Detection model to the GPU device
[ INFO ] Start inference 
To close the application, press 'CTRL+C' here or switch to the output window and press ESC key
[ INFO ] Total Inference time: 53685.9

[ INFO ] Execution successful

② 実行例「Ubuntu on Core™ i7-1185G7」+ GPU (FP32)

$ cd ~/run_app/
$ ./_crossroad_camera_demo_g32.sh 
[crossroad_camera_demo_g32.sh] 'crossroad_camera_demo (GPU32)' Run !!
InferenceEngine: 	API version ......... 2.1
	Build ........... 2021.3.0-2787-60059f2c755-releases/2021/3
[ INFO ] Parsing input parameters
[ INFO ] Person Attributes Recognition detection DISABLED
[ INFO ] Person Reidentification Retail detection DISABLED
[ INFO ] Loading device GPU
[ INFO ] 	GPU
	clDNNPlugin version ......... 2.1
	Build ........... 2021.3.0-2787-60059f2c755-releases/2021/3

[ INFO ] Loading network files for PersonDetection
[ INFO ] Batch size is forced to  1
[ INFO ] Checking Person Detection inputs
[ INFO ] Checking Person Detection outputs
[ INFO ] Loading Person Detection model to the GPU device
[ INFO ] Start inference 
To close the application, press 'CTRL+C' here or switch to the output window and press ESC key
[ INFO ] Total Inference time: 37541.1

[ INFO ] Execution successful

③ 実行例「Ubuntu on Core™ i7-1185G7」

$ cd ~/run_app/
$ ./_crossroad_camera_demo.sh 
[crossroad_camera_demo.sh] 'crossroad_camera_demo' Run !!
InferenceEngine: 	API version ......... 2.1
	Build ........... 2021.3.0-2787-60059f2c755-releases/2021/3
[ INFO ] Parsing input parameters
[ INFO ] Person Attributes Recognition detection DISABLED
[ INFO ] Person Reidentification Retail detection DISABLED
[ INFO ] Loading device CPU
[ INFO ] 	CPU
	MKLDNNPlugin version ......... 2.1
	Build ........... 2021.3.0-2787-60059f2c755-releases/2021/3

[ INFO ] Loading network files for PersonDetection
[ INFO ] Batch size is forced to  1
[ INFO ] Checking Person Detection inputs
[ INFO ] Checking Person Detection outputs
[ INFO ] Loading Person Detection model to the CPU device
[ INFO ] Start inference 
To close the application, press 'CTRL+C' here or switch to the output window and press ESC key
[ INFO ] Total Inference time: 24514.2

[ INFO ] Execution successfulm

④ 実行例「Ubuntu on Core™ i7-1185G7」+ NCS2

$ cd ~/run_app/
$ ./_crossroad_camera_demo_16.sh 
[crossroad_camera_demo_16.sh] 'crossroad_camera_demo (NCS2)' Run !!
InferenceEngine: 	API version ......... 2.1
	Build ........... 2021.3.0-2787-60059f2c755-releases/2021/3
[ INFO ] Parsing input parameters
[ INFO ] Person Attributes Recognition detection DISABLED
[ INFO ] Person Reidentification Retail detection DISABLED
[ INFO ] Loading device MYRIAD
[ INFO ] 	MYRIAD
	myriadPlugin version ......... 2.1
	Build ........... 2021.3.0-2787-60059f2c755-releases/2021/3

[ INFO ] Loading network files for PersonDetection
[ INFO ] Batch size is forced to  1
[ INFO ] Checking Person Detection inputs
[ INFO ] Checking Person Detection outputs
[ INFO ] Loading Person Detection model to the MYRIAD device
[ INFO ] Start inference 
To close the application, press 'CTRL+C' here or switch to the output window and press ESC key
[ INFO ] Total Inference time: 29247.3

[ INFO ] Execution successful

↑

速度比較 †

項目	①	②	③	④	Core™i5-10210
detection time(ms)	20	17.6	24.3	269.2	30
fps	74	56	40.1	3.71	32

↑

Human Pose Estimation C++ Demo †

↑

デモの実行 †

① 実行例「Ubuntu on Core™ i7-1185G7」+ GPU (FP16)

$ cd ~/run_app/
$ ./_human_pose_estimation_g16.sh 
[human_pose_estimation_demo_g16.sh] 'human_pose_estimation_demo (GPU16)' Run !!
[ INFO ] Initializing Inference Engine...
[ INFO ] Loading network...
[ INFO ] Reading network from IR...
[ INFO ] Reshape net to {'data': [1, 3, 256, 456]}
[ INFO ] Loading network to GPU plugin...
[ INFO ] Starting inference...
To close the application, press 'CTRL+C' here or switch to the output window and press ESC key
Latency: 23.5 ms
FPS: 37.9

② 実行例「Ubuntu on Core™ i7-1185G7」+ GPU (FP32)

$ cd ~/run_app/
$ ./_human_pose_estimation_g32.sh 
[human_pose_estimation_demo_g32.sh] 'human_pose_estimation_demo (GPU32)' Run !!
[ INFO ] Initializing Inference Engine...
[ INFO ] Loading network...
[ INFO ] Reading network from IR...
[ INFO ] Reshape net to {'data': [1, 3, 256, 456]}
[ INFO ] Loading network to GPU plugin...
[ INFO ] Starting inference...
To close the application, press 'CTRL+C' here or switch to the output window and press ESC key
Latency: 28.7 ms
FPS: 31.3

③ 実行例「Ubuntu on Core™ i7-1185G7」

$ cd ~/run_app/
$ ./_human_pose_estimation.sh 
[human_pose_estimation_demo.sh] 'human_pose_estimation_demo' Run !!
[ INFO ] Initializing Inference Engine...
[ INFO ] Loading network...
[ INFO ] Reading network from IR...
[ INFO ] Reshape net to {'data': [1, 3, 256, 456]}
[ INFO ] Loading network to CPU plugin...
[ INFO ] Starting inference...
To close the application, press 'CTRL+C' here or switch to the output window and press ESC key
Latency: 51.8 ms
FPS: 18.5

