OpenVINO13 - PukiWiki

OpenVINO™ Toolkit for Linux「Core™ i7-2620M」 †

　OpenVINO™ツールキットを手持ちのノートパソコンにインストールする。
　第2世代 CPU の実行速度の違いを調査する。

OpenVINO™ Toolkit for Linux「Core™ i7-2620M」
- 「OpenVINO™ Toolkit for Linux」のインストール
- OpenVINO™ ツールキットサンプルデモのインストール
Open Model Zoo Demos を動かす 3
参考資料

※ 最終更新:2021/04/16　

↑

「OpenVINO™ Toolkit for Linux」のインストール †

↑

事前準備 †

Hyper-V に ubuntu20.04.1 仮想マシンを構築
- 「クイック作成」を使用する。
  - オプション設定　ネットワークスイッチ
  - ローカルのisoファイル「ubuntu-20.04.1-desktop-amd64.iso」を指定する。
  - Windowsチェックを外す
  - ゲストサービスにチェックを入れる

ubuntu基本設定

言語サポート
日本語(Mozc)

インストール

sudo apt install openssh-server
sudo apt install net-tools

vi 設定

$ vi ~/.vimrc
set nocompatible
set backspace=indent,eol,start
set expandtab
set tabstop=4
set shiftwidth=4
set autoindent

拡張セッションで起動する。(解像度設定変更するため)
Hyper-V上で動くUbuntu 20.04LTSで拡張セッションを使うには

↑

OpenVINO™ Toolkit のダウンロード †

Intel® OpenVINO™ Toolkit Storage サイトからダウンロードする。
最新バージョンは「2021.3」(※2021/04/16) だが速度比較をするのでこれまでの「2021.2」版を使用する。
ダウンロードファイル「l_openvino_toolkit_p_2021.2.185.tgz」を~/ダウンロードフォルダに保存する。

↑

OpenVINO™ Toolkit のインストール †

オフィシャルサイトの手順に従ってインストール
　Install Intel® Distribution of OpenVINO™ toolkit for Linux*
以下の手順詳細は Windows10 Hyper-V 上の仮想マシンにインストールする参照。

ダウンロードされたパッケージを解凍
解凍したパッケージの中にあるインストーラを起動
依存関係の外部パッケージをインストール
環境変数の設定
Model Optimizer の設定
サンプルデモの実行１ demo_security_barrier_camera.sh
サンプルデモの実行２ demo_squeezenet_download_convert_run.sh
サンプルデモの実行３ demo_benchmark_app.sh
推論モデルファイルの一括ダウンロード
Pytorch をインストールする。

パブリックモデルの一括コンバート

$ python3 /opt/intel/openvino_2021/deployment_tools/tools/model_downloader/converter.py --all
    :

[ SUCCESS ] Total execution time: 52.05 seconds. 
[ SUCCESS ] Memory consumed: 1779 MB. 
It's been a while, check for a new version of Intel(R) Distribution of OpenVINO(TM) toolkit here https://software.intel.com/content/www/us/en/develop/tools/openvino-toolkit/choose-download.html?cid=other&source=Prod&campid=ww_2021_bu_IOTG&content=upg_pro&medium=organic_uid_agjj or on the GitHub*

FAILED:
brain-tumor-segmentation-0001
cocosnet
efficientnet-b5-pytorch
efficientnet-b7-pytorch
face-recognition-mobilefacenet-arcface
face-recognition-resnet100-arcface
face-recognition-resnet34-arcface
face-recognition-resnet50-arcface
googlenet-v3-pytorch
mobilefacedet-v1-mxnet
octave-densenet-121-0.125
octave-resnet-101-0.125
octave-resnet-200-0.125
octave-resnet-26-0.25
octave-resnet-50-0.125
octave-resnext-101-0.25
octave-resnext-50-0.25
octave-se-resnet-50-0.125
retinaface-anti-cov
retinaface-resnet50
vgg19-caffe2

