私的AI研究会 > OpenVINOtest2
以下の操作はNeural Compute Application 実行スクリプト２ を使用する。
$ cd ~/run_app2
$ ./_hello_query_device.sh
[hello_query_device.sh] 'hello_query_device' Run !!
Available devices:
:
Device: CPU
:
Device: MYRIAD.3.4.1-ma2480
:
Device: MYRIAD.3.4.3-ma2480
:
Device: MYRIAD.3.4.4-ma2480
:
| NCS2 並列数 | CPU |
| ① NCS2 1本 | Core™ i7-1185G7 |
| ② NCS2 2本 | Core™ i7-1185G7 |
| ③ NCS2 3本 | Core™ i7-1185G7 |
$ cd ~/run_app2
$ source set_MYRIAD16.sh
$ ./_benchmark_app.sh
[benchmark_app.sh] 'benchmark_app' Run !!
DEVICE: MYRIAD
COMMAND: ./benchmark_app -d MYRIAD -m /home/mizutu/model/public/FP16/squeezenet1.1.xml -pc -niter 1000
:
Full device name: Intel Movidius Myriad X VPU
Count: 1000 iterations
Duration: 3498.72 ms
Latency: 13.97 ms
Throughput: 285.82 FPS
・② NCS2 2本$ cd ~/run_app2
$ source set_MYRIAD16_2X.sh
$ ./_benchmark_app.sh
[benchmark_app.sh] 'benchmark_app' Run !!
DEVICE: MULTI:MYRIAD.3.4.1-ma2480,MYRIAD.3.4.3-ma2480
COMMAND: ./benchmark_app -d MULTI:MYRIAD.3.4.1-ma2480,MYRIAD.3.4.3-ma2480 -m /home/mizutu/model/public/FP16/squeezenet1.1.xml -pc -niter 1000
:
Full device name:
Count: 1000 iterations
Duration: 1753.36 ms
Throughput: 570.33 FPS
・③ NCS2 3本$ cd ~/run_app2
$ source set_MYRIAD16_3X.sh
$ ./_benchmark_app.sh
[benchmark_app.sh] 'benchmark_app' Run !!
DEVICE: MULTI:MYRIAD.3.4.1-ma2480,MYRIAD.3.4.3-ma2480,MYRIAD.3.4.4-ma2480
COMMAND: ./benchmark_app -d MULTI:MYRIAD.3.4.1-ma2480,MYRIAD.3.4.3-ma2480,MYRIAD.3.4.4-ma2480 -m /home/mizutu/model/public/FP16/squeezenet1.1.xml -pc -niter 1000
:
Full device name:
Count: 1008 iterations
Duration: 1181.41 ms
Throughput: 853.22 FPS| 項目 | ①1本 | ②2本 | ③3本 |
| Duration (ms) | 3438 | 1753 | 1181 |
| Throughput (fps) | 285.8 | 570.3 | 853.2 |
$ cd ~/run_app2/
$ source set_MIRYAD16xxx. sh xxx → なし (1本), _2X (2本), _3X (3本)
$ cd ~/run_app2 $ source set_MYRIAD16.sh $ ./_human_pose_estimation_3d_demo.sh [human_pose_estimation_3d_demo.sh] 'human_pose_estimation_3d_demo' Run !! MODEL: FP16 DEVICE: MYRIAD COMMAND: python3 human_pose_estimation_3d_demo.py -m /home/mizutu/model/public/FP16/human-pose-estimation-3d-0001.xml -i /home/mizutu/Videos/driver.mp4 -d MYRIAD・② NCS2 2本
$ cd ~/run_app2 $ source set_MYRIAD16_2X.sh $ ./_human_pose_estimation_3d_demo.sh [human_pose_estimation_3d_demo.sh] 'human_pose_estimation_3d_demo' Run !! MODEL: FP16 DEVICE: MULTI:MYRIAD.3.4.1-ma2480,MYRIAD.3.4.3-ma2480 COMMAND: python3 human_pose_estimation_3d_demo.py -m /home/mizutu/model/public/FP16/human-pose-estimation-3d-0001.xml -i /home/mizutu/Videos/driver.mp4 -d MULTI:MYRIAD.3.4.1-ma2480,MYRIAD.3.4.3-ma2480・③ NCS2 3本
$ cd ~/run_app2 $ source set_MYRIAD16_3X.sh $ ./_human_pose_estimation_3d_demo.sh [human_pose_estimation_3d_demo.sh] 'human_pose_estimation_3d_demo' Run !! MODEL: FP16 DEVICE: MULTI:MYRIAD.3.4.1-ma2480,MYRIAD.3.4.3-ma2480,MYRIAD.3.4.4-ma2480 COMMAND: python3 human_pose_estimation_3d_demo.py -m /home/mizutu/model/public/FP16/human-pose-estimation-3d-0001.xml -i /home/mizutu/Videos/driver.mp4 -d MULTI:MYRIAD.3.4.1-ma2480,MYRIAD.3.4.3-ma2480,MYRIAD.3.4.4-ma2480
| 項目 | ①1本 | ②2本 | ③3本 |
| fps | 4.1 | 4.1 | 4.1 |
$ cd ~/run_app2
$ source set_MYRIAD16.sh
$ ./_action_recognition.sh
[action_recognition_demo.sh] 'action_recognition_demo' Run !!
MODEL: FP16
DEVICE: MYRIAD
COMMAND: python3 action_recognition_demo.py -m_en /home/mizutu/model/intel/FP16/driver-action-recognition-adas-0002-encoder.xml -at en-de -m_de /home/mizutu/model/intel/FP16/driver-action-recognition-adas-0002-decoder.xml -i /home/mizutu/Videos/driver.mp4 -lb driver_actions.txt -d MYRIAD
:
Frame 81: Safe driving - 84.15% -- 7.85ms
Frame 82: Safe driving - 84.23% -- 8.46ms
finishing <action_recognition_demo.steps.RenderStep object at 0x7fe00dc84d30>
Data total: 2.42ms (+/-: 1.61) 412.47fps
Data own: 2.41ms (+/-: 1.61) 415.57fps
Encoder total: 6.71ms (+/-: 4.12) 148.93fps
Encoder own: 6.70ms (+/-: 4.12) 149.36fps
Decoder total: 1.60ms (+/-: 2.96) 625.01fps
Decoder own: 1.58ms (+/-: 2.96) 631.00fps
Render total: 32.59ms (+/-: 22.16) 30.68fps
Render own: 32.11ms (+/-: 20.00) 31.15fps
・② NCS2 2本$ cd ~/run_app2
$ source set_MYRIAD16_2X.sh
$ ./_action_recognition.sh
[action_recognition_demo.sh] 'action_recognition_demo' Run !!
MODEL: FP16
DEVICE: MULTI:MYRIAD.3.4.1-ma2480,MYRIAD.3.4.3-ma2480
COMMAND: python3 action_recognition_demo.py -m_en /home/mizutu/model/intel/FP16/driver-action-recognition-adas-0002-encoder.xml -at en-de -m_de /home/mizutu/model/intel/FP16/driver-action-recognition-adas-0002-decoder.xml -i /home/mizutu/Videos/driver.mp4 -lb driver_actions.txt -d MULTI:MYRIAD.3.4.1-ma2480,MYRIAD.3.4.3-ma2480
:
Frame 54: Safe driving - 63.34% -- 27.53ms
Frame 55: Safe driving - 64.52% -- 27.55ms
finishing <action_recognition_demo.steps.RenderStep object at 0x7f17eb91eb20>
Data total: 2.78ms (+/-: 1.96) 359.29fps
Data own: 2.76ms (+/-: 1.96) 361.85fps
Encoder total: 26.54ms (+/-: 1.14) 37.68fps
Encoder own: 26.52ms (+/-: 1.14) 37.71fps
Decoder total: 1.05ms (+/-: 4.94) 954.88fps
Decoder own: 1.03ms (+/-: 4.94) 968.41fps
Render total: 49.96ms (+/-: 33.19) 20.02fps
Render own: 49.54ms (+/-: 29.75) 20.19fps
・③ NCS2 3本$ cd ~/run_app2
$ source set_MYRIAD16_3X.sh
$ ./_action_recognition.sh
[action_recognition_demo.sh] 'action_recognition_demo' Run !!
MODEL: FP16
DEVICE: MULTI:MYRIAD.3.4.1-ma2480,MYRIAD.3.4.3-ma2480,MYRIAD.3.4.4-ma2480
COMMAND: python3 action_recognition_demo.py -m_en /home/mizutu/model/intel/FP16/driver-action-recognition-adas-0002-encoder.xml -at en-de -m_de /home/mizutu/model/intel/FP16/driver-action-recognition-adas-0002-decoder.xml -i /home/mizutu/Videos/driver.mp4 -lb driver_actions.txt -d MULTI:MYRIAD.3.4.1-ma2480,MYRIAD.3.4.3-ma2480,MYRIAD.3.4.4-ma2480
:
Frame 53: Safe driving - 63.68% -- 28.39ms
Frame 54: Safe driving - 63.34% -- 28.11ms
finishing <action_recognition_demo.steps.RenderStep object at 0x7efe3fdb4b20>
Data total: 2.54ms (+/-: 1.50) 393.59fps
Data own: 2.52ms (+/-: 1.50) 396.49fps
Encoder total: 26.75ms (+/-: 1.27) 37.39fps
Encoder own: 26.72ms (+/-: 1.27) 37.42fps
Decoder total: 0.88ms (+/-: 3.32) 1136.27fps
Decoder own: 0.87ms (+/-: 3.32) 1155.67fps
Render total: 54.44ms (+/-: 35.01) 18.37fps
Render own: 53.88ms (+/-: 31.15) 18.56fps| 項目 | ①1本 | ②2本 | ③3本 | |
| Data totai | fps | 412 | 359 | 393 |
| ms | 2.42 | 2.78 | 2.54 | |
| Encoder total | fps | 149 | 37.7 | 38.0 |
| ms | 6.71 | 26.5 | 26.7 | |
| Decoder total | fps | 625 | 955 | 1136 |
| ms | 1.60 | 1.05 | 0.88 | |
| Render total | fps | 30.7 | 20.0 | 18.4 |
| ms | 32.6 | 50.0 | 54.4 | |
$ cd ~/run_app2
$ source set_MYRIAD16.sh
$ ./_object_detection_python_demo.sh
[object_detection_demo.sh] 'object_detection_demo' Run !!
MODEL: FP16
DEVICE: MYRIAD
COMMAND: python3 object_detection_demo.py -m /home/mizutu/model/intel/FP16/person-vehicle-bike-detection-crossroad-yolov3-1020.xml -i /home/mizutu/Videos/car_person.mp4 -at yolo -d MYRIAD
:
[ INFO ] Starting inference...