④ 実行例「Ubuntu on Core™ i7-1185G7」+ NCS2

$ cd ~/run_app/
$ ./_human_pose_estimation_16.sh 
[human_pose_estimation_demo_16.sh] 'human_pose_estimation_demo (NCS2)' Run !!
[ INFO ] Initializing Inference Engine...
[ INFO ] Loading network...
[ INFO ] Reading network from IR...
[ INFO ] Reshape net to {'data': [1, 3, 256, 456]}
[ INFO ] Loading network to MYRIAD plugin...
[ INFO ] Starting inference...
To close the application, press 'CTRL+C' here or switch to the output window and press ESC key
Latency: 212.2 ms
FPS: 4.5

↑

速度比較 †

項目	①	②	③	④	Core™i5-10210
Latency (ms)	23.5	28.7	51.8	212.2	43.4
FPS	37.9	31.3	18.5	4.5	21.5

　※「2021.3」で変更あり。

↑

Object Detection C++ Demo †

↑

デモの実行 †

① 実行例「Ubuntu on Core™ i7-1185G7」+ GPU (FP16)

$ cd ~/run_app/
$ ./_object_detection_demo_g16.sh 
[object_detection_demo_g16.sh] 'object_detection_demo (GPU)' Run !!
[ INFO ] InferenceEngine: 	API version ......... 2.1
	Build ........... 2021.3.0-2787-60059f2c755-releases/2021/3
[ INFO ] Parsing input parameters
[ INFO ] Reading input
[ INFO ] Loading Inference Engine
[ INFO ] Device info: 
[ INFO ] 	GPU
	clDNNPlugin version ......... 2.1
	Build ........... 2021.3.0-2787-60059f2c755-releases/2021/3
Loading network files
[ INFO ] Batch size is forced to 1.
[ INFO ] Checking that the inputs are as the demo expects
[ INFO ] Checking that the outputs are as the demo expects
[ INFO ] Loading model to the device

[ INFO ] Metric reports:
Latency: 20.3 ms
FPS: 214.7
[ INFO ] 

[ INFO ] The execution has completed successfully

② 実行例「Ubuntu on Core™ i7-1185G7」+ GPU (FP32)

$ cd ~/run_app/
$ ./_object_detection_demo_g32.sh 
[object_detection_demo_g32.sh] 'object_detection_demo (GPU32)' Run !!
[ INFO ] InferenceEngine: 	API version ......... 2.1
	Build ........... 2021.3.0-2787-60059f2c755-releases/2021/3
[ INFO ] Parsing input parameters
[ INFO ] Reading input
[ INFO ] Loading Inference Engine
[ INFO ] Device info: 
[ INFO ] 	GPU
	clDNNPlugin version ......... 2.1
	Build ........... 2021.3.0-2787-60059f2c755-releases/2021/3
Loading network files
[ INFO ] Batch size is forced to 1.
[ INFO ] Checking that the inputs are as the demo expects
[ INFO ] Checking that the outputs are as the demo expects
[ INFO ] Loading model to the device

[ INFO ] Metric reports:
Latency: 30.9 ms
FPS: 151.7
[ INFO ] 

[ INFO ] The execution has completed successfully

③ 実行例「Ubuntu on Core™ i7-1185G7」

$ cd ~/run_app/
$ ./_object_detection_demo.sh 
[object_detection_demo.sh] 'object_detection_demo' Run !!
[ INFO ] InferenceEngine: 	API version ......... 2.1
	Build ........... 2021.3.0-2787-60059f2c755-releases/2021/3
[ INFO ] Parsing input parameters
[ INFO ] Reading input
[ INFO ] Loading Inference Engine
[ INFO ] Device info: 
[ INFO ] 	CPU
	MKLDNNPlugin version ......... 2.1
	Build ........... 2021.3.0-2787-60059f2c755-releases/2021/3
Loading network files
[ INFO ] Batch size is forced to 1.
[ INFO ] Checking that the inputs are as the demo expects
[ INFO ] Checking that the outputs are as the demo expects
[ INFO ] Loading model to the device

[ INFO ] Metric reports:
Latency: 44.6 ms
FPS: 104.5
[ INFO ] 

[ INFO ] The execution has completed successfully

④ 実行例「Ubuntu on Core™ i7-1185G7」+ NCS2

$ cd ~/run_app/
$ ./_object_detection_demo_16.sh 
[object_detection_demo_16.sh] 'object_detection_demo (NCS2)' Run !!
[ INFO ] InferenceEngine: 	API version ......... 2.1
	Build ........... 2021.3.0-2787-60059f2c755-releases/2021/3
[ INFO ] Parsing input parameters
[ INFO ] Reading input
[ INFO ] Loading Inference Engine
[ INFO ] Device info: 
[ INFO ] 	MYRIAD
	myriadPlugin version ......... 2.1
	Build ........... 2021.3.0-2787-60059f2c755-releases/2021/3
Loading network files
[ INFO ] Batch size is forced to 1.
[ INFO ] Checking that the inputs are as the demo expects
[ INFO ] Checking that the outputs are as the demo expects
[ INFO ] Loading model to the device

[ INFO ] Metric reports:
Latency: 307.9 ms
FPS: 15.7
[ INFO ] 

[ INFO ] The execution has completed successfully
double free or corruption (fasttop)
Aborted (core dumped)

↑

速度比較 †

項目	①	②	③	④	Core™i5-10210
Latency(ms)	20.3	30.9	44.6	307.9	22
fps	214.7	151.7	104.5	15.7	73.0

↑

Smart Classroom C++ Demo †

↑

デモの実行 †

① 実行例「Ubuntu on Core™ i7-1185G7」+ GPU (FP16)

$ cd ~/run_app/
$ ./_smart_classroom_demo_g16.sh 
[smart_classroom_demo_g16.sh] 'smart_classroom_demo (GPU16)' Run !!
[ INFO ] InferenceEngine: 	API version ......... 2.1
	Build ........... 2021.3.0-2787-60059f2c755-releases/2021/3
[ INFO ] Parsing input parameters
[ INFO ] Loading Inference Engine
[ INFO ] Device info: 
[ INFO ] 	GPU
	clDNNPlugin version ......... 2.1
	Build ........... 2021.3.0-2787-60059f2c755-releases/2021/3

