OpenVINO15

最新の20件

私的AI研究会 > OpenVINO15

OpenVINO™ Toolkit for Linux on VirtualBox †

　OpenVINO™ツールキットの最新版「2021.3」を「Core™ i7-2620M」VirtualBox 上の ubuntu20.04 にインストールする。
　VirtualBox は USB デバイスを使用できるので、Windows10 上の Ununtu 仮想マシンでソフトウェアの動作を確認する。

「OpenVINO™ Toolkit for Linux 2021.3」のインストール †

事前準備 †

• Virtual Box に ubuntu20.04.1 仮想マシンを構築
  • 仮想マシンを「新規」作成する。
    • ネットワーク設定で「ブリッジアダプター」を指定。
      
    • 「起動」ボタンを押しローカルのisoファイル「ubuntu-20.04.2-desktop-amd64.iso」を指定する。
    • ubuntu20.04 をインストールする。
      
• 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

  • sudo 付きでの vi 対応
    sudo 付きで vi を実行した場合は、root の設定が使用されるので、rootの .vimrcを ~/vimrc のシンボリックリンクにする。
    

    $ sudo ln -s ~/.vimrc /root/.vimrc
    $ sudo ls -la /root
    合計 24
    drwx------  4 root root 4096  3月 19 05:34 .
    drwxr-xr-x 21 root root 4096  3月 19 04:49 ..
    -rw-r--r--  1 root root  570  9月  9  2019 .bashrc
    drwx------  2 root root 4096  9月 26 09:13 .cache
    -rw-r--r--  1 root root  148  9月  9  2019 .profile
    lrwxrwxrwx  1 root root   15  3月 19 05:34 .vimrc -> /home/pi/.vimrc
    drwx------  3 root root 4096  3月 17 15:37 .vnc

OpenVINO™ Toolkit のダウンロード †

　Intel® のオフィシャルサイトが確実。(最新版が入手できる)

• Get the Intel® Distribution of OpenVINO™ Toolkit
• 最新バージョンは「2021.3」(※2021/04/23)
  
• ダウンロードファイル「l_openvino_toolkit_p_2021.3.394.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。
  

1. ダウンロードされたパッケージを解凍
   

   $ tar -xvzf l_openvino_toolkit_p_2021.3.394.tgz

2. 解凍したパッケージの中にあるインストーラを起動
   

   $ cd l_openvino_toolkit_p_2021.3.394
   $ sudo ./install_GUI.sh

3. 依存関係の外部パッケージをインストール

   $ cd /opt/intel/openvino_2021/install_dependencies
   $ sudo -E ./install_openvino_dependencies.sh

4. 環境変数の設定

   $ source /opt/intel/openvino_2021/bin/setupvars.sh
   [setupvars.sh] OpenVINO environment initialized

   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 /opt/intel/openvino_2021/bin/setupvars.sh」の1行を追記する。
   
   
5. Model Optimizer の設定

   $ cd /opt/intel/openvino_2021/deployment_tools/model_optimizer/install_prerequisites
   $ sudo ./install_prerequisites.sh

6. Pytorch をインストール (オフィシャルサイトに記述はないがあとで必要になるので..)
   オフィシャルサイト PyTorch FROM RESEARCH TO PRODUCTION にアクセスして、インストールパラメータを取得する。
   
   

   pip install torch==1.8.0+cpu torchvision==0.9.0+cpu torchaudio==0.8.0 -f https://download.pytorch.org/whl/torch_stable.html