To close the application, press 'CTRL+C' here or switch to the output window and press ESC key
Latency: 470.2 ms
FPS: 2.1
・② NCS2 2本$ cd ~/run_app2
$ source set_MYRIAD16_2X.sh
$ ./_object_detection_python_demo.sh
[object_detection_demo.sh] 'object_detection_demo' Run !!
MODEL: FP16
DEVICE: MULTI:MYRIAD.3.4.1-ma2480,MYRIAD.3.4.3-ma2480
COMMAND: python3 object_detection_demo.py -m /home/mizutu/model/intel/FP16/person-vehicle-bike-detection-crossroad-yolov3-1020.xml -i /home/mizutu/Videos/car_person.mp4 -at yolo -d MULTI:MYRIAD.3.4.1-ma2480,MYRIAD.3.4.3-ma2480
:
[ INFO ] Starting inference...
To close the application, press 'CTRL+C' here or switch to the output window and press ESC key
Latency: 466.1 ms
FPS: 2.1
・③ NCS2 3本$ cd ~/run_app2
$ source set_MYRIAD16_3X.sh
$ ./_object_detection_python_demo.sh
[object_detection_demo.sh] 'object_detection_demo' Run !!
MODEL: FP16
DEVICE: MULTI:MYRIAD.3.4.1-ma2480,MYRIAD.3.4.3-ma2480,MYRIAD.3.4.4-ma2480
COMMAND: python3 object_detection_demo.py -m /home/mizutu/model/intel/FP16/person-vehicle-bike-detection-crossroad-yolov3-1020.xml -i /home/mizutu/Videos/car_person.mp4 -at yolo -d MULTI:MYRIAD.3.4.1-ma2480,MYRIAD.3.4.3-ma2480,MYRIAD.3.4.4-ma2480
:
[ INFO ] Starting inference...
To close the application, press 'CTRL+C' here or switch to the output window and press ESC key
Latency: 470.4 ms
FPS: 2.1| 項目 | ①1本 | ②2本 | ③3本 |
| Latency (ms) | 470.2 | 466.1 | 470.4 |
| fps | 2.1 | 2.1 | 2.1 |
$ cd ~/run_app2
$ source set_MYRIAD16.sh
$ ./_human_pose_estimation.sh
[human_pose_estimation_demo.sh] 'human_pose_estimation_demo' Run !!
MODEL: FP16
DEVICE: MYRIAD
COMMAND: python3 human_pose_estimation_demo.py -i /home/mizutu/Videos/driver.mp4 -m /home/mizutu/model/intel/FP16/human-pose-estimation-0001.xml -at openpose -d MYRIAD
:
[ INFO ] Starting inference...
To close the application, press 'CTRL+C' here or switch to the output window and press ESC key
Latency: 213.2 ms
FPS: 4.6
・② NCS2 2本$ cd ~/run_app2
$ source set_MYRIAD16_2X.sh
$ ./_human_pose_estimation.sh
[human_pose_estimation_demo.sh] 'human_pose_estimation_demo' Run !!
MODEL: FP16
DEVICE: MULTI:MYRIAD.3.4.1-ma2480,MYRIAD.3.4.3-ma2480
COMMAND: python3 human_pose_estimation_demo.py -i /home/mizutu/Videos/driver.mp4 -m /home/mizutu/model/intel/FP16/human-pose-estimation-0001.xml -at openpose -d MULTI:MYRIAD.3.4.1-ma2480,MYRIAD.3.4.3-ma2480
:
[ INFO ] Starting inference...
To close the application, press 'CTRL+C' here or switch to the output window and press ESC key
Latency: 211.7 ms
FPS: 4.5
・③ NCS2 3本$ cd ~/run_app2
$ source set_MYRIAD16_3X.sh
$ ./_human_pose_estimation.sh
[human_pose_estimation_demo.sh] 'human_pose_estimation_demo' Run !!
MODEL: FP16
DEVICE: MULTI:MYRIAD.3.4.1-ma2480,MYRIAD.3.4.3-ma2480,MYRIAD.3.4.4-ma2480
COMMAND: python3 human_pose_estimation_demo.py -i /home/mizutu/Videos/driver.mp4 -m /home/mizutu/model/intel/FP16/human-pose-estimation-0001.xml -at openpose -d MULTI:MYRIAD.3.4.1-ma2480,MYRIAD.3.4.3-ma2480,MYRIAD.3.4.4-ma2480
:
[ INFO ] Starting inference...
To close the application, press 'CTRL+C' here or switch to the output window and press ESC key
Latency: 212.8 ms
FPS: 4.5| 項目 | ①1本 | ②2本 | ③3本 |
| Latency (ms) | 213.2 | 211.7 | 212.8 |
| fps | 4.6 | 4.5 | 4.5 |
$ cd ~/run_app2
$ source set_MYRIAD16.sh
$ ./_gesture_recognition_demo.sh
[gesture_recognition_demo.sh] 'gesture_recognition_demo' Run !!
MODEL: FP16
DEVICE: MYRIAD
COMMAND: python3 gesture_recognition_demo.py -m_a /home/mizutu/model/intel/FP16/asl-recognition-0004.xml -m_d /home/mizutu/model/intel/FP16/person-detection-asl-0001.xml -i /home/mizutu/Videos/ASK_Please.mp4 -c /opt/intel/openvino_2021/deployment_tools/open_model_zoo/data/dataset_classes/msasl100.json -d MYRIAD
:
File "/opt/intel/openvino_2021.3.394/deployment_tools/open_model_zoo/demos/gesture_recognition_demo/python/gesture_recognition_demo/common.py", line 40, in __init__
self.exec_net = ie_core.load_network(network=self.net,
File "ie_api.pyx", line 336, in openvino.inference_engine.ie_api.IECore.load_network
File "ie_api.pyx", line 345, in openvino.inference_engine.ie_api.IECore.load_network
RuntimeError: get_element_type() must be called on a node with exactly one output.
・② NCS2 2本$ cd ~/run_app2
$ source set_MYRIAD16_2X.sh
$ ./_gesture_recognition_demo.sh
[gesture_recognition_demo.sh] 'gesture_recognition_demo' Run !!
MODEL: FP16
DEVICE: MULTI:MYRIAD.3.4.1-ma2480,MYRIAD.3.4.3-ma2480
COMMAND: python3 gesture_recognition_demo.py -m_a /home/mizutu/model/intel/FP16/asl-recognition-0004.xml -m_d /home/mizutu/model/intel/FP16/person-detection-asl-0001.xml -i /home/mizutu/Videos/ASK_Please.mp4 -c /opt/intel/openvino_2021/deployment_tools/open_model_zoo/data/dataset_classes/msasl100.json -d MULTI:MYRIAD.3.4.1-ma2480,MYRIAD.3.4.3-ma2480
:
File "/opt/intel/openvino_2021.3.394/deployment_tools/open_model_zoo/demos/gesture_recognition_demo/python/gesture_recognition_demo/common.py", line 40, in __init__
self.exec_net = ie_core.load_network(network=self.net,
File "ie_api.pyx", line 336, in openvino.inference_engine.ie_api.IECore.load_network
File "ie_api.pyx", line 345, in openvino.inference_engine.ie_api.IECore.load_network
RuntimeError: get_element_type() must be called on a node with exactly one output.
・③ NCS2 3本$ cd ~/run_app2
$ source set_MYRIAD16_3X.sh
$ ./_gesture_recognition_demo.sh
[gesture_recognition_demo.sh] 'gesture_recognition_demo' Run !!
MODEL: FP16
DEVICE: MULTI:MYRIAD.3.4.1-ma2480,MYRIAD.3.4.3-ma2480,MYRIAD.3.4.4-ma2480
COMMAND: python3 gesture_recognition_demo.py -m_a /home/mizutu/model/intel/FP16/asl-recognition-0004.xml -m_d /home/mizutu/model/intel/FP16/person-detection-asl-0001.xml -i /home/mizutu/Videos/ASK_Please.mp4 -c /opt/intel/openvino_2021/deployment_tools/open_model_zoo/data/dataset_classes/msasl100.json -d MULTI:MYRIAD.3.4.1-ma2480,MYRIAD.3.4.3-ma2480,MYRIAD.3.4.4-ma2480
:
File "/opt/intel/openvino_2021.3.394/deployment_tools/open_model_zoo/demos/gesture_recognition_demo/python/gesture_recognition_demo/common.py", line 40, in __init__
self.exec_net = ie_core.load_network(network=self.net,
File "ie_api.pyx", line 336, in openvino.inference_engine.ie_api.IECore.load_network
File "ie_api.pyx", line 345, in openvino.inference_engine.ie_api.IECore.load_network
RuntimeError: get_element_type() must be called on a node with exactly one output.
$ cd ~/run_app2
$ source set_MYRIAD16.sh
$ ./_handwritten_text_recognition_demo.sh
[handwritten_text_recognition_demo.sh] 'handwritten_text_recognition_demo' Run !!
MODEL: FP16
DEVICE: MYRIAD
COMMAND: python3 handwritten_text_recognition_demo.py -i ./data/handwritten_japanese_test.png -m /home/mizutu/model/intel/FP16/handwritten-japanese-recognition-0001.xml -d MYRIAD
:
[ INFO ] Starting inference (1 iterations)
['菊池朋子']
[ INFO ] Average throughput: 917.2377586364746 ms
・② NCS2 2本$ cd ~/run_app2
$ source set_MYRIAD16_2X.sh
$ ./_handwritten_text_recognition_demo.sh
[handwritten_text_recognition_demo.sh] 'handwritten_text_recognition_demo' Run !!
MODEL: FP16
DEVICE: MULTI:MYRIAD.3.4.1-ma2480,MYRIAD.3.4.3-ma2480
COMMAND: python3 handwritten_text_recognition_demo.py -i ./data/handwritten_japanese_test.png -m /home/mizutu/model/intel/FP16/handwritten-japanese-recognition-0001.xml -d MULTI:MYRIAD.3.4.1-ma2480,MYRIAD.3.4.3-ma2480
:
[ INFO ] Starting inference (1 iterations)
['菊池朋子']
[ INFO ] Average throughput: 924.9143600463867 ms
・③ NCS2 3本$ cd ~/run_app2
$ source set_MYRIAD16_3X.sh
$ ./_handwritten_text_recognition_demo.sh
[handwritten_text_recognition_demo.sh] 'handwritten_text_recognition_demo' Run !!