[ INFO ] 	CPU
	MKLDNNPlugin version ......... 2.1
	Build ........... 2021.3.0-2787-60059f2c755-releases/2021/3

[ WARNING ] Face recognition models are disabled!
To close the application, press 'CTRL+C' here or switch to the output window and press ESC key

[ INFO ] Mean FPS: 39.2263
[ INFO ] Frames processed: 363

[ INFO ] Execution successful

② 実行例「Ubuntu on Core™ i7-1185G7」+ GPU (FP32)

$ cd ~/run_app/
$ ./_smart_classroom_demo_g32.sh 
[smart_classroom_demo_g32.sh] 'smart_classroom_demo (GPU32)' Run !!
[ INFO ] InferenceEngine: 	API version ......... 2.1
	Build ........... 2021.3.0-2787-60059f2c755-releases/2021/3
[ INFO ] Parsing input parameters
[ INFO ] Loading Inference Engine
[ INFO ] Device info: 
[ INFO ] 	GPU
	clDNNPlugin version ......... 2.1
	Build ........... 2021.3.0-2787-60059f2c755-releases/2021/3

[ INFO ] 	CPU
	MKLDNNPlugin version ......... 2.1
	Build ........... 2021.3.0-2787-60059f2c755-releases/2021/3

[ WARNING ] Face recognition models are disabled!
To close the application, press 'CTRL+C' here or switch to the output window and press ESC key

[ INFO ] Mean FPS: 22.469
[ INFO ] Frames processed: 87

[ INFO ] Execution successful

③ 実行例「Ubuntu on Core™ i7-1185G7」

$ cd ~/run_app/
$ ./_smart_classroom_demo.sh 
[smart_classroom_demo.sh] 'smart_classroom_demo' Run !!
[ INFO ] InferenceEngine: 	API version ......... 2.1
	Build ........... 2021.3.0-2787-60059f2c755-releases/2021/3
[ INFO ] Parsing input parameters
[ INFO ] Loading Inference Engine
[ INFO ] Device info: 
[ INFO ] 	CPU
	MKLDNNPlugin version ......... 2.1
	Build ........... 2021.3.0-2787-60059f2c755-releases/2021/3

[ WARNING ] Face recognition models are disabled!
To close the application, press 'CTRL+C' here or switch to the output window and press ESC key

[ INFO ] Mean FPS: 20.3443
[ INFO ] Frames processed: 117

[ INFO ] Execution successful

④ 実行例「Ubuntu on Core™ i7-1185G7」+ NCS2

$ cd ~/run_app/
$ ./_smart_classroom_demo_16.sh 
[smart_classroom_demo_16.sh] 'smart_classroom_demo (NCS2)' Run !!
[ INFO ] InferenceEngine: 	API version ......... 2.1
	Build ........... 2021.3.0-2787-60059f2c755-releases/2021/3
[ INFO ] Parsing input parameters
[ INFO ] Loading Inference Engine
[ INFO ] Device info: 
[ INFO ] 	MYRIAD
	myriadPlugin version ......... 2.1
	Build ........... 2021.3.0-2787-60059f2c755-releases/2021/3

[ INFO ] 	CPU
	MKLDNNPlugin version ......... 2.1
	Build ........... 2021.3.0-2787-60059f2c755-releases/2021/3

[ WARNING ] Face recognition models are disabled!
To close the application, press 'CTRL+C' here or switch to the output window and press ESC key

[ INFO ] Mean FPS: 3.70975
[ INFO ] Frames processed: 25

[ INFO ] Execution successful

↑

速度比較 †

項目	①	②	③	④	Core™i5-10210
Mean Fps	39.2	22.5	20.3	3.7	20
Frames processed	363	87	117	25	168

↑

Pedestrian Tracker C++ Demo †

↑

デモの実行 †

① 実行例「Ubuntu on Core™ i7-1185G7」+ GPU (FP16)

$ cd ~/run_app/
$ ./_pedestrian_tracker_demo_g16.sh 
[pedestrian_tracker_demo_g16.sh] 'pedestrian_tracker_demo (GPU16)' Run !!
InferenceEngine: 	API version ......... 2.1
	Build ........... 2021.3.0-2787-60059f2c755-releases/2021/3
Loading device GPU
	GPU
	clDNNPlugin version ......... 2.1
	Build ........... 2021.3.0-2787-60059f2c755-releases/2021/3

To close the application, press 'CTRL+C' here or switch to the output window and press ESC key

Execution successful

② 実行例「Ubuntu on Core™ i7-1185G7」+ GPU (FP32)

$ cd ~/run_app/
$ ./_pedestrian_tracker_demo_g32.sh 
[pedestrian_tracker_demo_g32.sh] 'pedestrian_tracker_demo (GPU32)' Run !!
InferenceEngine: 	API version ......... 2.1
	Build ........... 2021.3.0-2787-60059f2c755-releases/2021/3
Loading device GPU
	GPU
	clDNNPlugin version ......... 2.1
	Build ........... 2021.3.0-2787-60059f2c755-releases/2021/3

To close the application, press 'CTRL+C' here or switch to the output window and press ESC key

Execution successful

③ 実行例「Ubuntu on Core™ i7-1185G7」

$ cd ~/run_app/
$ ./_pedestrian_tracker_demo.sh 
[pedestrian_tracker_demo.sh] 'pedestrian_tracker_demo' Run !!
InferenceEngine: 	API version ......... 2.1
	Build ........... 2021.3.0-2787-60059f2c755-releases/2021/3
Loading device CPU
	CPU
	MKLDNNPlugin version ......... 2.1
	Build ........... 2021.3.0-2787-60059f2c755-releases/2021/3

To close the application, press 'CTRL+C' here or switch to the output window and press ESC key

Execution successful

④ 実行例「Ubuntu on Core™ i7-1185G7」+ NCS2

$ cd ~/run_app/
$ ./_pedestrian_tracker_demo_16.sh 
[pedestrian_tracker_demo_16.sh] 'pedestrian_tracker_demo (NCS2)' Run !!
InferenceEngine: 	API version ......... 2.1
	Build ........... 2021.3.0-2787-60059f2c755-releases/2021/3
Loading device MYRIAD
	MYRIAD
	myriadPlugin version ......... 2.1
	Build ........... 2021.3.0-2787-60059f2c755-releases/2021/3

[ ERROR ] Failed to compile layer "736": Unsupported combination of indices in layer "736". Only across channel and full batch supported.