   $ pip3 install torch==1.8.1+cpu torchvision==0.9.1+cpu torchaudio==0.8.1 -f https://download.pytorch.org/whl/torch_stable.html
   Defaulting to user installation because normal site-packages is not writeable
   Looking in links: https://download.pytorch.org/whl/torch_stable.html
   Collecting torch==1.8.1+cpu
     Downloading https://download.pytorch.org/whl/cpu/torch-1.8.1%2Bcpu-cp38-cp38-linux_x86_64.whl (169.1 MB)
        |████████████████████████████████| 169.1 MB 4.4 kB/s 
   Collecting torchvision==0.9.1+cpu
     Downloading https://download.pytorch.org/whl/cpu/torchvision-0.9.1%2Bcpu-cp38-cp38-linux_x86_64.whl (13.3 MB)
        |████████████████████████████████| 13.3 MB 5.0 MB/s 
   Collecting torchaudio==0.8.1
     Downloading torchaudio-0.8.1-cp38-cp38-manylinux1_x86_64.whl (1.9 MB)
        |████████████████████████████████| 1.9 MB 1.5 MB/s 
   Requirement already satisfied: numpy in /usr/local/lib/python3.8/dist-packages (from torch==1.8.1+cpu) (1.18.5)
   Requirement already satisfied: typing-extensions in /usr/local/lib/python3.8/dist-packages (from torch==1.8.1+cpu) (3.7.4.3)
   Requirement already satisfied: pillow>=4.1.1 in /usr/lib/python3/dist-packages (from torchvision==0.9.1+cpu) (7.0.0)
   Installing collected packages: torch, torchvision, torchaudio
     WARNING: The scripts convert-caffe2-to-onnx and convert-onnx-to-caffe2 are installed in '/home/mizutu/.local/bin' which is not on PATH.
     Consider adding this directory to PATH or, if you prefer to suppress this warning, use --no-warn-script-location.
   Successfully installed torch-1.8.1+cpu torchaudio-0.8.1 torchvision-0.9.1+cpu

7. scipy をインストール (オフィシャルサイトに記述はないがあとで必要になるので..)
   

   $ pip3 install scipy
   Defaulting to user installation because normal site-packages is not writeable
   Collecting scipy
     Downloading scipy-1.6.2-cp38-cp38-manylinux1_x86_64.whl (27.2 MB)
        |████████████████████████████████| 27.2 MB 434 kB/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

8. Neural Compute Stick 2 (NCS2) の設定
   

   $ sudo usermod -a -G users "$(whoami)"
   
   $ sudo cp /opt/intel/openvino_2021/inference_engine/external/97-myriad-usbboot.rules /etc/udev/rules.d/
   $ sudo udevadm control --reload-rules
   $ sudo udevadm trigger
   $ sudo ldconfig

   1. システムを再起動する。
      
   2. VirtualBox の USBデバイスで「Miriad...」をチェックしておく。
      
   3. 設定確認
      

      $ lsusb
      Bus 001 Device 002: ID 03e7:2485 Intel Movidius MyriadX
      Bus 001 Device 001: ID 1d6b:0002 Linux Foundation 2.0 root hub
      Bus 002 Device 002: ID 80ee:0021 VirtualBox USB Tablet
      Bus 002 Device 001: ID 1d6b:0001 Linux Foundation 1.1 root hub
      $ id mizutu
      uid=1000(mizutu) gid=1000(mizutu) groups=1000(mizutu),4(adm),24(cdrom),27(sudo),30(dip),46(plugdev),100(users),120(lpadmin),131(lxd),132(sambashare)

9. サンプルデモの実行１ demo_security_barrier_camera.sh
   

   $ cd /opt/intel/openvino_2021/deployment_tools/demo
   $ ./demo_security_barrier_camera.sh