MODEL: FP16
DEVICE: MULTI:MYRIAD.3.4.1-ma2480,MYRIAD.3.4.3-ma2480,MYRIAD.3.4.4-ma2480
COMMAND: python3 handwritten_text_recognition_demo.py -i ./data/handwritten_japanese_test.png -m /home/mizutu/model/intel/FP16/handwritten-japanese-recognition-0001.xml -d MULTI:MYRIAD.3.4.1-ma2480,MYRIAD.3.4.3-ma2480,MYRIAD.3.4.4-ma2480
:
[ INFO ] Starting inference (1 iterations)
['菊池朋子']
[ INFO ] Average throughput: 922.9774475097656 ms| 項目 | ①1本 | ②2本 | ③3本 |
| Average throughput(ms) | 917.2 | 924.9 | 923.0 |
$ cd ~/run_app2
$ source set_MYRIAD16.sh
$ ./_text_detection_demo.sh
[text_detection_demo.sh] 'text_detection_demo' Run !!
MODEL: FP16
DEVICE: MYRIAD
COMMAND: ./text_detection_demo -loop -m_td /home/mizutu/model/intel/FP16/text-detection-0004.xml -m_tr /home/mizutu/model/intel/FP16/text-recognition-0012.xml -i /home/mizutu/Images/text-img.jpg -d_td MYRIAD -d_tr MYRIAD
:
[ 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): 650 1.53846
text detection postprocessing (ms) (fps): 85.3333 11.7188
text recognition model inference (ms) (fps): 76.7926 13.0221
text recognition postprocessing (ms) (fps): 0.0170148 58772.3
text crop (ms) (fps): 0.133244 7505
・② NCS2 2本$ cd ~/run_app2
$ source set_MYRIAD16_2X.sh
$ ./_text_detection_demo.sh
[text_detection_demo.sh] 'text_detection_demo' Run !!
MODEL: FP16
DEVICE: MULTI:MYRIAD.3.4.1-ma2480,MYRIAD.3.4.3-ma2480
COMMAND: ./text_detection_demo -loop -m_td /home/mizutu/model/intel/FP16/text-detection-0004.xml -m_tr /home/mizutu/model/intel/FP16/text-recognition-0012.xml -i /home/mizutu/Images/text-img.jpg -d_td MULTI:MYRIAD.3.4.1-ma2480,MYRIAD.3.4.3-ma2480 -d_tr MULTI:MYRIAD.3.4.1-ma2480,MYRIAD.3.4.3-ma2480
:
[ 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): 650.75 1.53669
text detection postprocessing (ms) (fps): 85.125 11.7474
text recognition model inference (ms) (fps): 77.1167 12.9674
text recognition postprocessing (ms) (fps): 0.016525 60514.4
text crop (ms) (fps): 0.117425 8516.07
・③ NCS2 3本$ cd ~/run_app2
$ source set_MYRIAD16_3X.sh
$ ./_text_detection_demo.sh
[text_detection_demo.sh] 'text_detection_demo' Run !!
MODEL: FP16
DEVICE: MULTI:MYRIAD.3.4.1-ma2480,MYRIAD.3.4.3-ma2480,MYRIAD.3.4.4-ma2480
COMMAND: ./text_detection_demo -loop -m_td /home/mizutu/model/intel/FP16/text-detection-0004.xml -m_tr /home/mizutu/model/intel/FP16/text-recognition-0012.xml -i /home/mizutu/Images/text-img.jpg -d_td MULTI:MYRIAD.3.4.1-ma2480,MYRIAD.3.4.3-ma2480,MYRIAD.3.4.4-ma2480 -d_tr MULTI:MYRIAD.3.4.1-ma2480,MYRIAD.3.4.3-ma2480,MYRIAD.3.4.4-ma2480
:
[ 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): 651.778 1.53427
text detection postprocessing (ms) (fps): 91 10.989
text recognition model inference (ms) (fps): 77.3481 12.9286
text recognition postprocessing (ms) (fps): 0.0163704 61086
text crop (ms) (fps): 0.119 8403.36| 項目 | ①1本 | ②2本 | ③3本 | |
| detection model inference | ms | 650 | 651 | 652 |
| fps | 1.54 | 1.54 | 1.53 | |
| detection model postprocessing | ms | 85.3 | 85.1 | 91 |
| fps | 11.7 | 11.7 | 11.0 | |
| recognition model inference | ms | 76.8 | 77.1 | 77.3 |
| fps | 13.0 | 13.0 | 12.9 | |
| recognition model postprocessing | ms | 0.017 | 0.017 | 0.016 |
| fps | 58772 | 60514 | 61086 | |
$ cd ~/run_app2
$ source set_MYRIAD16.sh
$ ./_crossroad_camera_demo.sh
[crossroad_camera_demo.sh] 'crossroad_camera_demo' Run !!
MODEL: FP16
DEVICE: MYRIAD
COMMAND: ./crossroad_camera_demo -loop -i /home/mizutu/Videos/car.mp4 -m /home/mizutu/model/intel/FP16/person-vehicle-bike-detection-crossroad-0078.xml -d MYRIAD
:
To close the application, press 'CTRL+C' here or switch to the output window and press ESC key
[ INFO ] Total Inference time: 9719.26
[ INFO ] Execution successful
・② NCS2 2本$ cd ~/run_app2
$ source set_MYRIAD16_2X.sh
$ ./_crossroad_camera_demo.sh
[crossroad_camera_demo.sh] 'crossroad_camera_demo' Run !!
MODEL: FP16
DEVICE: MULTI:MYRIAD.3.4.1-ma2480,MYRIAD.3.4.3-ma2480
COMMAND: ./crossroad_camera_demo -loop -i /home/mizutu/Videos/car.mp4 -m /home/mizutu/model/intel/FP16/person-vehicle-bike-detection-crossroad-0078.xml -d MULTI:MYRIAD.3.4.1-ma2480,MYRIAD.3.4.3-ma2480
:
To close the application, press 'CTRL+C' here or switch to the output window and press ESC key
[ INFO ] Total Inference time: 10031.7
[ INFO ] Execution successful
・③ NCS2 3本$ cd ~/run_app2
$ source set_MYRIAD16_3X.sh
$ ./_crossroad_camera_demo.sh
[crossroad_camera_demo.sh] 'crossroad_camera_demo' Run !!
MODEL: FP16
DEVICE: MULTI:MYRIAD.3.4.1-ma2480,MYRIAD.3.4.3-ma2480,MYRIAD.3.4.4-ma2480
COMMAND: ./crossroad_camera_demo -loop -i /home/mizutu/Videos/car.mp4 -m /home/mizutu/model/intel/FP16/person-vehicle-bike-detection-crossroad-0078.xml -d MULTI:MYRIAD.3.4.1-ma2480,MYRIAD.3.4.3-ma2480,MYRIAD.3.4.4-ma2480
:
To close the application, press 'CTRL+C' here or switch to the output window and press ESC key
[ INFO ] Total Inference time: 28182.4
[ INFO ] Execution successful| 項目 | ①1本 | ②2本 | ③3本 |
| detection time (ms) | 270.8 | 270.8 | 270.6 |
| fps | 3.70 | 3.69 | 3,6 |
$ cd ~/run_app2
$ source set_MYRIAD16.sh
$ ./_human_pose_estimation.sh
[human_pose_estimation_demo.sh] 'human_pose_estimation_demo' Run !!
MODEL: FP16
DEVICE: MYRIAD
COMMAND: python3 human_pose_estimation_demo.py -i /home/mizutu/Videos/driver.mp4 -m /home/mizutu/model/intel/FP16/human-pose-estimation-0001.xml -at openpose -d MYRIAD
:
[ INFO ] Starting inference...
To close the application, press 'CTRL+C' here or switch to the output window and press ESC key
Latency: 212.3 ms
FPS: 4.6
・② NCS2 2本$ cd ~/run_app2
$ source set_MYRIAD16_2X.sh
$ ./_human_pose_estimation.sh
[human_pose_estimation_demo.sh] 'human_pose_estimation_demo' Run !!
MODEL: FP16
DEVICE: MULTI:MYRIAD.3.4.1-ma2480,MYRIAD.3.4.3-ma2480
COMMAND: python3 human_pose_estimation_demo.py -i /home/mizutu/Videos/driver.mp4 -m /home/mizutu/model/intel/FP16/human-pose-estimation-0001.xml -at openpose -d MULTI:MYRIAD.3.4.1-ma2480,MYRIAD.3.4.3-ma2480
:
[ INFO ] Starting inference...
To close the application, press 'CTRL+C' here or switch to the output window and press ESC key
Latency: 213.3 ms
FPS: 4.5
・③ NCS2 3本$ cd ~/run_app2
$ source set_MYRIAD16_3X.sh
$ ./_human_pose_estimation.sh
[human_pose_estimation_demo.sh] 'human_pose_estimation_demo' Run !!
MODEL: FP16
DEVICE: MULTI:MYRIAD.3.4.1-ma2480,MYRIAD.3.4.3-ma2480,MYRIAD.3.4.4-ma2480
COMMAND: python3 human_pose_estimation_demo.py -i /home/mizutu/Videos/driver.mp4 -m /home/mizutu/model/intel/FP16/human-pose-estimation-0001.xml -at openpose -d MULTI:MYRIAD.3.4.1-ma2480,MYRIAD.3.4.3-ma2480,MYRIAD.3.4.4-ma2480
:
[ INFO ] Starting inference...
To close the application, press 'CTRL+C' here or switch to the output window and press ESC key
Latency: 212.9 ms
FPS: 4.5| 項目 | ①1本 | ②2本 | ③3本 |
| Latency (ms) | 212.3 | 213.3 | 212.9 |
| fps | 4.6 | 4.5 | 4.5 |
$ cd ~/run_app2
$ source set_MYRIAD16.sh
$ ./_object_detection_demo.sh
[object_detection_demo.sh] 'object_detection_demo' Run !!
MODEL: FP16
DEVICE: MYRIAD
COMMAND: ./object_detection_demo -i /home/mizutu/Videos/video001.mp4 -at ssd -m /home/mizutu/model/intel/FP16/person-detection-retail-0013.xml -loop -d MYRIAD
:
[ INFO ] Metric reports:
Latency: 308.2 ms
FPS: 15.8
[ INFO ]
[ INFO ] The execution has completed successfully
double free or corruption (fasttop)
Aborted (core dumped)
・② NCS2 2本$ cd ~/run_app2
$ source set_MYRIAD16_2X.sh
$ ./_object_detection_demo.sh
[object_detection_demo.sh] 'object_detection_demo' Run !!