↑

Super Resolution C++ Demo †

↑

デモの実行 †

① 実行例「Ubuntu on Core™ i7-1185G7」+ GPU (FP16)

$ cd ~/run_app/
$ ./_super_resolution_demo_g16.sh 
[super_resolution_demo_g16.sh] 'super_resolution_demo (GPU16)' Run !!
[ INFO ] InferenceEngine: 	API version ......... 2.1
	Build ........... 2021.3.0-2787-60059f2c755-releases/2021/3
[ INFO ] Parsing input parameters
[ INFO ] Files were added: 1
[ INFO ]     /home/mizutu/Images/image-low.bmp
[ INFO ] Loading Inference Engine
[ INFO ] Device info: 
[ INFO ] 	GPU
	clDNNPlugin version ......... 2.1
	Build ........... 2021.3.0-2787-60059f2c755-releases/2021/3

[ INFO ] Loading network files
[ INFO ] Preparing input blobs
[ INFO ] Batch size is 1
[ INFO ] Preparing output blobs
[ INFO ] Loading model to the device
[ INFO ] Create infer request
To close the application, press 'CTRL+C' here or switch to the output window and press any key
[ INFO ] Start inference
[ INFO ] Output size [N,C,H,W]: 1, 3, 1080, 1920
[ INFO ] Execution successful

[ INFO ] This demo is an API example, for any performance measurements please use the dedicated benchmark_app tool from the openVINO toolkit

② 実行例「Ubuntu on Core™ i7-1185G7」+ GPU (FP32)

$ cd ~/run_app/
$ ./_super_resolution_demo_g32.sh 
[super_resolution_demo_g32.sh] 'super_resolution_demo (GPU32)' Run !!
[ INFO ] InferenceEngine: 	API version ......... 2.1
	Build ........... 2021.3.0-2787-60059f2c755-releases/2021/3
[ INFO ] Parsing input parameters
[ INFO ] Files were added: 1
[ INFO ]     /home/mizutu/Images/image-low.bmp
[ INFO ] Loading Inference Engine
[ INFO ] Device info: 
[ INFO ] 	GPU
	clDNNPlugin version ......... 2.1
	Build ........... 2021.3.0-2787-60059f2c755-releases/2021/3

[ INFO ] Loading network files
[ INFO ] Preparing input blobs
[ INFO ] Batch size is 1
[ INFO ] Preparing output blobs
[ INFO ] Loading model to the device
[ INFO ] Create infer request
To close the application, press 'CTRL+C' here or switch to the output window and press any key
[ INFO ] Start inference
[ INFO ] Output size [N,C,H,W]: 1, 3, 1080, 1920
[ INFO ] Execution successful

[ INFO ] This demo is an API example, for any performance measurements please use the dedicated benchmark_app tool from the openVINO toolkit

③ 実行例「Ubuntu on Core™ i7-1185G7」

$ cd ~/run_app/
$ ./_super_resolution_demo.sh 
[super_resolution_demo.sh] 'super_resolution_demo' Run !!
[ INFO ] InferenceEngine: 	API version ......... 2.1
	Build ........... 2021.3.0-2787-60059f2c755-releases/2021/3
[ INFO ] Parsing input parameters
[ INFO ] Files were added: 1
[ INFO ]     /home/mizutu/Images/image-low.bmp
[ INFO ] Loading Inference Engine
[ INFO ] Device info: 
[ INFO ] 	CPU
	MKLDNNPlugin version ......... 2.1
	Build ........... 2021.3.0-2787-60059f2c755-releases/2021/3

[ INFO ] Loading network files
[ INFO ] Preparing input blobs
[ INFO ] Batch size is 1
[ INFO ] Preparing output blobs
[ INFO ] Loading model to the device
[ INFO ] Create infer request
To close the application, press 'CTRL+C' here or switch to the output window and press any key
[ INFO ] Start inference
[ INFO ] Output size [N,C,H,W]: 1, 3, 1080, 1920
[ INFO ] Execution successful

[ INFO ] This demo is an API example, for any performance measurements please use the dedicated benchmark_app tool from the openVINO toolkit

④ 実行例「Ubuntu on Core™ i7-1185G7」+ NCS2

$ cd ~/run_app/
$ ./_super_resolution_demo_16.sh 
[super_resolution_demo_16.sh] 'super_resolution_demo (NCS2)' Run !!
[ INFO ] InferenceEngine: 	API version ......... 2.1
	Build ........... 2021.3.0-2787-60059f2c755-releases/2021/3
[ INFO ] Parsing input parameters
[ INFO ] Files were added: 1
[ INFO ]     /home/mizutu/Images/image-low.bmp
[ INFO ] Loading Inference Engine
[ INFO ] Device info: 
[ INFO ] 	MYRIAD
	myriadPlugin version ......... 2.1
	Build ........... 2021.3.0-2787-60059f2c755-releases/2021/3

[ INFO ] Loading network files
[ INFO ] Preparing input blobs
[ INFO ] Batch size is 1
[ INFO ] Preparing output blobs
[ INFO ] Loading model to the device
[ INFO ] Create infer request
To close the application, press 'CTRL+C' here or switch to the output window and press any key
[ INFO ] Start inference
[ INFO ] Output size [N,C,H,W]: 1, 3, 1080, 1920
[ INFO ] Execution successful

[ INFO ] This demo is an API example, for any performance measurements please use the dedicated benchmark_app tool from the openVINO toolkit

↑

Single Human Pose Estimation Demo (top-down pipeline) †

↑

デモの実行 †

① 実行例「Ubuntu on Core™ i7-1185G7」+ GPU (FP16)

$ cd ~/run_app/
$ ./_single_human_pose_estimation_demo_g16.sh 
[single_human_pose_estimation_demo_g16.sh] 'single_human_pose_estimation_demo (GPU16)' Run !!