　コンバートできないモデルは 21

学習済みモデルをまとめる。

↑

OpenVINO™ ツールキットサンプルデモのインストール †

　詳しくはここを参照。
　オフィシャルサイト Open Model Zoo Demos の手順で付属のデモを構築する。

python 拡張モジュールを構築する
- python のバージョン確認
```
mizutu@ubuntu2004dk:~$ python3 --version
python 3.8.5
```
- python3.8-dev のインストール
```
mizutu@ubuntu2004dk:~$ sudo apt install python3.8-dev
```
- 古い ~/omz_demos_build/ があれば削除しておく

新たにデモを python 拡張モジュールも含めてインストールする

$ cd /opt/intel/openvino_2021/deployment_tools/open_model_zoo/demos
$ ./build_demos.sh -DENABLE_PYTHON=ON

Setting environment variables for building demos...
[setupvars.sh] OpenVINO environment initialized
    :

[ 99%] Linking CXX executable ../intel64/Release/pedestrian_tracker_demo
[ 99%] Built target pedestrian_tracker_demo
[100%] Linking CXX executable ../intel64/Release/smart_classroom_demo
[100%] Built target smart_classroom_demo
Scanning dependencies of target ie_samples
[100%] Built target ie_samples

Build completed, you can find binaries for all demos in the /home/mizutu/omz_demos_build/intel64/Release subfolder.

デモソフトはカレントディレクトリ下の ~/omz_demos_build/intel64/Release/ に構築される。

ホームディレクトリにデモ実行環境設定のシェルスクリプトを作成する。

omz_demos.sh

#!/bin/sh

echo [OMZ_demos.sh] Open Model Zoo Demos environment initialized

export PYTHONPATH=$PYTHONPATH:/home/mizutu/omz_demos_build/intel64/Release/lib
export PYTHONPATH=$PYTHONPATH:/opt/intel/openvino_2021/deployment_tools/open_model_zoo/demos/python_demos/common

シェルを起動時に自動的に環境変数を設定するため「~/.bashrc」ファイルの最後に「source ~/omz_demos_python/omz_demos.sh」の1行を追記する。

学習済みモデルの場所
- ~/model/intel
- ~/model/pubkic

OpenVINO™ Toolkit に付属するデモソフト一覧

↑

Open Model Zoo Demos を動かす 3 †

「scipy」をインストールする

$ pip3 install scipy
Collecting scipy
  Downloading scipy-1.6.2-cp38-cp38-manylinux1_x86_64.whl (27.2 MB)
     |████████████████████████████████| 27.2 MB 11.8 MB/s 
Requirement already satisfied: numpy<1.23.0,>=1.16.5 in /usr/local/lib/python3.8/dist-packages (from scipy) (1.18.5)
Installing collected packages: scipy
Successfully installed scipy-1.6.2

↑

3D Human Pose Estimation Python* Demo †

↑

デモの実行 †

実行例「Ubuntu Core™ i7-2620M」

mizutu@ubuntu2004cf:~/omz_demos_python/python_demos/human_pose_estimation_3d_demo$ python3 human_pose_estimation_3d_demo.py -m ~/model/public/FP32/human-pose-estimation-3d-0001.xml -i ~/Videos/driver.mp4

↑

速度比較 †

項目	Core™ i5-10210	Hyper-V Core™ i7-6700	Celeron® J4005	Celeron® J4005 + NCS2	Hyper-v Core™ i7-2620M
fps	13.5	6.6	1.1	3.9	1.5

↑

Action Recognition Python* Demo †

↑

デモの実行 †

実行例「Ubuntu Core™ i7-2620M」

mizutu@ubuntu2004cf:~/omz_demos_python/python_demos/action_recognition$ python3 action_recognition.py -m_en ~/model/intel/FP32/driver-action-recognition-adas-0002-encoder.xml -m_de ~/model/intel/FP32/driver-action-recognition-adas-0002-decoder.xml -i ~/Videos/driver.mp4 -lb driver_actions.txt
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% -- 27.57ms
Frame 16: Safe driving - 87.28% -- 45.04ms
    :
    :
Frame 670: Safe driving - 92.34% -- 173.75ms
Frame 671: Safe driving - 92.72% -- 172.84ms
Frame 672: Safe driving - 93.25% -- 173.36ms
finishing <action_recognition_demo.steps.RenderStep object at 0x7fcc9f1ca940>
Frame 673: Safe driving - 93.71% -- 173.38ms
Data total: 1.56ms (+/-: 2.41) 642.36fps
Data   own: 1.55ms (+/-: 2.43) 645.63fps
Encoder total: 46.78ms (+/-: 12.45) 21.38fps
Encoder   own: 46.76ms (+/-: 12.45) 21.39fps
Decoder total: 126.39ms (+/-: 22.00) 7.91fps
Decoder   own: 126.37ms (+/-: 22.00) 7.91fps
Render total: 214.50ms (+/-: 88.67) 4.66fps
Render   own: 214.35ms (+/-: 88.58) 4.67fps