MODEL: FP16
DEVICE: MULTI:MYRIAD.3.4.1-ma2480,MYRIAD.3.4.3-ma2480
COMMAND: ./object_detection_demo -i /home/mizutu/Videos/video001.mp4 -at ssd -m /home/mizutu/model/intel/FP16/person-detection-retail-0013.xml -loop -d MULTI:MYRIAD.3.4.1-ma2480,MYRIAD.3.4.3-ma2480
:
[ INFO ] Metric reports:
Latency: 277.7 ms
FPS: 31.5
[ INFO ]
[ INFO ] The execution has completed successfully
・③ NCS2 3本$ cd ~/run_app2
$ source set_MYRIAD16_3X.sh
$ ./_object_detection_demo.sh
[object_detection_demo.sh] 'object_detection_demo' Run !!
MODEL: FP16
DEVICE: MULTI:MYRIAD.3.4.1-ma2480,MYRIAD.3.4.3-ma2480,MYRIAD.3.4.4-ma2480
COMMAND: ./object_detection_demo -i /home/mizutu/Videos/video001.mp4 -at ssd -m /home/mizutu/model/intel/FP16/person-detection-retail-0013.xml -loop -d MULTI:MYRIAD.3.4.1-ma2480,MYRIAD.3.4.3-ma2480,MYRIAD.3.4.4-ma2480
:
[ INFO ] Metric reports:
Latency: 267.1 ms
FPS: 47.3
[ INFO ]
[ INFO ] The execution has completed successfully| 項目 | ①1本 | ②2本 | ③3本 |
| Latency (ms) | 308.2 | 277.7 | 267.1 |
| fps | 15.8 | 31.5 | 47.3 |
$ cd ~/run_app2
$ source set_MYRIAD16.sh
$ ./_smart_classroom_demo.sh
[smart_classroom_demo.sh] 'smart_classroom_demo' Run !!
MODEL: FP16
DEVICE: MYRIAD
COMMAND: ./smart_classroom_demo -loop -i /home/mizutu/Videos/classroom_s.mp4 -m_act /home/mizutu/model/intel/FP16/person-detection-action-recognition-0005.xml -m_fd /home/mizutu/model/intel/FP16/face-detection-adas-0001.xml -d_act MYRIAD -d_fd MYRIAD
:
To close the application, press 'CTRL+C' here or switch to the output window and press ESC key
[ INFO ] Mean FPS: 3.69686
[ INFO ] Frames processed: 16
[ INFO ] Execution successful
・② NCS2 2本$ cd ~/run_app2
$ source set_MYRIAD16_2X.sh
$ ./_smart_classroom_demo.sh
[smart_classroom_demo.sh] 'smart_classroom_demo' Run !!
MODEL: FP16
DEVICE: MULTI:MYRIAD.3.4.1-ma2480,MYRIAD.3.4.3-ma2480
COMMAND: ./smart_classroom_demo -loop -i /home/mizutu/Videos/classroom_s.mp4 -m_act /home/mizutu/model/intel/FP16/person-detection-action-recognition-0005.xml -m_fd /home/mizutu/model/intel/FP16/face-detection-adas-0001.xml -d_act MULTI:MYRIAD.3.4.1-ma2480,MYRIAD.3.4.3-ma2480 -d_fd MULTI:MYRIAD.3.4.1-ma2480,MYRIAD.3.4.3-ma2480
:
To close the application, press 'CTRL+C' here or switch to the output window and press ESC key
[ INFO ] Mean FPS: 3.68899
[ INFO ] Frames processed: 13
E: [ncAPI] [ 272003] [smart_classroom] ncDeviceClose:1801 pthread_mutex_destroy(&d->graph_stream_m) failed with error: 16
[ INFO ] Execution successful
・③ NCS2 3本$ cd ~/run_app2
$ source set_MYRIAD16_3X.sh
$ ./_smart_classroom_demo.sh
[smart_classroom_demo.sh] 'smart_classroom_demo' Run !!
MODEL: FP16
DEVICE: MULTI:MYRIAD.3.4.1-ma2480,MYRIAD.3.4.3-ma2480,MYRIAD.3.4.4-ma2480
COMMAND: ./smart_classroom_demo -loop -i /home/mizutu/Videos/classroom_s.mp4 -m_act /home/mizutu/model/intel/FP16/person-detection-action-recognition-0005.xml -m_fd /home/mizutu/model/intel/FP16/face-detection-adas-0001.xml -d_act MULTI:MYRIAD.3.4.1-ma2480,MYRIAD.3.4.3-ma2480,MYRIAD.3.4.4-ma2480 -d_fd MULTI:MYRIAD.3.4.1-ma2480,MYRIAD.3.4.3-ma2480,MYRIAD.3.4.4-ma2480
:
To close the application, press 'CTRL+C' here or switch to the output window and press ESC key
[ INFO ] Mean FPS: 3.68656
[ INFO ] Frames processed: 43
E: [ncAPI] [ 837713] [smart_classroom] ncDeviceClose:1801 pthread_mutex_destroy(&d->graph_stream_m) failed with error: 16
E: [ncAPI] [ 838637] [smart_classroom] ncDeviceClose:1801 pthread_mutex_destroy(&d->graph_stream_m) failed with error: 16
[ INFO ] Execution successful| 項目 | ①1本 | ②2本 | ③3本 |
| Mean FPS | 3.70 | 3.70 | 3.70 |
| Frames processed | 16 | 13 | 43 |
$ cd ~/run_app2
$ source set_MYRIAD16.sh
$ ./_pedestrian_tracker_demo.sh
[pedestrian_tracker_demo.sh] 'pedestrian_tracker_demo' Run !!
MODEL: FP16
DEVICE: MYRIAD
COMMAND: ./pedestrian_tracker_demo -loop -i /home/mizutu/Videos/video003_m.mp4 -m_det /home/mizutu/model/intel/FP16/person-detection-retail-0013.xml -m_reid /home/mizutu/model/intel/FP16/person-reidentification-retail-0288.xml -d_det MYRIAD -d_reid MYRIAD
:
[ ERROR ] Failed to compile layer "736": Unsupported combination of indices in layer "736". Only across channel and full batch supported.
・② NCS2 2本$ cd ~/run_app2
$ source set_MYRIAD16_2X.sh
$ ./_pedestrian_tracker_demo.sh
[pedestrian_tracker_demo.sh] 'pedestrian_tracker_demo' Run !!
MODEL: FP16
DEVICE: MULTI:MYRIAD.3.4.1-ma2480,MYRIAD.3.4.3-ma2480
COMMAND: ./pedestrian_tracker_demo -loop -i /home/mizutu/Videos/video003_m.mp4 -m_det /home/mizutu/model/intel/FP16/person-detection-retail-0013.xml -m_reid /home/mizutu/model/intel/FP16/person-reidentification-retail-0288.xml -d_det MULTI:MYRIAD.3.4.1-ma2480,MYRIAD.3.4.3-ma2480 -d_reid MULTI:MYRIAD.3.4.1-ma2480,MYRIAD.3.4.3-ma2480
:
[ ERROR ] Failed to compile layer "736": Unsupported combination of indices in layer "736". Only across channel and full batch supported.
・③ NCS2 3本$ cd ~/run_app2
$ source set_MYRIAD16_3X.sh
$ ./_pedestrian_tracker_demo.sh
[pedestrian_tracker_demo.sh] 'pedestrian_tracker_demo' Run !!
MODEL: FP16
DEVICE: MULTI:MYRIAD.3.4.1-ma2480,MYRIAD.3.4.3-ma2480,MYRIAD.3.4.4-ma2480
COMMAND: ./pedestrian_tracker_demo -loop -i /home/mizutu/Videos/video003_m.mp4 -m_det /home/mizutu/model/intel/FP16/person-detection-retail-0013.xml -m_reid /home/mizutu/model/intel/FP16/person-reidentification-retail-0288.xml -d_det MULTI:MYRIAD.3.4.1-ma2480,MYRIAD.3.4.3-ma2480,MYRIAD.3.4.4-ma2480 -d_reid MULTI:MYRIAD.3.4.1-ma2480,MYRIAD.3.4.3-ma2480,MYRIAD.3.4.4-ma2480
:
[ ERROR ] Failed to compile layer "736": Unsupported combination of indices in layer "736". Only across channel and full batch supported.
$ cd ~/run_app2
$ source set_MYRIAD16.sh
$ ./_super_resolution_demo.sh
[super_resolution_demo.sh] 'super_resolution_demo' Run !!
MODEL: FP16
DEVICE: MYRIAD
COMMAND: ./super_resolution_demo -i /home/mizutu/Images/image-low.bmp -m /home/mizutu/model/intel/FP16/single-image-super-resolution-1032.xml -show true -d MYRIAD
:
[ 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 NCS2 2本$ cd ~/run_app2
$ source set_MYRIAD16_2X.sh
$ ./_super_resolution_demo.sh
[super_resolution_demo.sh] 'super_resolution_demo' Run !!
MODEL: FP16
DEVICE: MULTI:MYRIAD.3.4.1-ma2480,MYRIAD.3.4.3-ma2480
COMMAND: ./super_resolution_demo -i /home/mizutu/Images/image-low.bmp -m /home/mizutu/model/intel/FP16/single-image-super-resolution-1032.xml -show true -d MULTI:MYRIAD.3.4.1-ma2480,MYRIAD.3.4.3-ma2480
:
[ 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 NCS2 3本$ cd ~/run_app2
$ source set_MYRIAD16_3X.sh
$ ./_super_resolution_demo.sh
[super_resolution_demo.sh] 'super_resolution_demo' Run !!