② 実行例「Ubuntu on Core™ i7-1185G7」+ GPU (FP32)

$ cd ~/run_app_16
$ ./_single_human_pose_estimation_demo_g32.sh 
[single_human_pose_estimation_demo_g32.sh] 'single_human_pose_estimation_demo (GPU32)' Run !!

③ 実行例「Ubuntu on Core™ i7-1185G7」

$ cd ~/run_app/
$ ./_single_human_pose_estimation_demo.sh 
[single_human_pose_estimation_demo.sh] 'single_human_pose_estimation_demo' Run !!

④ 実行例「Ubuntu on Core™ i7-1185G7」+ NCS2

$ cd ~/run_app_16
$ ./_single_human_pose_estimation_demo_16.sh 
[single_human_pose_estimation_demo_16.sh] 'single_human_pose_estimation_demo (NCS2)' Run !!

↑

速度比較 †

項目	①	②	③	④	Core™i5-10210
summary (fps)	4.5	3.2	1.5	0.3	0.9
estimation (fps)	18.1	10.0	4.7	1.5	5.6
detection (fps)	140.2	118	78.3	26.3	109.9

↑

Interactive Face Detection C++ Demo †

↑

デモの実行 †

① 実行例「Ubuntu on Core™ i7-1185G7」+ GPU (FP16)

$ cd ~/run_app/
$ ./_interactive_face_detection_demo_g16.sh 
[interactive_face_detection_demo_g16.sh] 'interactive_face_detection_demo (GPU16)' Run !!
InferenceEngine: 	API version ......... 2.1
	Build ........... 2021.3.0-2787-60059f2c755-releases/2021/3
[ INFO ] Parsing input parameters
[ INFO ] Loading device GPU
[ INFO ] 	GPU
	clDNNPlugin version ......... 2.1
	Build ........... 2021.3.0-2787-60059f2c755-releases/2021/3

[ INFO ] Loading network files for Face Detection
[ INFO ] Batch size is set to 1
[ INFO ] Checking Face Detection network inputs
[ INFO ] Checking Face Detection network outputs
[ INFO ] Loading Face Detection model to the GPU device
[ INFO ] Loading network files for Age/Gender Recognition network
[ INFO ] Batch size is set to 16 for Age/Gender Recognition network
[ INFO ] Checking Age/Gender Recognition network inputs
[ INFO ] Checking Age/Gender Recognition network outputs
[ INFO ] Loading Age/Gender Recognition model to the GPU plugin
[ INFO ] Loading network files for Head Pose Estimation network
[ INFO ] Batch size is set to  16 for Head Pose Estimation network
[ INFO ] Checking Head Pose Estimation network inputs
[ INFO ] Checking Head Pose Estimation network outputs
[ INFO ] Loading Head Pose Estimation model to the GPU plugin
[ INFO ] Loading network files for Emotions Recognition
[ INFO ] Batch size is set to 16 for Emotions Recognition
[ INFO ] Checking Emotions Recognition network inputs
[ INFO ] Checking Emotions Recognition network outputs
[ INFO ] Loading Emotions Recognition model to the GPU plugin
[ INFO ] Loading network files for Facial Landmarks Estimation
[ INFO ] Batch size is set to  16 for Facial Landmarks Estimation network
[ INFO ] Checking Facial Landmarks Estimation network inputs
[ INFO ] Checking Facial Landmarks Estimation network outputs
[ INFO ] Loading Facial Landmarks Estimation model to the GPU plugin
[ INFO ] Loading network files for Antispoofing Classifier network
[ INFO ] Batch size is set to 16 for Antispoofing Classifier network
[ INFO ] Checking Antispoofing Classifier network inputs
[ INFO ] Checking Antispoofing Classifier network outputs
[ INFO ] Loading Antispoofing Classifier model to the GPU plugin
To close the application, press 'CTRL+C' here or switch to the output window and press Q or Esc
[ INFO ] Number of processed frames: 218
[ INFO ] Total image throughput: 19.2402 fps

[ INFO ] Execution successful

② 実行例「Ubuntu on Core™ i7-1185G7」+ GPU (FP32)

$ cd ~/run_app/
$ ./_interactive_face_detection_demo_g32.sh 
[interactive_face_detection_demo_g32.sh] 'interactive_face_detection_demo (GPU32)' Run !!
InferenceEngine: 	API version ......... 2.1
	Build ........... 2021.3.0-2787-60059f2c755-releases/2021/3
[ INFO ] Parsing input parameters
[ INFO ] Loading device GPU
[ INFO ] 	GPU
	clDNNPlugin version ......... 2.1
	Build ........... 2021.3.0-2787-60059f2c755-releases/2021/3

[ INFO ] Loading network files for Face Detection
[ INFO ] Batch size is set to 1
[ INFO ] Checking Face Detection network inputs
[ INFO ] Checking Face Detection network outputs
[ INFO ] Loading Face Detection model to the GPU device
[ INFO ] Loading network files for Age/Gender Recognition network
[ INFO ] Batch size is set to 16 for Age/Gender Recognition network
[ INFO ] Checking Age/Gender Recognition network inputs
[ INFO ] Checking Age/Gender Recognition network outputs
[ INFO ] Loading Age/Gender Recognition model to the GPU plugin
[ INFO ] Loading network files for Head Pose Estimation network
[ INFO ] Batch size is set to  16 for Head Pose Estimation network
[ INFO ] Checking Head Pose Estimation network inputs
[ INFO ] Checking Head Pose Estimation network outputs
[ INFO ] Loading Head Pose Estimation model to the GPU plugin
[ INFO ] Loading network files for Emotions Recognition
[ INFO ] Batch size is set to 16 for Emotions Recognition
[ INFO ] Checking Emotions Recognition network inputs
[ INFO ] Checking Emotions Recognition network outputs
[ INFO ] Loading Emotions Recognition model to the GPU plugin
[ INFO ] Loading network files for Facial Landmarks Estimation
[ INFO ] Batch size is set to  16 for Facial Landmarks Estimation network
[ INFO ] Checking Facial Landmarks Estimation network inputs
[ INFO ] Checking Facial Landmarks Estimation network outputs
[ INFO ] Loading Facial Landmarks Estimation model to the GPU plugin
[ INFO ] Loading network files for Antispoofing Classifier network
[ INFO ] Batch size is set to 16 for Antispoofing Classifier network
[ INFO ] Checking Antispoofing Classifier network inputs
[ INFO ] Checking Antispoofing Classifier network outputs
[ INFO ] Loading Antispoofing Classifier model to the GPU plugin
To close the application, press 'CTRL+C' here or switch to the output window and press Q or Esc
[ INFO ] Number of processed frames: 467
[ INFO ] Total image throughput: 16.4802 fps