↑

速度比較 †

項目		Core™ i5-10210	Hyper-V Core™ i7-6700	Celeron® J4005	Celeron® J4005 + NCS2	Hyper-v Core™ i7-2620M
Data totai	fps	1152	146	99	84	642
Data totai	ms	0.87	10	10	12	1.56
Encoder total	fps	235	95	11	175	21.4
Encoder total	ms	4.3	10.5	91	5.7	46.8
Decoder total	fps	44	20	2.5	53	7.9
Decoder total	ms	23	50	400	19	126
Render total	fps	27	15	2.0	26.6	4.66
Render total	ms	37	67	494	38	215

↑

Object Detection Python* Demo †

↑

デモの実行 †

実行例「Ubuntu Core™ i7-2620M」

mizutu@ubuntu2004cf:~/omz_demos_python/python_demos/object_detection_demo$ python3 object_detection_demo.py -i ~/Videos/car_person.mp4 -m ~/model/intel/FP32/person-vehicle-bike-detection-crossroad-yolov3-1020.xml -at yolo
[ 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: 2623.0 ms
FPS: 0.4

↑

速度比較 †

項目	Core™ i5-10210	Hyper-V Core™ i7-6700	Celeron® J4005	Celeron® J4005 + NCS2	Hyper-v Core™ i7-2620M
Latency(ms)	219.2	431	6575	1515	2623
fps	4.5	2.5	0.2	1.9	0.4

↑

Human Pose Estimation Python* Demo †

↑

デモの実行 †

実行例「Ubuntu Core™ i7-2620M」

mizutu@ubuntu2004cf:~/omz_demos_python/python_demos/human_pose_estimation_demo$ python3 human_pose_estimation.py -i ~/Videos/driver.mp4 -m ~/model/intel/FP32/human-pose-estimation-0001.xml -at openpose -d CPU
[ INFO ] Initializing Inference Engine...
[ INFO ] Loading network...
[ INFO ] Using USER_SPECIFIED mode
[ INFO ] Reading network from IR...
[ INFO ] Loading network to plugin...
[ INFO ] Reading network from IR...
[ INFO ] Loading network to plugin...
[ INFO ] Starting inference...
To close the application, press 'CTRL+C' here or switch to the output window and press ESC key
To switch between min_latency/user_specified modes, press TAB key in the output window
[ INFO ] Using MIN_LATENCY mode
[ INFO ] Using USER_SPECIFIED mode
[ INFO ] 
[ INFO ] Mode: USER_SPECIFIED
[ INFO ] FPS: 1.9
[ INFO ] Latency: 534.2 ms
[ INFO ] 
[ INFO ] Mode: MIN_LATENCY
[ INFO ] FPS: 1.7
[ INFO ] Latency: 563.1 ms

↑

速度比較 †

項目		Core™ i5-10210	Hyper-V Core™ i7-6700	Celeron® J4005	Celeron® J4005 + NCS2	Hyper-v Core™ i7-2620M
USER_SPECIFIDE mode	FPS	17.3	9.2	1.2	0.5	1.9
USER_SPECIFIDE mode	Latency (ms)	44.1	104	714	236	534
MIN_LATENCY mode	FPS	19.9	9.5	1.2	3.9	1.7
MIN_LATENCY mode	Latency (ms)	48.1	101	701	236.5	563