MODEL: FP16
DEVICE: MULTI:MYRIAD.3.4.1-ma2480,MYRIAD.3.4.3-ma2480,MYRIAD.3.4.4-ma2480
COMMAND: ./super_resolution_demo -i /home/mizutu/Images/image-low.bmp -m /home/mizutu/model/intel/FP16/single-image-super-resolution-1032.xml -show true -d MULTI:MYRIAD.3.4.1-ma2480,MYRIAD.3.4.3-ma2480,MYRIAD.3.4.4-ma2480
:
[ 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
$ cd ~/run_app2 $ source set_MYRIAD16.sh $ ./_single_human_pose_estimation_demo.sh [single_human_pose_estimation_demo.sh] 'single_human_pose_estimation_demo' Run !! MODEL: FP16 DEVICE: MYRIAD COMMAND: python3 single_human_pose_estimation_demo.py -m_od /home/mizutu/model/public/FP16/mobilenet-ssd.xml -m_hpe /home/mizutu/model/public/FP16/single-human-pose-estimation-0001.xml -i /home/mizutu/Videos/person_m.mp4 -d MYRIAD・② NCS2 2本
$ cd ~/run_app2 $ source set_MYRIAD16_2X.sh $ ./_single_human_pose_estimation_demo.sh [single_human_pose_estimation_demo.sh] 'single_human_pose_estimation_demo' Run !! MODEL: FP16 DEVICE: MULTI:MYRIAD.3.4.1-ma2480,MYRIAD.3.4.3-ma2480 COMMAND: python3 single_human_pose_estimation_demo.py -m_od /home/mizutu/model/public/FP16/mobilenet-ssd.xml -m_hpe /home/mizutu/model/public/FP16/single-human-pose-estimation-0001.xml -i /home/mizutu/Videos/person_m.mp4 -d MULTI:MYRIAD.3.4.1-ma2480,MYRIAD.3.4.3-ma2480・③ NCS2 3本
$ cd ~/run_app2 $ source set_MYRIAD16_3X.sh $ ./_single_human_pose_estimation_demo.sh [single_human_pose_estimation_demo.sh] 'single_human_pose_estimation_demo' Run !! MODEL: FP16 DEVICE: MULTI:MYRIAD.3.4.1-ma2480,MYRIAD.3.4.3-ma2480,MYRIAD.3.4.4-ma2480 COMMAND: python3 single_human_pose_estimation_demo.py -m_od /home/mizutu/model/public/FP16/mobilenet-ssd.xml -m_hpe /home/mizutu/model/public/FP16/single-human-pose-estimation-0001.xml -i /home/mizutu/Videos/person_m.mp4 -d MULTI:MYRIAD.3.4.1-ma2480,MYRIAD.3.4.3-ma2480,MYRIAD.3.4.4-ma2480
| 項目 | ①1本 | ②2本 | ③3本 |
| summary (fps) | 0.5 | 0.5 | 0.4 |
| estimation (fps) | 1.6 | 1.6 | 1.6 |
| detection (fps) | 25.6 | 25.6 | 25.6 |
$ cd ~/run_app2
$ source set_MYRIAD16.sh
$ ./_interactive_face_detection_demo.sh
[interactive_face_detection_demo.sh] 'interactive_face_detection_demo' Run !!
MODEL: FP16
DEVICE: MYRIAD
COMMAND: ./interactive_face_detection_demo -loop -i /home/mizutu/Videos/emotion2_m.mp4 -m /home/mizutu/model/intel/FP16/face-detection-adas-0001.xml -m_ag /home/mizutu/model/intel/FP16/age-gender-recognition-retail-0013.xml -m_hp /home/mizutu/model/intel/FP16/head-pose-estimation-adas-0001.xml -m_em /home/mizutu/model/intel/FP16/emotions-recognition-retail-0003.xml -m_lm /home/mizutu/model/intel/FP16/facial-landmarks-35-adas-0002.xml -m_am /home/mizutu/model/public/FP16/anti-spoof-mn3.xml -d MYRIAD -d_ag MYRIAD -d_hp MYRIAD -d_em MYRIAD -d_lm MYRIAD -d_am MYRIAD
:
[ 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: 14
[ INFO ] Total image throughput: 2.40595 fps
[ INFO ] Execution successful
・② NCS2 2本$ cd ~/run_app2
$ source set_MYRIAD16_2X.sh
$ ./_interactive_face_detection_demo.sh
[interactive_face_detection_demo.sh] 'interactive_face_detection_demo' Run !!
MODEL: FP16
DEVICE: MULTI:MYRIAD.3.4.1-ma2480,MYRIAD.3.4.3-ma2480
COMMAND: ./interactive_face_detection_demo -loop -i /home/mizutu/Videos/emotion2_m.mp4 -m /home/mizutu/model/intel/FP16/face-detection-adas-0001.xml -m_ag /home/mizutu/model/intel/FP16/age-gender-recognition-retail-0013.xml -m_hp /home/mizutu/model/intel/FP16/head-pose-estimation-adas-0001.xml -m_em /home/mizutu/model/intel/FP16/emotions-recognition-retail-0003.xml -m_lm /home/mizutu/model/intel/FP16/facial-landmarks-35-adas-0002.xml -m_am /home/mizutu/model/public/FP16/anti-spoof-mn3.xml -d MULTI:MYRIAD.3.4.1-ma2480,MYRIAD.3.4.3-ma2480 -d_ag MULTI:MYRIAD.3.4.1-ma2480,MYRIAD.3.4.3-ma2480 -d_hp MULTI:MYRIAD.3.4.1-ma2480,MYRIAD.3.4.3-ma2480 -d_em MULTI:MYRIAD.3.4.1-ma2480,MYRIAD.3.4.3-ma2480 -d_lm MULTI:MYRIAD.3.4.1-ma2480,MYRIAD.3.4.3-ma2480 -d_am MULTI:MYRIAD.3.4.1-ma2480,MYRIAD.3.4.3-ma2480
:
[ INFO ] Loading Antispoofing Classifier model to the MULTI:MYRIAD.3.4.1-ma2480,MYRIAD.3.4.3-ma2480 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: 17
[ INFO ] Total image throughput: 2.38364 fps
[ INFO ] Execution successful
・③ NCS2 3本$ cd ~/run_app2
$ source set_MYRIAD16_3X.sh
$ ./_interactive_face_detection_demo.sh
[interactive_face_detection_demo.sh] 'interactive_face_detection_demo' Run !!
MODEL: FP16
DEVICE: MULTI:MYRIAD.3.4.1-ma2480,MYRIAD.3.4.3-ma2480,MYRIAD.3.4.4-ma2480
COMMAND: ./interactive_face_detection_demo -loop -i /home/mizutu/Videos/emotion2_m.mp4 -m /home/mizutu/model/intel/FP16/face-detection-adas-0001.xml -m_ag /home/mizutu/model/intel/FP16/age-gender-recognition-retail-0013.xml -m_hp /home/mizutu/model/intel/FP16/head-pose-estimation-adas-0001.xml -m_em /home/mizutu/model/intel/FP16/emotions-recognition-retail-0003.xml -m_lm /home/mizutu/model/intel/FP16/facial-landmarks-35-adas-0002.xml -m_am /home/mizutu/model/public/FP16/anti-spoof-mn3.xml -d MULTI:MYRIAD.3.4.1-ma2480,MYRIAD.3.4.3-ma2480,MYRIAD.3.4.4-ma2480 -d_ag MULTI:MYRIAD.3.4.1-ma2480,MYRIAD.3.4.3-ma2480,MYRIAD.3.4.4-ma2480 -d_hp MULTI:MYRIAD.3.4.1-ma2480,MYRIAD.3.4.3-ma2480,MYRIAD.3.4.4-ma2480 -d_em MULTI:MYRIAD.3.4.1-ma2480,MYRIAD.3.4.3-ma2480,MYRIAD.3.4.4-ma2480 -d_lm MULTI:MYRIAD.3.4.1-ma2480,MYRIAD.3.4.3-ma2480,MYRIAD.3.4.4-ma2480 -d_am MULTI:MYRIAD.3.4.1-ma2480,MYRIAD.3.4.3-ma2480,MYRIAD.3.4.4-ma2480
:
[ INFO ] Loading Antispoofing Classifier model to the MULTI:MYRIAD.3.4.1-ma2480,MYRIAD.3.4.3-ma2480,MYRIAD.3.4.4-ma2480 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: 19
[ INFO ] Total image throughput: 2.38784 fps
[ INFO ] Execution successful| 項目 | ①1本 | ②2本 | ③3本 |
| Number of processed frames | 2.41 | 2.38 | 2.39 |
| Total image throughput (fps) | 14 | 17 | 19 |
$ cd ~/run_app2
$ source set_MYRIAD16.sh
$ ./_gaze_estimation_demo.sh
[gaze_estimation_demo.sh] 'gaze_estimation_demo' Run !!
MODEL: FP16
DEVICE: MYRIAD
COMMAND: ./gaze_estimation_demo -loop -i /home/mizutu/Videos/emotion2_m.mp4 -m /home/mizutu/model/intel/FP16/gaze-estimation-adas-0002.xml -m_fd /home/mizutu/model/intel/FP16/face-detection-retail-0004.xml -m_hp /home/mizutu/model/intel/FP16/head-pose-estimation-adas-0001.xml -m_lm /home/mizutu/model/intel/FP16/facial-landmarks-35-adas-0002.xml -m_es /home/mizutu/model/public/FP16/open-closed-eye-0001.xml -d MYRIAD -d_fd MYRIAD -d_hp MYRIAD -d_lm MYRIAD -d_es MYRIAD
:
[ INFO ] Execution successful
・② NCS2 2本$ cd ~/run_app2
$ source set_MYRIAD16_2X.sh
$ ./_gaze_estimation_demo.sh
[gaze_estimation_demo.sh] 'gaze_estimation_demo' Run !!
MODEL: FP16
DEVICE: MULTI:MYRIAD.3.4.1-ma2480,MYRIAD.3.4.3-ma2480
COMMAND: ./gaze_estimation_demo -loop -i /home/mizutu/Videos/emotion2_m.mp4 -m /home/mizutu/model/intel/FP16/gaze-estimation-adas-0002.xml -m_fd /home/mizutu/model/intel/FP16/face-detection-retail-0004.xml -m_hp /home/mizutu/model/intel/FP16/head-pose-estimation-adas-0001.xml -m_lm /home/mizutu/model/intel/FP16/facial-landmarks-35-adas-0002.xml -m_es /home/mizutu/model/public/FP16/open-closed-eye-0001.xml -d MULTI:MYRIAD.3.4.1-ma2480,MYRIAD.3.4.3-ma2480 -d_fd MULTI:MYRIAD.3.4.1-ma2480,MYRIAD.3.4.3-ma2480 -d_hp MULTI:MYRIAD.3.4.1-ma2480,MYRIAD.3.4.3-ma2480 -d_lm MULTI:MYRIAD.3.4.1-ma2480,MYRIAD.3.4.3-ma2480 -d_es MULTI:MYRIAD.3.4.1-ma2480,MYRIAD.3.4.3-ma2480
:
[ INFO ] Execution successful
・③ NCS2 3本$ cd ~/run_app2
$ source set_MYRIAD16_3X.sh
$ ./_gaze_estimation_demo.sh
[gaze_estimation_demo.sh] 'gaze_estimation_demo' Run !!