10. サンプルデモの実行２ demo_squeezenet_download_convert_run.sh
    

    $ ./demo_squeezenet_download_convert_run.sh

11. サンプルデモの実行３ demo_benchmark_app.sh
    

    $ ./demo_benchmark_app.sh

12. ディスク使用量の確認
    

    $ df -h
    Filesystem      Size  Used Avail Use% Mounted on
    udev            965M     0  965M   0% /dev
    tmpfs           199M  1.4M  198M   1% /run
    /dev/sda5       251G   15G  224G   7% /
    tmpfs           994M     0  994M   0% /dev/shm
    tmpfs           5.0M  4.0K  5.0M   1% /run/lock
    tmpfs           994M     0  994M   0% /sys/fs/cgroup
    /dev/loop0       56M   56M     0 100% /snap/core18/1988
    /dev/loop1      219M  219M     0 100% /snap/gnome-3-34-1804/66
    /dev/loop2       65M   65M     0 100% /snap/gtk-common-themes/1514
    /dev/loop3       52M   52M     0 100% /snap/snap-store/518
    /dev/loop4       32M   32M     0 100% /snap/snapd/11036
    /dev/sda1       511M  4.0K  511M   1% /boot/efi
    tmpfs           199M   24K  199M   1% /run/user/1000

    およそ 15GB を使用しているよう。
    
    
13. 推論モデルファイルの一括ダウンロード (すでに別マシンで処理済みの場合は省略..)
    時間がかかる処理。(今回およそ1時間)
    

    $ cd ~/openvino_models
    $ python3 /opt/intel/openvino_2021/deployment_tools/tools/model_downloader/downloader.py --all

    ダウンロードされたモデルは、./public ./intel ディレクトリ配下に格納される。
    
14. パブリックモデルの一括コンバート (すでに別マシンで処理済みの場合は省略..)
    時間がかかる処理。(今回およそ2.5時間)
    

    $ python3 /opt/intel/openvino_2021/deployment_tools/tools/model_downloader/converter.py --all
        :
    
    [ SUCCESS ] Total execution time: 32.49 seconds. 
    [ SUCCESS ] Memory consumed: 1783 MB. 
    
    FAILED:
    cocosnet
    efficientdet-d0-tf
    efficientdet-d1-tf
    googlenet-v3-pytorch
    regnetx-3.2gf
    rexnet-v1-x1.0

    　コンバートできないモデルは 6
    
    
15. 学習済みモデルをまとめる。 (すでに別マシンで処理済みの場合はコピー..)
    このままではアクセスしにくいので、出来上がったIRモデルをディレクトリ「~/model」に移動する。
    

    ~/model/intel/FP16
    ~/model/intel/FP32
    ~/model/public/FP16
    ~/model/public/FP32

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。

• 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

  C++ デモソフトは ~/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_build/omz_demos.sh
  
  #!/bin/sh
  
  echo [OMZ_demos.sh] Open Model Zoo Demos environment initialized
  
  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_build/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 †