↑

Gesture Recognition Python* Demo †

↑

デモの実行 †

実行例「Ubuntu Core™ i7-2620M」

mizutu@ubuntu2004cf:~/omz_demos_python/python_demos/gesture_recognition_demo$ python3 gesture_recognition_demo.py -m_a ~/model/intel/FP32/asl-recognition-0004.xml -m_d ~/model/intel/FP32/person-detection-asl-0001.xml -i ~/Videos/ASK_Please.mp4 -c ./msasl100-classes.json

mizutu@ubuntu2004cf:~/omz_demos_python/python_demos/gesture_recognition_demo$ python3 gesture_recognition_demo.py -m_a ~/model/intel/FP32/asl-recognition-0004.xml -m_d ~/model/intel/FP32/person-detection-asl-0001.xml -i ~/Videos/ASL_TankYou.mp4 -c ./msasl100-classes.json

↑

速度比較 †

項目	Core™ i5-10210	Hyper-V Core™ i7-6700	Celeron® J4005	Celeron® J4005 + NCS2	Hyper-v Core™ i7-2620M
fps	14.3	8.7	0.95	X	1.9
fps	14.5	8.8	0.94	X	1.9

↑

Handwritten Text Recognition Demo †

↑

デモの実行 †

実行例「Ubuntu Core™ i7-2620M」

mizutu@ubuntu2004cf:~/omz_demos_python/python_demos/handwritten_text_recognition_demo$ python3 handwritten_text_recognition_demo.py -i data/handwritten_japanese_test.png -m ~/model/intel/FP32/handwritten-japanese-recognition-0001.xml
[ 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: 2742.302179336548 ms

↑

速度比較 †

項目	Core™ i5-10210	Hyper-V Core™ i7-6700	Celeron® J4005	Celeron® J4005 + NCS2	Hyper-v Core™ i7-2620M
Average throughput(ms)	277	603	4353	866	2742

↑

Text Detection C++ Demo †

↑

デモの実行 †

実行例「Ubuntu Core™ i7-2620M」

mizutu@ubuntu2004cf:~/omz_demos_build/intel64/Release$ ./text_detection_demo -loop -m_td ~/model/intel/FP32/text-detection-0004.xml -m_tr ~/model/intel/FP32/text-recognition-0012.xml -i ~/Images/text-img.jpg
InferenceEngine: 	API version ......... 2.1
	Build ........... 2021.2.0-1877-176bdf51370-releases/2021/2
[ INFO ] Parsing input parameters
[ INFO ] Loading Inference Engine
[ INFO ] Device info: 
[ INFO ] 	CPU
	MKLDNNPlugin version ......... 2.1
	Build ........... 2021.2.0-1877-176bdf51370-releases/2021/2

[ 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): 1079.21 0.9266
text detection postprocessing (ms) (fps): 111.143 8.99743

text recognition model inference (ms) (fps): 77.3112 12.9347
text recognition postprocessing (ms) (fps): 0.0122959 81327.8

text crop (ms) (fps): 0.0832806 12007.6

↑

速度比較 †

項目		Core™ i5-10210	Hyper-V Core™ i7-6700	Celeron® J4005	Celeron® J4005 + NCS2	Hyper-v Core™ i7-2620M
detection model inference	ms	102	185	1154	685	1079
detection model inference	fps	9.8	5.4	0.87	1.46	0.93
detection model postprocessing	ms	40.4	69	148	154	111
detection model postprocessing	fps	24.7	14.4	6.76	6.50	9.0
recognition model inference	ms	7.1	14.6	103	76.0	77.3
recognition model inference	fps	140	68.7	9.70	13.2	12.9
recognition model postprocessing	ms	0.007	0.01	0.015	0.04	0.012
recognition model postprocessing	fps	136364	91731	63348	23160	81328

↑

Crossroad Camera C++ Demo †

↑

デモの実行 †

実行例「Ubuntu Core™ i7-2620M」

mizutu@ubuntu2004cf:~/omz_demos_build/intel64/Release$ ./crossroad_camera_demo -i ~/Videos/car.mp4 -m ~/model/intel/FP32/person-vehicle-bike-detection-crossroad-0078.xml
InferenceEngine: 	API version ......... 2.1
	Build ........... 2021.2.0-1877-176bdf51370-releases/2021/2
[ 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 ........... 2021.2.0-1877-176bdf51370-releases/2021/2