MODEL: FP16
DEVICE: MULTI:MYRIAD.3.4.1-ma2480,MYRIAD.3.4.3-ma2480,MYRIAD.3.4.4-ma2480
COMMAND: ./gaze_estimation_demo -loop -i /home/mizutu/Videos/emotion2_m.mp4 -m /home/mizutu/model/intel/FP16/gaze-estimation-adas-0002.xml -m_fd /home/mizutu/model/intel/FP16/face-detection-retail-0004.xml -m_hp /home/mizutu/model/intel/FP16/head-pose-estimation-adas-0001.xml -m_lm /home/mizutu/model/intel/FP16/facial-landmarks-35-adas-0002.xml -m_es /home/mizutu/model/public/FP16/open-closed-eye-0001.xml -d MULTI:MYRIAD.3.4.1-ma2480,MYRIAD.3.4.3-ma2480,MYRIAD.3.4.4-ma2480 -d_fd MULTI:MYRIAD.3.4.1-ma2480,MYRIAD.3.4.3-ma2480,MYRIAD.3.4.4-ma2480 -d_hp MULTI:MYRIAD.3.4.1-ma2480,MYRIAD.3.4.3-ma2480,MYRIAD.3.4.4-ma2480 -d_lm MULTI:MYRIAD.3.4.1-ma2480,MYRIAD.3.4.3-ma2480,MYRIAD.3.4.4-ma2480 -d_es MULTI:MYRIAD.3.4.1-ma2480,MYRIAD.3.4.3-ma2480,MYRIAD.3.4.4-ma2480
:
[ INFO ] Execution successful| 項目 | ①1本 | ②2本 | ③3本 |
| overrali (fps) | 28 | 29 | 31 |
| interface (fps) | 32 | 33 | 35 |
$ cd ~/run_app2
$ source set_MYRIAD16.sh
$ ./_security_barrier_camera_demo.sh
[security_barrier_camera_demo.sh] 'security_barrier_camera_demo' Run !!
MODEL: FP16
DEVICE: MYRIAD
COMMAND: ./security_barrier_camera_demo -i /home/mizutu/Videos/car-detection.mp4 -m /home/mizutu/model/intel/FP16/vehicle-license-plate-detection-barrier-0106.xml -m_va /home/mizutu/model/intel/FP16/vehicle-attributes-recognition-barrier-0039.xml -m_lpr /home/mizutu/model/intel/FP16/license-plate-recognition-barrier-0001.xml -d MYRIAD -d_va MYRIAD -d_lpr MYRIAD
:
[ 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
・② NCS2 2本$ cd ~/run_app2
$ source set_MYRIAD16_2X.sh
$ ./_security_barrier_camera_demo.sh
[security_barrier_camera_demo.sh] 'security_barrier_camera_demo' Run !!
MODEL: FP16
DEVICE: MULTI:MYRIAD.3.4.1-ma2480,MYRIAD.3.4.3-ma2480
COMMAND: ./security_barrier_camera_demo -i /home/mizutu/Videos/car-detection.mp4 -m /home/mizutu/model/intel/FP16/vehicle-license-plate-detection-barrier-0106.xml -m_va /home/mizutu/model/intel/FP16/vehicle-attributes-recognition-barrier-0039.xml -m_lpr /home/mizutu/model/intel/FP16/license-plate-recognition-barrier-0001.xml -d MULTI:MYRIAD.3.4.1-ma2480,MYRIAD.3.4.3-ma2480 -d_va MULTI:MYRIAD.3.4.1-ma2480,MYRIAD.3.4.3-ma2480 -d_lpr MULTI:MYRIAD.3.4.1-ma2480,MYRIAD.3.4.3-ma2480
:
[ 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
35.1FPS for (375 / 1) frames
Detection InferRequests usage: 100.0%
[ INFO ] Execution successful
・③ NCS2 3本$ cd ~/run_app2
$ source set_MYRIAD16_3X.sh
$ ./_security_barrier_camera_demo.sh
[security_barrier_camera_demo.sh] 'security_barrier_camera_demo' Run !!
MODEL: FP16
DEVICE: MULTI:MYRIAD.3.4.1-ma2480,MYRIAD.3.4.3-ma2480,MYRIAD.3.4.4-ma2480
COMMAND: ./security_barrier_camera_demo -i /home/mizutu/Videos/car-detection.mp4 -m /home/mizutu/model/intel/FP16/vehicle-license-plate-detection-barrier-0106.xml -m_va /home/mizutu/model/intel/FP16/vehicle-attributes-recognition-barrier-0039.xml -m_lpr /home/mizutu/model/intel/FP16/license-plate-recognition-barrier-0001.xml -d MULTI:MYRIAD.3.4.1-ma2480,MYRIAD.3.4.3-ma2480,MYRIAD.3.4.4-ma2480 -d_va MULTI:MYRIAD.3.4.1-ma2480,MYRIAD.3.4.3-ma2480,MYRIAD.3.4.4-ma2480 -d_lpr MULTI:MYRIAD.3.4.1-ma2480,MYRIAD.3.4.3-ma2480,MYRIAD.3.4.4-ma2480
:
[ 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
35.4FPS for (375 / 1) frames
Detection InferRequests usage: 100.0%
[ INFO ] Execution successful| 項目 | ①1本 | ②2本 | ③3本 |
| fps | 35.3 | 35.1 | 35.4 |
$ cd ~/run_app2 $ source set_MYRIAD16.sh $ ./_image_inpainting_demo.sh [image_inpainting_demo.sh] 'image_inpainting_demo' Run !! MODEL: FP16 DEVICE: MYRIAD COMMAND: python3 image_inpainting_demo.py -m /home/mizutu/model/public/FP16/gmcnn-places2-tf.xml -i /home/mizutu/Images/car_m.jpg -ar -d MYRIAD・② NCS2 2本
$ cd ~/run_app2 $ source set_MYRIAD16_2X.sh $ ./_image_inpainting_demo.sh [image_inpainting_demo.sh] 'image_inpainting_demo' Run !! MODEL: FP16 DEVICE: MULTI:MYRIAD.3.4.1-ma2480,MYRIAD.3.4.3-ma2480 COMMAND: python3 image_inpainting_demo.py -m /home/mizutu/model/public/FP16/gmcnn-places2-tf.xml -i /home/mizutu/Images/car_m.jpg -ar -d MULTI:MYRIAD.3.4.1-ma2480,MYRIAD.3.4.3-ma2480・③ NCS2 3本
$ cd ~/run_app2 $ source set_MYRIAD16_3X.sh $ ./_image_inpainting_demo.sh [image_inpainting_demo.sh] 'image_inpainting_demo' Run !! MODEL: FP16 DEVICE: MULTI:MYRIAD.3.4.1-ma2480,MYRIAD.3.4.3-ma2480,MYRIAD.3.4.4-ma2480 COMMAND: python3 image_inpainting_demo.py -m /home/mizutu/model/public/FP16/gmcnn-places2-tf.xml -i /home/mizutu/Images/car_m.jpg -ar -d MULTI:MYRIAD.3.4.1-ma2480,MYRIAD.3.4.3-ma2480,MYRIAD.3.4.4-ma2480
$ cd ~/run_app2 $ source set_MYRIAD16.sh $ ./_colorization_demo.sh [colorization_demo.sh] 'colorization_demo' Run !! MODEL: FP16 DEVICE: MYRIAD COMMAND: python3 colorization_demo.py -m /home/mizutu/model/public/FP16/colorization-v2.xml -i /home/mizutu/Videos/mono03.mp4 -d MYRIAD・② NCS2 2本
$ cd ~/run_app2 $ source set_MYRIAD16_2X.sh $ ./_colorization_demo.sh [colorization_demo.sh] 'colorization_demo' Run !! MODEL: FP16 DEVICE: MULTI:MYRIAD.3.4.1-ma2480,MYRIAD.3.4.3-ma2480 COMMAND: python3 colorization_demo.py -m /home/mizutu/model/public/FP16/colorization-v2.xml -i /home/mizutu/Videos/mono03.mp4 -d MULTI:MYRIAD.3.4.1-ma2480,MYRIAD.3.4.3-ma2480・③ NCS2 3本
$ cd ~/run_app2 $ source set_MYRIAD16_3X.sh $ ./_colorization_demo.sh [colorization_demo.sh] 'colorization_demo' Run !! MODEL: FP16 DEVICE: MULTI:MYRIAD.3.4.1-ma2480,MYRIAD.3.4.3-ma2480,MYRIAD.3.4.4-ma2480 COMMAND: python3 colorization_demo.py -m /home/mizutu/model/public/FP16/colorization-v2.xml -i /home/mizutu/Videos/mono03.mp4 -d MULTI:MYRIAD.3.4.1-ma2480,MYRIAD.3.4.3-ma2480,MYRIAD.3.4.4-ma2480
$ cd ~/run_app2
$ source set_MYRIAD16.sh
$ ./_deblurring_demo.sh
[deblurring_demo.sh] 'deblurring_demo' Run !!
MODEL: FP16
DEVICE: MYRIAD
COMMAND: python3 deblurring_demo.py -m /home/mizutu/model/public/FP16/deblurgan-v2.xml -i /home/mizutu/Images/deblurred_image.png --loop -d MYRIAD
:
[ INFO ] Starting inference...
To close the application, press 'CTRL+C' here or switch to the output window and press ESC key
Latency: 589.8 ms
FPS: 1.6
・② NCS2 2本$ cd ~/run_app2
$ source set_MYRIAD16_2X.sh
$ ./_deblurring_demo.sh
[deblurring_demo.sh] 'deblurring_demo' Run !!
MODEL: FP16
DEVICE: MULTI:MYRIAD.3.4.1-ma2480,MYRIAD.3.4.3-ma2480
COMMAND: python3 deblurring_demo.py -m /home/mizutu/model/public/FP16/deblurgan-v2.xml -i /home/mizutu/Images/deblurred_image.png --loop -d MULTI:MYRIAD.3.4.1-ma2480,MYRIAD.3.4.3-ma2480
:
[ INFO ] Starting inference...