オリジナル・ソースの場所 /opt/intel/openvino_2021/deployment_tools/open_model_zoo/demos
↓↓↓↓「2021.3」　　　　　　　　　　　　　　　　　　　　　　↓↓↓↓「2021.2」と同じ構成のディレクトリにコピー
├── 3d_segmentation_demo
│   └── python >>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>> ~/omz_demos_python/python_demos/3d_segmentation_demo/
├── action_recognition_demo
│   └── python >>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>> ~/omz_demos_python/python_demos/action_recognition/
│       └── action_recognition_demo
├── bert_question_answering_demo
│   └── python >>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>> ~/omz_demos_python/python_demos/bert_question_answering_demo/
├── bert_question_answering_embedding_demo
│   └── python >>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>> ~/omz_demos_python/python_demos/bert_question_answering_embedding_demo/
├── classification_demo
│   └── cpp -------------------------------------------- ~/omz_demos_build/intel64/Release
├── colorization_demo
│   └── python >>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>> ~/omz_demos_python/python_demos/colorization_demo/
├── common
│   ├── cpp
│   │   ├── models
│   │   │   ├── include
│   │   │   │   └── models
│   │   │   └── src
│   │   ├── monitors
│   │   │   ├── include
│   │   │   │   └── monitors
│   │   │   └── src
│   │   ├── pipelines
│   │   │   ├── include
│   │   │   │   └── pipelines
│   │   │   └── src
│   │   └── utils
│   │       ├── include
│   │       │   └── utils
│   │       └── src
│   └── python >>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>> ~/omz_demos_python/python_demos/common/
│       ├── models
│       ├── monitors_extension
│       └── pipelines
├── crossroad_camera_demo
│   └── cpp -------------------------------------------- ~/omz_demos_build/intel64/Release
├── deblurring_demo
│   └── python xxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxx (2021.3 にはない)
├── face_detection_mtcnn_demo
│   └── python xxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxx (2021.3 にはない)
├── formula_recognition_demo
│   └── python >>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>> ~/omz_demos_python/python_demos/formula_recognition_demo/
├── gaze_estimation_demo
│   └── cpp -------------------------------------------- ~/omz_demos_build/intel64/Release
│       ├── include
│       └── src
├── gesture_recognition_demo
│   └── python >>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>> ~/omz_demos_python/python_demos/gesture_recognition_demo/
│       └── gesture_recognition_demo
├── handwritten_text_recognition_demo
│   └── python >>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>> ~/omz_demos_python/python_demos/handwritten_text_recognition_demo/
│       ├── data
│       └── utils
├── human_pose_estimation_3d_demo
│   └── python >>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>> ~/omz_demos_python/python_demos/human_pose_estimation_3d_demo
│       ├── data
│       ├── modules
│       └── pose_extractor
│           └── src
├── human_pose_estimation_demo
│   ├── cpp -------------------------------------------- ~/omz_demos_build/intel64/Release
│   └── python >>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>> ~/omz_demos_python/python_demos/human_pose_estimation_demo/
├── image_inpainting_demo
│   └── python >>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>> ~/omz_demos_python/python_demos/image_inpainting_demo/
├── image_retrieval_demo
│   └── python >>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>> ~/omz_demos_python/python_demos/image_retrieval_demo/
│       └── image_retrieval_demo
│           └── roi_cv_detector
├── image_translation_demo 
│   └── python >>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>> ~/omz_demos_python/python_demos/image_translation_demo/
│       └── image_translation_demo
├── instance_segmentation_demo
│   └── python >>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>> ~/omz_demos_python/python_demos/instance_segmentation_demo/
│       └── instance_segmentation_demo
├── interactive_face_detection_demo
│   ├── cpp -------------------------------------------- ~/omz_demos_build/intel64/Release
│   └── cpp_gapi --------------------------------------- ~/omz_demos_build/intel64/Release (2021.2 にはない)
├── machine_translation_demo
│   └── python >>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>> ~/omz_demos_python/python_demos/machine_translation_demo/
├── mask_rcnn_demo
│   └── cpp -------------------------------------------- ~/omz_demos_build/intel64/Release
├── monodepth_demo
│   └── python >>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>> ~/omz_demos_python/python_demos/monodepth_demo/
├── multi_camera_multi_target_tracking_demo
│   └── python >>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>> ~/omz_demos_python/python_demos/multi_camera_multi_target_tracking_demo/
│       ├── configs
│       ├── mc_tracker
│       └── utils
├── multi_channel_common
│   └── cpp
│       └── multicam
├── multi_channel_face_detection_demo
│   └── cpp -------------------------------------------- ~/omz_demos_build/intel64/Release
├── multi_channel_human_pose_estimation_demo
│   └── cpp -------------------------------------------- ~/omz_demos_build/intel64/Release
├── multi_channel_object_detection_demo_yolov3
│   └── cpp -------------------------------------------- ~/omz_demos_build/intel64/Release
├── object_detection_demo
│   ├── cpp -------------------------------------------- ~/omz_demos_build/intel64/Release
│   └── python >>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>> ~/omz_demos_python/python_demos/object_detection_demo/
├── pedestrian_tracker_demo
│   └── cpp -------------------------------------------- ~/omz_demos_build/intel64/Release
│       ├── include
│       └── src
├── place_recognition_demo
│   └── python xxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxx (2021.3 にはない)
│       └── place_recognition_demo
├── security_barrier_camera_demo
│   └── cpp -------------------------------------------- ~/omz_demos_build/intel64/Release
├── segmentation_demo
│   ├── cpp -------------------------------------------- ~/omz_demos_build/intel64/Release
│   └── python >>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>> ~/omz_demos_python/python_demos/segmentation_demo/
├── single_human_pose_estimation_demo
│   └── python >>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>> ~/omz_demos_python/python_demos/single_human_pose_estimation_demo/
├── smart_classroom_demo
│   └── cpp -------------------------------------------- ~/omz_demos_build/intel64/Release
│       ├── include
│       └── src
├── sound_classification_demo
│   └── python >>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>> ~/omz_demos_python/python_demos/sound_classification_demo/
├── speech_recognition_demo
│   └── python >>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>> ~/omz_demos_python/python_demos/speech_recognition_demo/
│       ├── ctcdecode-numpy
│       │   ├── ctcdecode_numpy
│       │   │   └── yoklm
│       │   └── third_party
│       │       └── ThreadPool
│       └── utils
├── super_resolution_demo
│   └── cpp -------------------------------------------- ~/omz_demos_build/intel64/Release
├── text_detection_demo
│   └── cpp -------------------------------------------- ~/omz_demos_build/intel64/Release
│       ├── include
│       └── src
├── text_spotting_demo
│   └── python >>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>> ~/omz_demos_python/python_demos/text_spotting_demo/
│       └── text_spotting_demo
├── text_to_speech_demo
│   └── python >>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>> ~/omz_demos_python/python_demos/text_to_speech_demo/
│       ├── models
│       └── utils
├── thirdparty
│   └── gflags
│       ├── bazel
│       ├── cmake
│       ├── src
│       └── test
│           ├── config
│           └── nc
└── whiteboard_inpainting_demo
    └── python >>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>> ~/omz_demos_python/python_demos/whiteboard_inpainting_demo/
        └── utils