[ 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: 83333.4

[ INFO ] Execution successful

↑

速度比較 †

項目	Core™ i5-10210	Hyper-V Core™ i7-6700	Celeron® J4005	Celeron® J4005 + NCS2	Hyper-v Core™ i7-2620M
detection time(ms)	30	50.1	312.2	275.3	342
fps	32	14	3,1	3.6	3.0

↑

Human Pose Estimation C++ Demo †

↑

デモの実行 †

実行例「Ubuntu Core™ i7-2620M」

mizutu@ubuntu2004cf:~/omz_demos_build/intel64/Release$ ./human_pose_estimation_demo -i ~/Videos/driver.mp4 -m ~/model/intel/FP32/human-pose-estimation-0001.xml -d CPU
InferenceEngine: 	API version ......... 2.1
	Build ........... 2021.2.0-1877-176bdf51370-releases/2021/2
Parsing input parameters
To close the application, press 'CTRL+C' here or switch to the output window and press ESC key
To pause execution, switch to the output window and press 'p' key

Total Inference time: 411609

Execution successful

↑

速度比較 †

項目			Core™ i5-10210	Hyper-V Core™ i7-6700	Celeron® J4005	Celeron® J4005 + NCS2	Hyper-v Core™ i7-2620M
SYNC	OpwnCV cap/render time	ms	5	9.6	36	37	16.5
	Wallclock time	ms	45	100	710	248	510
	Wallclock time	fps	13	10	1.4	4.1	1.93
	Detection time	ms	45	95	677	205	503
	Detection time	fps	22	10	1.5	4.0	1.8
ASYNC	OpwnCV cap/render time	ms	9	14	69	36	28
	Wallclock time	ms	50	95	712	42	536
	Wallclock time	fps	19	10	1.4	24	2.0

↑

Object Detection C++ Demo †

↑

デモの実行 †

実行例「Ubuntu Core™ i7-2620M」

mizutu@ubuntu2004cf:~/omz_demos_build/intel64/Release$ ./object_detection_demo -i ~/Videos/video001.mp4 -at ssd -m ~/model/intel/FP32/person-detection-retail-0013.xml
[ INFO ] InferenceEngine: 	API version ......... 2.1
	Build ........... 2021.2.0-1877-176bdf51370-releases/2021/2
[ INFO ] Parsing input parameters
[ INFO ] Reading input
[ INFO ] Loading Inference Engine
[ INFO ] Device info: 
[ INFO ] 	CPU
	MKLDNNPlugin version ......... 2.1
	Build ........... 2021.2.0-1877-176bdf51370-releases/2021/2
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: 161.7 ms
FPS: 11.8
[ INFO ] 

[ INFO ] The execution has completed successfully

↑

速度比較 †

項目	Core™ i5-10210	Hyper-V Core™ i7-6700	Celeron® J4005	Celeron® J4005 + NCS2	Hyper-v Core™ i7-2620M
Latency(ms)	22	45	259.3	145.1	162
fps	73.0	42.3	7.5	13.0	11.8

↑

Smart Classroom C++ Demo †

↑

デモの実行 †

実行例「Ubuntu Core™ i7-2620M」

mizutu@ubuntu2004cf:~/omz_demos_build/intel64/Release$ ./smart_classroom_demo -m_act ~/model/intel/FP32/person-detection-action-recognition-0005.xml -m_fd ~/model/intel/FP32/face-detection-adas-0001.xml -i ~/Videos/classroom_s.mp4
[ INFO ] InferenceEngine: 	API version ......... 2.1
	Build ........... 2021.2.0-1877-176bdf51370-releases/2021/2
[ INFO ] Parsing input parameters
[ INFO ] Loading Inference Engine
[ INFO ] Device info: 
[ INFO ] 	CPU
	MKLDNNPlugin version ......... 2.1
	Build ........... 2021.2.0-1877-176bdf51370-releases/2021/2

[ 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: 2.32512
[ INFO ] Frames processed: 983

[ INFO ] Execution successful

↑

速度比較 †

項目	Core™ i5-10210	Hyper-V Core™ i7-6700	Celeron® J4005	Celeron® J4005 + NCS2	Hyper-v Core™ i7-2620M
fps	21	12	1	3	2.3