[ INFO ] Execution successful

③ 実行例「Ubuntu on Core™ i7-1185G7」

$ cd ~/run_app/
$ ./_interactive_face_detection_demo.sh 
[interactive_face_detection_demo.sh] 'interactive_face_detection_demo' Run !!
InferenceEngine: 	API version ......... 2.1
	Build ........... 2021.3.0-2787-60059f2c755-releases/2021/3
[ INFO ] Parsing input parameters
[ INFO ] Loading device CPU
[ INFO ] 	CPU
	MKLDNNPlugin version ......... 2.1
	Build ........... 2021.3.0-2787-60059f2c755-releases/2021/3

[ INFO ] Loading network files for Face Detection
[ INFO ] Batch size is set to 1
[ INFO ] Checking Face Detection network inputs
[ INFO ] Checking Face Detection network outputs
[ INFO ] Loading Face Detection model to the CPU device
[ INFO ] Loading network files for Age/Gender Recognition network
[ INFO ] Batch size is set to 16 for Age/Gender Recognition network
[ INFO ] Checking Age/Gender Recognition network inputs
[ INFO ] Checking Age/Gender Recognition network outputs
[ INFO ] Loading Age/Gender Recognition model to the CPU plugin
[ INFO ] Loading network files for Head Pose Estimation network
[ INFO ] Batch size is set to  16 for Head Pose Estimation network
[ INFO ] Checking Head Pose Estimation network inputs
[ INFO ] Checking Head Pose Estimation network outputs
[ INFO ] Loading Head Pose Estimation model to the CPU plugin
[ INFO ] Loading network files for Emotions Recognition
[ INFO ] Batch size is set to 16 for Emotions Recognition
[ INFO ] Checking Emotions Recognition network inputs
[ INFO ] Checking Emotions Recognition network outputs
[ INFO ] Loading Emotions Recognition model to the CPU plugin
[ INFO ] Loading network files for Facial Landmarks Estimation
[ INFO ] Batch size is set to  16 for Facial Landmarks Estimation network
[ INFO ] Checking Facial Landmarks Estimation network inputs
[ INFO ] Checking Facial Landmarks Estimation network outputs
[ INFO ] Loading Facial Landmarks Estimation model to the CPU plugin
[ INFO ] Loading network files for Antispoofing Classifier network
[ INFO ] Batch size is set to 16 for Antispoofing Classifier network
[ INFO ] Checking Antispoofing Classifier network inputs
[ INFO ] Checking Antispoofing Classifier network outputs
[ INFO ] Loading Antispoofing Classifier model to the CPU plugin
To close the application, press 'CTRL+C' here or switch to the output window and press Q or Esc
[ INFO ] Number of processed frames: 379
[ INFO ] Total image throughput: 17.5594 fps

[ INFO ] Execution successful

④ 実行例「Ubuntu on Core™ i7-1185G7」+ NCS2

$ cd ~/run_app/
$ ./_interactive_face_detection_demo_16.sh 
[interactive_face_detection_demo_16.sh] 'interactive_face_detection_demo (NCS2)' Run !!
InferenceEngine: 	API version ......... 2.1
	Build ........... 2021.3.0-2787-60059f2c755-releases/2021/3
[ INFO ] Parsing input parameters
[ INFO ] Loading device MYRIAD
[ INFO ] 	MYRIAD
	myriadPlugin version ......... 2.1
	Build ........... 2021.3.0-2787-60059f2c755-releases/2021/3

[ INFO ] Loading network files for Face Detection
[ INFO ] Batch size is set to 1
[ INFO ] Checking Face Detection network inputs
[ INFO ] Checking Face Detection network outputs
[ INFO ] Loading Face Detection model to the MYRIAD device
[ INFO ] Loading network files for Age/Gender Recognition network
[ INFO ] Batch size is set to 16 for Age/Gender Recognition network
[ INFO ] Checking Age/Gender Recognition network inputs
[ INFO ] Checking Age/Gender Recognition network outputs
[ INFO ] Loading Age/Gender Recognition model to the MYRIAD plugin
[ INFO ] Loading network files for Head Pose Estimation network
[ INFO ] Batch size is set to  16 for Head Pose Estimation network
[ INFO ] Checking Head Pose Estimation network inputs
[ INFO ] Checking Head Pose Estimation network outputs
[ INFO ] Loading Head Pose Estimation model to the MYRIAD plugin
[ INFO ] Loading network files for Emotions Recognition
[ INFO ] Batch size is set to 16 for Emotions Recognition
[ INFO ] Checking Emotions Recognition network inputs
[ INFO ] Checking Emotions Recognition network outputs
[ INFO ] Loading Emotions Recognition model to the MYRIAD plugin
[ INFO ] Loading network files for Facial Landmarks Estimation
[ INFO ] Batch size is set to  16 for Facial Landmarks Estimation network
[ INFO ] Checking Facial Landmarks Estimation network inputs
[ INFO ] Checking Facial Landmarks Estimation network outputs
[ INFO ] Loading Facial Landmarks Estimation model to the MYRIAD plugin
[ INFO ] Loading network files for Antispoofing Classifier network
[ INFO ] Batch size is set to 16 for Antispoofing Classifier network
[ INFO ] Checking Antispoofing Classifier network inputs
[ INFO ] Checking Antispoofing Classifier network outputs
[ INFO ] Loading Antispoofing Classifier model to the MYRIAD plugin
To close the application, press 'CTRL+C' here or switch to the output window and press Q or Esc
[ INFO ] Number of processed frames: 13
[ INFO ] Total image throughput: 2.40366 fps

[ INFO ] Execution successful

↑

速度比較 †

項目	①	②	③	④	Core™i5-10210
Number of processed frames	218	467	379	13	86
Total image throughput (fps)	19.2	16.5	17.6	2.40	17.4