153 directories

• python プログラムのデモソフトの場所が「2021.2」と異なっている。
  
• c++ のプログラムは「2021.2」と同じくスクリプトにより~/omz_demos_build フォルダ内に展開される・
• 参考：OpenVINO™ Toolkit「2021.2」に付属するデモソフト一覧

Neural Compute Stick 2 (NCS2) エラー †

　Virtual Box 上の ubuntu で　MYRIAD (NCS2) デバイスを使用するアプリケーションで下記エラーとなる。

[ ERROR ] Can not init Myriad device: NC_ERROR

• インテルのコミュニティ・サイト を参考に対処する。
  
  
  • 仮想マシンをシャットダウンする。
    
  • VirtualBox Manager を開く。
    
  • Open Settings -> USB (remove all usb from host)
  • Check “Enable USB Controller”
  • Check “USB 3.0 (xHCI) Controller”
  • Add a new USB filter with Vendor ID: 03e7
  • The other filter fields can be blank.
  • Add a new USB filter with Vendor ID: 040e
  • The other filter fields can be blank.
• アプリケーション実行例 (メガネ・帽子 バーチャル試着アプリケーション)
  NCS2 と Webカメラを接続して使用。
  
  

  $ ./virtual_fitting_16.sh 0 cam
  [virtual_fitting_16.sh] virtual_Fitting.py (MYRIAD) 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. : MYRIAD
  input.. : -i cam
  output. :
  
  ---  Virtual Fitting ---
  4.5.2-openvino
  OpenVINO inference_engine: 2.1.2021.3.0-2787-60059f2c755-releases/2021/3
  
  virtual_fitting.py:145: 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   :  0
     - 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       :  MYRIAD
     - Program Title:  y
     - Processed out:  non
  
   Finished.