To close the application, press 'CTRL+C' here or switch to the output window and press ESC key
Latency: 589.9 ms
FPS: 1.6
・③ NCS2 3本$ cd ~/run_app2 $ source set_MYRIAD16_3X.sh $ ./_deblurring_demo.sh [deblurring_demo.sh] 'deblurring_demo' Run !! MODEL: FP16 DEVICE: MULTI:MYRIAD.3.4.1-ma2480,MYRIAD.3.4.3-ma2480,MYRIAD.3.4.4-ma2480 COMMAND: python3 deblurring_demo.py -m /home/mizutu/model/public/FP16/deblurgan-v2.xml -i /home/mizutu/Images/deblurred_image.png --loop -d MULTI:MYRIAD.3.4.1-ma2480,MYRIAD.3.4.3-ma2480,MYRIAD.3.4.4-ma2480 [ INFO ] Initializing Inference Engine... [ INFO ] Loading network... [ INFO ] Reading network from IR... [ INFO ] Loading network to MULTI:MYRIAD.3.4.1-ma2480,MYRIAD.3.4.3-ma2480,MYRIAD.3.4.4-ma2480 plugin... [ INFO ] Starting inference... To close the application, press 'CTRL+C' here or switch to the output window and press ESC key Latency: 590.7 ms FPS: 1.6
| 項目 | ①1本 | ②2本 | ③3本 |
| Latency (ms) | 589.8 | 589.9 | 590.7 |
| fps | 1.6 | 1.6 | 1.6 |
使用可能なすべての推論エンジン デバイスを照会し、サポートされているメトリックと既定の構成値を出力する。
$ cd ~/run_app2 $ source set_MYRIAD16_3X.sh $ ./face_mask.sh [face_mask.sh] 'face_mask' Run !! DEVICE: MULTI:MYRIAD.3.4.1-ma2480,MYRIAD.3.4.3-ma2480,MYRIAD.3.4.4-ma2480 COMMAND: python3 face_mask.py -m_dt ./models/face-detection-adas-0001.xml -m_mk ./models/face_mask.xml -d MULTI:MYRIAD.3.4.1-ma2480,MYRIAD.3.4.3-ma2480,MYRIAD.3.4.4-ma2480 --- Face Mask Check --- 4.5.2-openvino OpenVINO inference_engine: 2.1.2021.3.0-2787-60059f2c755-releases/2021/3 Face Mask Check: Starting application... - Image File : ./images/mask-test.jpg - m_detect : ./models/face-detection-adas-0001.xml - m_mask : ./models/face_mask.xml - Device : MULTI:MYRIAD.3.4.1-ma2480,MYRIAD.3.4.3-ma2480,MYRIAD.3.4.4-ma2480 - Language : jp - Input Shape1 : data - Output Shape1: detection_out - Input Shape2 : data - Output Shape2: fc5 - Program Title: y - Speed flag : y - Processed out: non FPS average: 5.90 Finished.
| 項目 | ①1本 | ②2本 | ③3本 |
| fps | 5.90 | 5.90 | 5.90 |
$ cd ~/run_app2 $ source set_MYRIAD16_3X.sh $ ./virtual_fitting.sh [virtual_fitting.sh] virtual_Fitting.py Run !! itemidx.: 0 program : virtual_fitting.py model1. : -m_dt /home/mizutu/model/intel/FP16/face-detection-retail-0005.xml model2. : -m_lm /home/mizutu/model/intel/FP16/landmarks-regression-retail-0009.xml device. : MULTI:MYRIAD.3.4.1-ma2480,MYRIAD.3.4.3-ma2480,MYRIAD.3.4.4-ma2480 input.. : -i /home/mizutu/Images/photo.jpg output. : MODEL: FP16 DEVICE: MULTI:MYRIAD.3.4.1-ma2480,MYRIAD.3.4.3-ma2480,MYRIAD.3.4.4-ma2480 COMMAND: python3 virtual_fitting.py -item 0 -m_dt /home/mizutu/model/intel/FP16/face-detection-retail-0005.xml -m_lm /home/mizutu/model/intel/FP16/landmarks-regression-retail-0009.xml -i /home/mizutu/Images/photo.jpg -d MULTI:MYRIAD.3.4.1-ma2480,MYRIAD.3.4.3-ma2480,MYRIAD.3.4.4-ma2480 --- Virtual Fitting --- 4.5.2-openvino OpenVINO inference_engine: 2.1.2021.3.0-2787-60059f2c755-releases/2021/3 virtual_fitting.py:161: DeprecationWarning: 'inputs' property of IENetwork class is deprecated. To access DataPtrs user need to use 'input_data' property of InputInfoPtr objects which can be accessed by 'input_info' property. input_blob_face = next(iter(net_face.inputs)) Virtual Fitting: Starting application... - Item File : ../../Images/parts/glass01.png - Image File : /home/mizutu/Images/photo.jpg - m_detect : /home/mizutu/model/intel/FP16/face-detection-retail-0005.xml - m_recognition: /home/mizutu/model/intel/FP16/landmarks-regression-retail-0009.xml - Device : MULTI:MYRIAD.3.4.1-ma2480,MYRIAD.3.4.3-ma2480,MYRIAD.3.4.4-ma2480 - Program Title: y - Speed flag : y - Processed out: non FPS average: 19.70 Finished.
| 項目 | ①1本 | ②2本 | ③3本 |
| fps | 18.70 | 19.70 | 19.70 |
$ cd ~/run_app2 $ source set_MYRIAD16_3X.sh $ ./emotion2.sh [emotion2.sh] emotion2.py Run !! program : emotion2.py model1. : -m_dt /home/mizutu/model/intel/FP16/face-detection-adas-0001.xml model2. : -m_re /home/mizutu/model/intel/FP16/emotions-recognition-retail-0003.xml device. : MULTI:MYRIAD.3.4.1-ma2480,MYRIAD.3.4.3-ma2480,MYRIAD.3.4.4-ma2480 input.. : -i /home/mizutu/Images/emo2.jpg output. : MODEL: FP16 DEVICE: MULTI:MYRIAD.3.4.1-ma2480,MYRIAD.3.4.3-ma2480,MYRIAD.3.4.4-ma2480 COMMAND: python3 emotion2.py -m_dt /home/mizutu/model/intel/FP16/face-detection-adas-0001.xml -m_re /home/mizutu/model/intel/FP16/emotions-recognition-retail-0003.xml -d MULTI:MYRIAD.3.4.1-ma2480,MYRIAD.3.4.3-ma2480,MYRIAD.3.4.4-ma2480 -i /home/mizutu/Images/emo2.jpg --- Emotion Recognition 2 --- 4.5.2-openvino OpenVINO inference_engine: 2.1.2021.3.0-2787-60059f2c755-releases/2021/3 Emotion Recognition 2: Starting application... - Image File : /home/mizutu/Images/emo2.jpg - m_detect : /home/mizutu/model/intel/FP16/face-detection-adas-0001.xml - m_recognition: /home/mizutu/model/intel/FP16/emotions-recognition-retail-0003.xml - Device : MULTI:MYRIAD.3.4.1-ma2480,MYRIAD.3.4.3-ma2480,MYRIAD.3.4.4-ma2480 - Language : jp - Input Shape1 : data - Output Shape1: detection_out - Input Shape2 : data - Output Shape2: prob_emotion - Program Title: y - Speed flag : y - Processed out: non FPS average: 9.40 Finished.
| 項目 | ①1本 | ②2本 | ③3本 |
| fps | 9.70 | 9.20 | 9.40 |
$ cd ~/run_app2 $ source set_MYRIAD16_3X.sh $ ./age_gender2.sh [age_gender2.sh] age_gender2.py Run !! program : age_gender2.py model1. : -m_dt /home/mizutu/model/intel/FP16/face-detection-adas-0001.xml model2. : -m_re /home/mizutu/model/intel/FP16/age-gender-recognition-retail-0013.xml device. : MULTI:MYRIAD.3.4.1-ma2480,MYRIAD.3.4.3-ma2480,MYRIAD.3.4.4-ma2480 input.. : -i /home/mizutu/Images/emo2.jpg output. : MODEL: FP16 DEVICE: MULTI:MYRIAD.3.4.1-ma2480,MYRIAD.3.4.3-ma2480,MYRIAD.3.4.4-ma2480 COMMAND: python3 age_gender2.py -m_dt /home/mizutu/model/intel/FP16/face-detection-adas-0001.xml -m_re /home/mizutu/model/intel/FP16/age-gender-recognition-retail-0013.xml -d MULTI:MYRIAD.3.4.1-ma2480,MYRIAD.3.4.3-ma2480,MYRIAD.3.4.4-ma2480 -i /home/mizutu/Images/emo2.jpg --- Age/Gender Recognition 2 --- 4.5.2-openvino OpenVINO inference_engine: 2.1.2021.3.0-2787-60059f2c755-releases/2021/3 Age/Gender Recognition 2: Starting application... - Image File : /home/mizutu/Images/emo2.jpg - m_detect : /home/mizutu/model/intel/FP16/face-detection-adas-0001.xml - m_recognition: /home/mizutu/model/intel/FP16/age-gender-recognition-retail-0013.xml - Device : MULTI:MYRIAD.3.4.1-ma2480,MYRIAD.3.4.3-ma2480,MYRIAD.3.4.4-ma2480 - Language : jp - Input Shape1 : data - Output Shape1: detection_out - Input Shape2 : data - Output Shape2: age_conv3 - Program Title: y - Speed flag : y - Processed out: non FPS average: 9.60 Finished.
| 項目 | ①1本 | ②2本 | ③3本 |
| fps | 9.10 | 9.60 | 9.60 |
$ cd ~/run_app2
$ source set_MYRIAD16_3X.sh
$ ./object_detect_yolo3_2.sh
[object_detect_yolo3_2.sh] object_detect_yolo3_2.py Run !!
program : object_detect_yolo3_2.py
model1. : --ir /home/mizutu/model/public/FP16/yolo-v3-tiny-tf.xml
model2. :
device. : MULTI:MYRIAD.3.4.1-ma2480,MYRIAD.3.4.3-ma2480,MYRIAD.3.4.4-ma2480
input.. : -i /home/mizutu/Videos/car.mp4
output. :
MODEL: FP16
DEVICE: MULTI:MYRIAD.3.4.1-ma2480,MYRIAD.3.4.3-ma2480,MYRIAD.3.4.4-ma2480
COMMAND: python3 object_detect_yolo3_2.py --ir /home/mizutu/model/public/FP16/yolo-v3-tiny-tf.xml -i /home/mizutu/Videos/car.mp4 -d MULTI:MYRIAD.3.4.1-ma2480,MYRIAD.3.4.3-ma2480,MYRIAD.3.4.4-ma2480
--- TinyYOLO V3 Object detection ---
4.5.2-openvino
OpenVINO inference_engine: 2.1.2021.3.0-2787-60059f2c755-releases/2021/3
Running OpenVINO NCS Tensorflow TinyYolo v3 example...
Displaying image with objects detected in GUI...
Click in the GUI window and hit any key to exit.
object_detect_yolo3_2.py:289: DeprecationWarning: 'inputs' property of IENetwork class is deprecated. To access DataPtrs user need to use 'input_data' property of InputInfoPtr objects which can be accessed by 'input_info' property.
input_blob = next(iter(net.inputs))
Tiny Yolo v3: Starting application...