↑

Gaze Estimation Demo †

↑

デモの実行 †

① 実行例「Ubuntu on Core™ i7-1185G7」+ GPU (FP16)

$ cd ~/run_app/
$ ./_gaze_estimation_demo_g16.sh 
[gaze_estimation_demo_g16.sh] 'gaze_estimation_demo (GPU16)' Run !!
InferenceEngine: 	API version ......... 2.1
	Build ........... 2021.3.0-2787-60059f2c755-releases/2021/3
[ INFO ] Parsing input parameters
[ INFO ] Loading device GPU
[ INFO ] 	GPU
	clDNNPlugin version ......... 2.1
	Build ........... 2021.3.0-2787-60059f2c755-releases/2021/3

[ INFO ] Loading device GPU
[ INFO ] 	GPU
	clDNNPlugin version ......... 2.1
	Build ........... 2021.3.0-2787-60059f2c755-releases/2021/3

[ INFO ] Loading device GPU
[ INFO ] 	GPU
	clDNNPlugin version ......... 2.1
	Build ........... 2021.3.0-2787-60059f2c755-releases/2021/3

[ INFO ] Loading device GPU
[ INFO ] 	GPU
	clDNNPlugin version ......... 2.1
	Build ........... 2021.3.0-2787-60059f2c755-releases/2021/3

[ INFO ] Loading device GPU
[ INFO ] 	GPU
	clDNNPlugin version ......... 2.1
	Build ........... 2021.3.0-2787-60059f2c755-releases/2021/3


[ INFO ] Execution successful

② 実行例「Ubuntu on Core™ i7-1185G7」+ GPU (FP32)

$ cd ~/run_app/
$ ./_gaze_estimation_demo_g32.sh 
[gaze_estimation_demo_g32.sh] 'gaze_estimation_demo (GPU32)' Run !!
InferenceEngine: 	API version ......... 2.1
	Build ........... 2021.3.0-2787-60059f2c755-releases/2021/3
[ INFO ] Parsing input parameters
[ INFO ] Loading device GPU
[ INFO ] 	GPU
	clDNNPlugin version ......... 2.1
	Build ........... 2021.3.0-2787-60059f2c755-releases/2021/3

[ INFO ] Loading device GPU
[ INFO ] 	GPU
	clDNNPlugin version ......... 2.1
	Build ........... 2021.3.0-2787-60059f2c755-releases/2021/3

[ INFO ] Loading device GPU
[ INFO ] 	GPU
	clDNNPlugin version ......... 2.1
	Build ........... 2021.3.0-2787-60059f2c755-releases/2021/3

[ INFO ] Loading device GPU
[ INFO ] 	GPU
	clDNNPlugin version ......... 2.1
	Build ........... 2021.3.0-2787-60059f2c755-releases/2021/3

[ INFO ] Loading device GPU
[ INFO ] 	GPU
	clDNNPlugin version ......... 2.1
	Build ........... 2021.3.0-2787-60059f2c755-releases/2021/3


[ INFO ] Execution successful

③ 実行例「Ubuntu on Core™ i7-1185G7」

$ cd ~/run_app/
mizutu@ubuntu-lat:~/run_app$ ./_gaze_estimation_demo.sh 
[gaze_estimation_demo.sh] 'gaze_estimation_demo' Run !!
InferenceEngine: 	API version ......... 2.1
	Build ........... 2021.3.0-2787-60059f2c755-releases/2021/3
[ INFO ] Parsing input parameters
[ INFO ] Loading device CPU
[ INFO ] 	CPU
	MKLDNNPlugin version ......... 2.1
	Build ........... 2021.3.0-2787-60059f2c755-releases/2021/3


[ INFO ] Execution successful

④ 実行例「Ubuntu on Core™ i7-1185G7」+ NCS2

$ cd ~/run_app/
$ ./_gaze_estimation_demo_16.sh 
[gaze_estimation_demo_16.sh] 'gaze_estimation_demo (NCS2)' Run !!
InferenceEngine: 	API version ......... 2.1
	Build ........... 2021.3.0-2787-60059f2c755-releases/2021/3
[ INFO ] Parsing input parameters
[ INFO ] Loading device MYRIAD
[ INFO ] 	MYRIAD
	myriadPlugin version ......... 2.1
	Build ........... 2021.3.0-2787-60059f2c755-releases/2021/3

[ INFO ] Loading device MYRIAD
[ INFO ] 	MYRIAD
	myriadPlugin version ......... 2.1
	Build ........... 2021.3.0-2787-60059f2c755-releases/2021/3

[ INFO ] Loading device MYRIAD
[ INFO ] 	MYRIAD
	myriadPlugin version ......... 2.1
	Build ........... 2021.3.0-2787-60059f2c755-releases/2021/3

[ INFO ] Loading device MYRIAD
[ INFO ] 	MYRIAD
	myriadPlugin version ......... 2.1
	Build ........... 2021.3.0-2787-60059f2c755-releases/2021/3

[ INFO ] Loading device MYRIAD
[ INFO ] 	MYRIAD
	myriadPlugin version ......... 2.1
	Build ........... 2021.3.0-2787-60059f2c755-releases/2021/3


[ INFO ] Execution successful

↑

速度比較 †

項目	①	②	③	④	Core™i5-10210
Overeli (fps)	40	32	62	28	110
Interface (fps)	46	41	75	32	202

↑

Security Barrier Camera C++ Demo †

↑

デモの実行 †

① 実行例「Ubuntu on Core™ i7-1185G7」+ GPU (FP16)

$ cd ~/run_app/
$ ./_security_barrier_camera_demo_g16.sh 
[security_barrier_camera_demo_g16.sh] 'security_barrier_camera_demo (GPU16)' Run !!
[ INFO ] InferenceEngine: 	API version ......... 2.1
	Build ........... 2021.3.0-2787-60059f2c755-releases/2021/3
[ INFO ] Files were added: 1
[ INFO ]     /home/mizutu/Videos/car-detection.mp4
[ INFO ] Loading device GPU
[ INFO ] 	GPU
	clDNNPlugin version ......... 2.1
	Build ........... 2021.3.0-2787-60059f2c755-releases/2021/3