   

Open Model Zoo Demos を動かす †

3D Human Pose Estimation Python* Demo †

デモの実行 †

• 実行例「Ubuntu on VirtualBox Core™ i7-2620M」

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

• 実行例「Ubuntu on VirtualBox Core™ i7-2620M」+ NCS2

  $ cd ~/run_app/
  $ ./_human_pose_estimation_3d_demo_16.sh 
  [human_pose_estimation_3d_demo_16.sh] 'human_pose_estimation_3d_demo_16' Run !!

速度比較 †

Action Recognition Python* Demo †

デモの実行 †

• 実行例「Ubuntu on VirtualBox Core™ i7-2620M」

  $ cd ~/run_app/
  $ ./_action_recognition.sh 
  [action_recognition.sh] 'action_recognition' 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% -- 82.12ms
  Frame 16: Safe driving - 87.28% -- 118.02ms
      :
      :
  Frame 41: Safe driving - 92.75% -- 264.68ms
  Frame 42: Safe driving - 93.13% -- 261.15ms
  finishing <action_recognition_demo.steps.RenderStep object at 0x7f6eb5b63f40>
  Data total: 8.23ms (+/-: 6.66) 121.57fps
  Data   own: 8.08ms (+/-: 6.70) 123.78fps
  Encoder total: 118.25ms (+/-: 32.23) 8.46fps
  Encoder   own: 118.23ms (+/-: 32.23) 8.46fps
  Decoder total: 99.95ms (+/-: 64.47) 10.00fps
  Decoder   own: 99.94ms (+/-: 64.47) 10.01fps
  Render total: 312.67ms (+/-: 165.61) 3.20fps
  Render   own: 312.15ms (+/-: 155.97) 3.20fps

• 実行例「Ubuntu on VirtualBox Core™ i7-2620M」+ NCS2

  $ cd ~/run_app/
  $ ./_action_recognition_16.sh 
  [action_recognition_16.sh] 'action_recognition (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% -- 22.77ms
  Frame 16: Safe driving - 86.75% -- 33.15ms
      :
      :
  Frame 260: Safe driving - 77.23% -- 42.88ms
  Frame 261: Safe driving - 76.42% -- 41.39ms
  finishing <action_recognition_demo.steps.RenderStep object at 0x7ff7df8a9160>
  Data total: 13.30ms (+/-: 11.29) 75.18fps
  Data   own: 13.21ms (+/-: 11.33) 75.70fps
  Encoder total: 17.03ms (+/-: 8.29) 58.70fps
  Encoder   own: 16.95ms (+/-: 8.25) 58.99fps
  Decoder total: 29.80ms (+/-: 16.25) 33.56fps
  Decoder   own: 29.77ms (+/-: 16.25) 33.59fps
  Render total: 102.85ms (+/-: 101.24) 9.72fps
  Render   own: 101.92ms (+/-: 98.33) 9.81fps

速度比較 †

Object Detection Python* Demo †

デモの実行 †

• 実行例「Ubuntu on VirtualBox Core™ i7-2620M」

  $ 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: 3010.5 ms
  FPS: 0.3

• 実行例「Ubuntu on VirtualBox Core™ i7-2620M」+ NCS2

  $ cd ~/run_app/
  $ ./_object_detection_python_demo_16.sh 
  [object_detection_demo/_16.sh] 'object_detection_demo (NCS_)' 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: 866.9 ms
  FPS: 1.1

速度比較 †

Human Pose Estimation Python* Demo †

デモの実行 †

• 実行例「Ubuntu on VirtualBox Core™ i7-2620M」

  $ cd ~/run_app/
  $ ./_human_pose_estimation.sh 
  [human_pose_estimation.sh] 'human_pose_estimation' Run !!
  [ 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 ] 
  [ INFO ] Mode: USER_SPECIFIED
  [ INFO ] FPS: 1.4
  [ INFO ] Latency: 590.5 ms
  [ INFO ] 
  [ INFO ] Mode: MIN_LATENCY
  [ INFO ] FPS: 1.7
  [ INFO ] Latency: 560.6 ms