- IR File : /home/mizutu/model/public/FP16/yolo-v3-tiny-tf.xml
- Input Shape : [1, 3, 416, 416]
- Output Shapes:
- output #0 name: conv2d_12/Conv2D/YoloRegion
- output shape: [1, 255, 26, 26]
- output #1 name: conv2d_9/Conv2D/YoloRegion
- output shape: [1, 255, 13, 13]
- Labels File : coco.names_jp
- Image File : /home/mizutu/Videos/car.mp4
- Threshold : 0.6
- Intersection Over Union: 0.25
- Device : MULTI:MYRIAD.3.4.1-ma2480,MYRIAD.3.4.3-ma2480,MYRIAD.3.4.4-ma2480
- Program Title: y
- Speed flag : y
- Processed out: non
object_detect_yolo3_2.py:367: DeprecationWarning: 'outputs' property of InferRequest is deprecated. Please instead use 'output_blobs' property.
all_output_results = req_handle.outputs
FPS average: 9.90
Finished.
| 項目 | ①1本 | ②2本 | ③3本 |
| fps | 10.20 | 10.20 | 9.90 |
$ cd ~/run_app2
$ source set_MYRIAD16_3X.sh
$ ./person-tracking2.sh
[person-tracking2.sh] person-tracking2.py Run !!
program : person-tracking2.py
model1. : -m_dt /home/mizutu/model/intel/FP16/person-detection-retail-0013.xml
model2. : -m_re /home/mizutu/model/intel/FP16/person-reidentification-retail-0287.xml
device. : MULTI:MYRIAD.3.4.1-ma2480,MYRIAD.3.4.3-ma2480,MYRIAD.3.4.4-ma2480
input.. : -i /home/mizutu/Videos/video002.mp4
output. :
MODEL: FP16
DEVICE: MULTI:MYRIAD.3.4.1-ma2480,MYRIAD.3.4.3-ma2480,MYRIAD.3.4.4-ma2480
COMMAND: python3 person-tracking2.py -m_dt /home/mizutu/model/intel/FP16/person-detection-retail-0013.xml -m_re /home/mizutu/model/intel/FP16/person-reidentification-retail-0287.xml -d MULTI:MYRIAD.3.4.1-ma2480,MYRIAD.3.4.3-ma2480,MYRIAD.3.4.4-ma2480 -i /home/mizutu/Videos/video002.mp4
--- Person Tracking 2 ---
4.5.2-openvino
OpenVINO inference_engine: 2.1.2021.3.0-2787-60059f2c755-releases/2021/3
Person Tracking 2: Starting application...
- Image File : /home/mizutu/Videos/video002.mp4
- m_detect : /home/mizutu/model/intel/FP16/person-detection-retail-0013.xml
- m_redient. : /home/mizutu/model/intel/FP16/person-reidentification-retail-0287.xml
- Device : MULTI:MYRIAD.3.4.1-ma2480,MYRIAD.3.4.3-ma2480,MYRIAD.3.4.4-ma2480
- Threshold : 0.8
- Speed flag : y
- Processed out: non
/usr/lib/python3/dist-packages/apport/report.py:13: DeprecationWarning: the imp module is deprecated in favour of importlib; see the module's documentation for alternative uses
import fnmatch, glob, traceback, errno, sys, atexit, locale, imp, stat
/usr/lib/python3/dist-packages/requests/__init__.py:89: RequestsDependencyWarning: urllib3 (1.26.4) or chardet (3.0.4) doesn't match a supported version!
warnings.warn("urllib3 ({}) or chardet ({}) doesn't match a supported "
Traceback (most recent call last):
File "person-tracking2.py", line 381, in <module>
sys.exit(main())
File "person-tracking2.py", line 266, in main
personReidentification = PersonReidentification(model_reidentification, device, ie_core, detection_threshold, num_requests=2)
File "person-tracking2.py", line 112, in __init__
super().__init__(model_path, device, ie_core, num_requests, None)
File "/home/mizutu/workspace/demo/model.py", line 16, in __init__
self.exec_net = ie_core.load_network(network=self.net, device_name=device, num_requests=num_requests)
File "ie_api.pyx", line 336, in openvino.inference_engine.ie_api.IECore.load_network
File "ie_api.pyx", line 345, in openvino.inference_engine.ie_api.IECore.load_network
RuntimeError: Failed to compile layer "736": Unsupported combination of indices in layer "736". Only across channel and full batch supported.
$ cd ~/run_app2
$ source set_MYRIAD16_3X.sh
$ ./face-tracking2.sh
[face-tracking2.sh] face-tracking2.py Run !!
program : face-tracking2.py
model1. : -m_dt /home/mizutu/model/intel/FP16/face-detection-0200.xml
model2. : -m_re /home/mizutu/model/intel/FP16/face-reidentification-retail-0095.xml
device. : MULTI:MYRIAD.3.4.1-ma2480,MYRIAD.3.4.3-ma2480,MYRIAD.3.4.4-ma2480
input.. : -i /home/mizutu/Videos/video001.mp4
output. :
MODEL: FP16
DEVICE: MULTI:MYRIAD.3.4.1-ma2480,MYRIAD.3.4.3-ma2480,MYRIAD.3.4.4-ma2480
COMMAND: python3 face-tracking2.py -m_dt /home/mizutu/model/intel/FP16/face-detection-0200.xml -m_re /home/mizutu/model/intel/FP16/face-reidentification-retail-0095.xml -d MULTI:MYRIAD.3.4.1-ma2480,MYRIAD.3.4.3-ma2480,MYRIAD.3.4.4-ma2480 -i /home/mizutu/Videos/video001.mp4
--- Face Tracking 2 ---
4.5.2-openvino
OpenVINO inference_engine: 2.1.2021.3.0-2787-60059f2c755-releases/2021/3
Face Tracking 2: Starting application...
- Image File : /home/mizutu/Videos/video001.mp4
- m_detect : /home/mizutu/model/intel/FP16/face-detection-0200.xml
- m_redient. : /home/mizutu/model/intel/FP16/face-reidentification-retail-0095.xml
- Device : MULTI:MYRIAD.3.4.1-ma2480,MYRIAD.3.4.3-ma2480,MYRIAD.3.4.4-ma2480
- Threshold : 0.5
- Speed flag : y
- Processed out: non
:
-------------------
1.0 (239,47)-(262,76)
0.9 (142,54)-(165,85)
0.8 (180,88)-(207,124)
0.8 (197,60)-(216,84)
====================
input: 4 DB:6
persionId:4 0.44961090435362355 conf:0.95068359375
persionId:1 0.6732033333626466 conf:0.89208984375
persionId:0 0.6363589789472626 conf:0.833984375
persionId:5 0.5802160279984151 conf:0.82373046875
[4 1 0 5]
[4 1 0 5]
FPS average: 8.00
Finished.
| 項目 | ①1本 | ②2本 | ③3本 |
| fps | 8.40 | 8.00 | 8.00 |
$ cd ~/run_app2 $ source set_MYRIAD16_3X.sh $ ./sentiment_analysis2.sh [sentiment_analysis2.sh] sentiment_analysis2.py Run !! program : sentiment_analysis2.py model1. : -m_dt /home/mizutu/model/intel/FP16/face-detection-retail-0004.xml model2. : -m_re /home/mizutu/model/intel/FP16/emotions-recognition-retail-0003.xml device. : MULTI:MYRIAD.3.4.1-ma2480,MYRIAD.3.4.3-ma2480,MYRIAD.3.4.4-ma2480 input.. : -i /home/mizutu/Images/emo2.jpg output. : MODEL: FP16 DEVICE: MULTI:MYRIAD.3.4.1-ma2480,MYRIAD.3.4.3-ma2480,MYRIAD.3.4.4-ma2480 COMMAND: python3 sentiment_analysis2.py -m_dt /home/mizutu/model/intel/FP16/face-detection-retail-0004.xml -m_re /home/mizutu/model/intel/FP16/emotions-recognition-retail-0003.xml -d MULTI:MYRIAD.3.4.1-ma2480,MYRIAD.3.4.3-ma2480,MYRIAD.3.4.4-ma2480 -i /home/mizutu/Images/emo2.jpg --- Real-time sentiment analysis 2 --- 4.5.2-openvino OpenVINO inference_engine: 2.1.2021.3.0-2787-60059f2c755-releases/2021/3 Real-time sentiment analysis 2: Starting application... - Image File : /home/mizutu/Images/emo2.jpg - m_detect : /home/mizutu/model/intel/FP16/face-detection-retail-0004.xml - m_recognition: /home/mizutu/model/intel/FP16/emotions-recognition-retail-0003.xml - Device : MULTI:MYRIAD.3.4.1-ma2480,MYRIAD.3.4.3-ma2480,MYRIAD.3.4.4-ma2480 - Language : jp - Program Title: y - Speed flag : y - Processed out: non FPS average: 33.30 Finished.
| 項目 | ①1本 | ②2本 | ③3本 |
| fps | 29.90 | 32.60 | 33.30 |
$ cd ~/run_app2 $ source set_MYRIAD16_3X.sh $ ./image_classification.sh [image_classification.sh] image_classification.py Run !! program : image_classification.py model1. : -m /home/mizutu/model/public/FP16/squeezenet1.1.xml model2. : device. : MULTI:MYRIAD.3.4.1-ma2480,MYRIAD.3.4.3-ma2480,MYRIAD.3.4.4-ma2480 input.. : -i /home/mizutu/Images/cat.jpg output. : MODEL: FP16 DEVICE: MULTI:MYRIAD.3.4.1-ma2480,MYRIAD.3.4.3-ma2480,MYRIAD.3.4.4-ma2480 COMMAND: python3 image_classification.py -m /home/mizutu/model/public/FP16/squeezenet1.1.xml -i /home/mizutu/Images/cat.jpg -d MULTI:MYRIAD.3.4.1-ma2480,MYRIAD.3.4.3-ma2480,MYRIAD.3.4.4-ma2480 --- Image Classification --- 4.5.2-openvino OpenVINO inference_engine: 2.1.2021.3.0-2787-60059f2c755-releases/2021/3 Image Classification: Starting application... - Image File : /home/mizutu/Images/cat.jpg - Model : /home/mizutu/model/public/FP16/squeezenet1.1.xml - Device : MULTI:MYRIAD.3.4.1-ma2480,MYRIAD.3.4.3-ma2480,MYRIAD.3.4.4-ma2480 - Label : ./synset_words_jp.txt - Program Title: y - Speed flag : y - Processed out: non FPS average: 42.90 Finished.
| 項目 | ①1本 | ②2本 | ③3本 |
| fps | 46.00 | 48.70 | 42.90 |