↑

Pedestrian Tracker C++ Demo †

↑

デモの実行 †

実行例「Ubuntu Core™ i7-2540M」

mizutu@ubuntu2004cf:~/omz_demos_build/intel64/Release$ ./pedestrian_tracker_demo -i ~/Videos/video003_m.mp4 -m_det ~/model/intel/FP32/person-detection-retail-0013.xml -m_reid ~/model/intel/FP32/person-reidentification-retail-0288.xml -d_det CPU
InferenceEngine: 	API version ......... 2.1
	Build ........... 2021.2.0-1877-176bdf51370-releases/2021/2
Loading device CPU
	CPU
	MKLDNNPlugin version ......... 2.1
	Build ........... 2021.2.0-1877-176bdf51370-releases/2021/2

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

Execution successful

↑

Super Resolution C++ Demo †

↑

デモの実行 †

実行例「Ubuntu Core™ i7-2620M」

mizutu@ubuntu2004cf:~/omz_demos_build/intel64/Release$ ./super_resolution_demo -i ~/Images/image-low.bmp -m ~/model/intel/FP32/single-image-super-resolution-1032.xml -show true
[ INFO ] InferenceEngine: 	API version ......... 2.1
	Build ........... 2021.2.0-1877-176bdf51370-releases/2021/2
[ 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 ........... 2021.2.0-1877-176bdf51370-releases/2021/2

[ 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 †

実行例「Ubuntu Core™ i7-2620M」

mizutu@ubuntu2004cf:~/omz_demos_python/python_demos/single_human_pose_estimation_demo$ python3 single_human_pose_estimation_demo.py --model_od ~/model/public/FP32/mobilenet-ssd.xml --model_hpe ~/model/public/FP32/single-human-pose-estimation-0001.xml --input ~/Videos/person_m.mp4

↑

速度比較 †

項目	Core™ i5-10210	Hyper-V Core™ i7-6700	Celeron® J4005	Celeron® J4005 + NCS2	Hyper-v Core™ i7-2620M
summary (fps)	0.9	0.7	0.1	0.5	0.2
estimation (fps)	5.6	2.4	0.3	1.6	0.5
detection (fps)	109.9	69.1	9.1	22.2	14.3

↑

Interactive Face Detection C++ Demo †

↑

デモの実行 †

実行例「Ubuntu Core™ i7-2620M」

mizutu@ubuntu2004cf:~/omz_demos_build/intel64/Release$ ./interactive_face_detection_demo -i ~/Videos/emotion2_m.mp4 -m ~/model/intel/FP32/face-detection-adas-0001.xml -m_ag ~/model/intel/FP32/age-gender-recognition-retail-0013.xml -m_hp ~/model/intel/FP32/head-pose-estimation-adas-0001.xml -m_em ~/model/intel/FP32/emotions-recognition-retail-0003.xml -m_lm ~/model/intel/FP32/facial-landmarks-35-adas-0002.xml -m_am ~/model/public/FP32/anti-spoof-mn3.xml -d CPU
InferenceEngine: 	API version ......... 2.1
	Build ........... 2021.2.0-1877-176bdf51370-releases/2021/2
[ INFO ] Parsing input parameters
[ INFO ] Loading device CPU
[ INFO ] 	CPU
	MKLDNNPlugin version ......... 2.1
	Build ........... 2021.2.0-1877-176bdf51370-releases/2021/2

[ 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: 275
[ INFO ] Total image throughput: 1.99915 fps

[ INFO ] Execution successful

↑

速度比較 †

項目	Core™ i5-10210	Hyper-V Core™ i7-6700	Celeron® J4005	Celeron® J4005 + NCS2	Hyper-v Core™ i7-2620M
throughput (fps)	19.3	9.16	0.45	0.6	1.9