[ INFO ] Loading detection model to the GPU plugin
[ INFO ] Loading Vehicle Attribs model to the GPU plugin
[ INFO ] Loading Licence Plate Recognition (LPR) model to the GPU plugin
[ INFO ] Number of InferRequests: 1 (detection), 3 (classification), 3 (recognition)
[ INFO ] 2 streams for GPU
[ INFO ] Display resolution: 1920x1080
[ INFO ] Number of allocated frames: 3
[ INFO ] Resizable input with support of ROI crop and auto resize is disabled
157.7FPS for (375 / 1) frames
Detection InferRequests usage: 100.0%

[ INFO ] Execution successful

② 実行例「Ubuntu on Core™ i7-1185G7」+ GPU (FP32)

$ cd ~/run_app/
$ ./_security_barrier_camera_demo_g32.sh 
[security_barrier_camera_demo_g32.sh] 'security_barrier_camera_demo (GPU32)' Run !!
[ INFO ] InferenceEngine: 	API version ......... 2.1
	Build ........... 2021.3.0-2787-60059f2c755-releases/2021/3
[ INFO ] Files were added: 1
[ INFO ]     /home/mizutu/Videos/car-detection.mp4
[ INFO ] Loading device GPU
[ INFO ] 	GPU
	clDNNPlugin version ......... 2.1
	Build ........... 2021.3.0-2787-60059f2c755-releases/2021/3

[ INFO ] Loading detection model to the GPU plugin
[ INFO ] Loading Vehicle Attribs model to the GPU plugin
[ INFO ] Loading Licence Plate Recognition (LPR) model to the GPU plugin
[ INFO ] Number of InferRequests: 1 (detection), 3 (classification), 3 (recognition)
[ INFO ] 2 streams for GPU
[ INFO ] Display resolution: 1920x1080
[ INFO ] Number of allocated frames: 3
[ INFO ] Resizable input with support of ROI crop and auto resize is disabled
161.4FPS for (375 / 1) frames
Detection InferRequests usage: 100.0%

[ INFO ] Execution successful

③ 実行例「Ubuntu on Core™ i7-1185G7」

$ cd ~/run_app/
$ ./_security_barrier_camera_demo.sh 
[security_barrier_camera_demo.sh] 'security_barrier_camera_demo' Run !!
[ INFO ] InferenceEngine: 	API version ......... 2.1
	Build ........... 2021.3.0-2787-60059f2c755-releases/2021/3
[ INFO ] Files were added: 1
[ INFO ]     /home/mizutu/Videos/car-detection.mp4
[ INFO ] Loading device CPU
[ INFO ] 	CPU
	MKLDNNPlugin version ......... 2.1
	Build ........... 2021.3.0-2787-60059f2c755-releases/2021/3

[ INFO ] Loading detection model to the CPU plugin
[ INFO ] Loading Vehicle Attribs model to the CPU plugin
[ INFO ] Loading Licence Plate Recognition (LPR) model to the CPU plugin
[ INFO ] Number of InferRequests: 1 (detection), 3 (classification), 3 (recognition)
[ INFO ] 4 streams for CPU
[ INFO ] Display resolution: 1920x1080
[ INFO ] Number of allocated frames: 3
[ INFO ] Resizable input with support of ROI crop and auto resize is disabled
128.9FPS for (375 / 1) frames
Detection InferRequests usage: 100.0%

[ INFO ] Execution successful

④ 実行例「Ubuntu on Core™ i7-1185G7」+ NCS2

$ cd ~/run_app/
$ ./_security_barrier_camera_demo_16.sh 
[security_barrier_camera_demo_16.sh] 'security_barrier_camera_demo (NCS2)' Run !!
[ INFO ] InferenceEngine: 	API version ......... 2.1
	Build ........... 2021.3.0-2787-60059f2c755-releases/2021/3
[ INFO ] Files were added: 1
[ INFO ]     /home/mizutu/Videos/car-detection.mp4
[ INFO ] Loading device MYRIAD
[ INFO ] 	MYRIAD
	myriadPlugin version ......... 2.1
	Build ........... 2021.3.0-2787-60059f2c755-releases/2021/3

[ INFO ] Loading detection model to the MYRIAD plugin
[ INFO ] Loading Vehicle Attribs model to the MYRIAD plugin
[ INFO ] Loading Licence Plate Recognition (LPR) model to the MYRIAD plugin
[ INFO ] Number of InferRequests: 1 (detection), 3 (classification), 3 (recognition)
[ INFO ] Display resolution: 1920x1080
[ INFO ] Number of allocated frames: 3
[ INFO ] Resizable input with support of ROI crop and auto resize is disabled
35.3FPS for (375 / 1) frames
Detection InferRequests usage: 100.0%

[ INFO ] Execution successful

↑

速度比較 †

項目	①	②	③	④	Core™i5-10210
fps	157.7	161.4	128.9	35.3	164.5

↑

テスト環境 †

↑

ハードウェア環境 †

DELL Latitude 7520
- CPU Intel® Core™ i7-1185G7 CPU
- Processor Graphics Intel® Iris® Xe Graphics

IntelR NUC キット BXNUC10I5FNH
- CPU Intel® Core™ i5-10210U CPU

↑

ソフトウェア環境 †

OS Ubuntu20.04LTS
OpenVINO™ Toolkit for Linux 2021.3

↑

更新履歴 †

2021/05/14 初版

↑

参考資料 †

オフィシャルサイト

最新の20件

Open Model Zoo Demos を動かす４ †

デモの実行 †

速度比較 †

デモの実行 †

速度比較 †

デモの実行 †

速度比較 †

デモの実行 †

速度比較 †

デモの実行 †

速度比較 †

デモの実行 †

速度比較 †

デモの実行 †

速度比較 †

デモの実行] †

速度比較 †

デモの実行 †

速度比較 †

デモの実行 †

速度比較 †

デモの実行 †

速度比較 †

デモの実行 †

デモの実行 †

デモの実行 †

速度比較 †

デモの実行 †

速度比較 †

デモの実行 †

速度比較 †

デモの実行 †

速度比較 †

テスト環境 †

ハードウェア環境 †

ソフトウェア環境 †

更新履歴 †

参考資料 †