↑

Gaze Estimation Demo †

↑

デモの実行 †

実行例「Ubuntu Core™ i7-2620M」

mizutu@ubuntu2004cf:~/omz_demos_build/intel64/Release$ ./gaze_estimation_demo -i ~/Videos/emotion2_m.mp4  -m ~/model/intel/FP32/gaze-estimation-adas-0002.xml -m_fd ~/model/intel/FP32/face-detection-retail-0004.xml -m_hp ~/model/intel/FP32/head-pose-estimation-adas-0001.xml -m_lm ~/model/intel/FP32/facial-landmarks-35-adas-0002.xml -m_es ~/model/public/FP32/open-closed-eye-0001.xml
InferenceEngine: 	API version ......... 2.1
	Build ........... 2021.2.0-1877-176bdf51370-releases/2021/2
[ INFO ] Parsing input parameters
[ INFO ] Loading device CPU
[ INFO ] 	CPU
	MKLDNNPlugin version ......... 2.1
	Build ........... 2021.2.0-1877-176bdf51370-releases/2021/2


[ INFO ] Execution successful

↑

速度比較 †

項目	Core™ i5-10210	Hyper-V Core™ i7-6700	Celeron® J4005	Celeron® J4005 + NCS2	Hyper-v Core™ i7-2620M
Overeli (fps)	110	63	5	5	14
Interface (fps)	202	106	5	7	16

↑

Security Barrier Camera C++ Demo †

↑

デモの実行 †

実行例「Ubuntu Core™ i7-2620M」

mizutu@ubuntu2004cf:~/omz_demos_build/intel64/Release$ ./security_barrier_camera_demo -i ~/Videos/car-detection.mp4 -m ~/model/intel/FP32/vehicle-license-plate-detection-barrier-0106.xml -m_va ~/model/intel/FP32/vehicle-attributes-recognition-barrier-0039.xml -m_lpr ~/model/intel/FP32/license-plate-recognition-barrier-0001.xml -d CPU
[ INFO ] InferenceEngine: 	API version ......... 2.1
	Build ........... 2021.2.0-1877-176bdf51370-releases/2021/2
[ INFO ] Files were added: 1
[ INFO ]     /home/mizutu/Videos/car-detection.mp4
[ INFO ] Loading device CPU
[ INFO ] 	CPU
	MKLDNNPlugin version ......... 2.1
	Build ........... 2021.2.0-1877-176bdf51370-releases/2021/2

[ 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 ] 1 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
25.9FPS for (375 / 1) frames
Detection InferRequests usage: 100.0%

[ INFO ] Execution successful

↑

速度比較 †

項目	Core™ i5-10210	Hyper-V Core™ i7-6700	Celeron® J4005	Celeron® J4005 + NCS2	Hyper-v Core™ i7-2620M
fps	164.5	106	11.7	24.7	25.9

↑

テスト環境 †

Intel® NUC キット BXNUC10I5FNH
- CPU Intel® Core™ i5-10210U CPU
- OS Ubuntu20.04LTS
- OpenVINO™ Toolkit for Linux 2021.2

HP EliteDesk 800 G2 SFF
- CPU Intel® Core™ i7-6700 CPU @ 3.40GHz
- OS Ubuntu20.04LTS (Hyper-V on Windows 10 Pro 64 bit)
- OpenVINO™ Toolkit for Linux 2021.2

Intel® NUC キット BOXNUC7CJYH
- CPU Intel® Celeron® J4005 Processor (4M Cache, up to 2.70 GHz)
- OS Ubuntu20.04LTS
- OpenVINO™ Toolkit for Linux 2021.2

Panasonic CF-B10BWJYS
- CPU Intel® Core™ i7-2620M vPro CPU @ 2.60GHz
- OS Ubuntu20.04LTS (Hyper-V on Windows 10 Pro 64 bit)
- OpenVINO™ Toolkit for Linux 2021.2

↑

更新履歴 †

2021/04/16 初版

↑

参考資料 †

オフィシャルサイト

最新の20件

OpenVINO™ Toolkit for Linux「Core™ i7-2620M」 †

「OpenVINO™ Toolkit for Linux」のインストール †

事前準備 †

OpenVINO™ Toolkit のダウンロード †

OpenVINO™ Toolkit のインストール †

OpenVINO™ ツールキット サンプルデモのインストール †

Open Model Zoo Demos を動かす 3 †

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 †

更新履歴 †

参考資料 †

OpenVINO™ ツールキットサンプルデモのインストール †