• 実行例「Ubuntu on VirtualBox Core™ i7-2620M」+ NCS2

  $ cd ~/run_app/
  $ ./_human_pose_estimation_16.sh 
  [human_pose_estimation_16.sh] 'human_pose_estimation (NCS2)' Run !!
  python3 human_pose_estimation.py -i /home/mizutu/Videos/driver.mp4 -m /home/mizutu/model/intel/FP16/human-pose-estimation-0001.xml -at openpose -d MYRIAD -loop 50
  [ 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 ] 
  [ INFO ] Mode: USER_SPECIFIED
  [ INFO ] FPS: 0.7
  [ INFO ] Latency: 345.1 ms
  [ INFO ] 
  [ INFO ] Mode: MIN_LATENCY
  [ INFO ] FPS: 2.7
  [ INFO ] Latency: 346.8 ms

速度比較 †

Gesture Recognition Python* Demo †

デモの実行 †

• 実行例「Ubuntu on VirtualBox Core™ i7-2620M」

  $ cd ~/run_app/
  $ ./_gesture_recognition_demo.sh 
  [gesture_recognition_demo.sh] 'gesture_recognition_demo' Run !!
  
  Traceback (most recent call last):
    File "/usr/lib/python3.8/multiprocessing/queues.py", line 245, in _feed
      send_bytes(obj)
    File "/usr/lib/python3.8/multiprocessing/connection.py", line 200, in send_bytes
      self._send_bytes(m[offset:offset + size])
    File "/usr/lib/python3.8/multiprocessing/connection.py", line 405, in _send_bytes
      self._send(buf)
    File "/usr/lib/python3.8/multiprocessing/connection.py", line 368, in _send
      n = write(self._handle, buf)
  BrokenPipeError: [Errno 32] Broken pipe

速度比較 †

Handwritten Text Recognition Demo †

デモの実行 †

• 実行例「Ubuntu on VirtualBox Core™ i7-2620M」

  $ 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: 2787.7955436706543 ms

• 実行例「Ubuntu on VirtualBox Core™ i7-2620M」+ NCS2

  $ cd ~/run_app/
  $ ./_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: 1195.0263977050781 ms

速度比較 †

Text Detection C++ Demo †

デモの実行 †

• 実行例「Ubuntu on VirtualBox Core™ i7-2620M」

  $ 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): 1421.88 0.703297
  text detection postprocessing (ms) (fps): 160.75 6.22084
  
  text recognition model inference (ms) (fps): 79.1827 12.629
  text recognition postprocessing (ms) (fps): 0.0354231 28230.2
  
  text crop (ms) (fps): 0.137048 7296.71

• 実行例「Ubuntu on VirtualBox Core™ i7-2620M」+ 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 ] 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): 1274.89 0.784382
  text detection postprocessing (ms) (fps): 225.333 4.43787
  
  text recognition model inference (ms) (fps): 78.7259 12.7023
  text recognition postprocessing (ms) (fps): 0.0341704 29265.1
  
  text crop (ms) (fps): 0.162741 6144.74

速度比較 †

Crossroad Camera C++ Demo †

デモの実行 †

• 実行例「Ubuntu on VirtualBox Core™ i7-2620M」

  $ 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
  ^C

• 実行例「Ubuntu on VirtualBox Core™ i7-2620M」+ 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
  ^C

速度比較 †

Human Pose Estimation C++ Demo †

デモの実行 †

• 実行例「Ubuntu on VirtualBox Core™ i7-2620M」

  $ cd ~/run_app/
  $ ./_human_pose_estimation_demo.sh 
  [human_pose_estimation_demo.sh] 'human_pose_estimation_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 ] Loading model to the device
  
  [ INFO ] Metric reports:
  Latency: 1209.3 ms
  FPS: 1.6
  [ INFO ] 
  
  [ INFO ] The execution has completed successfully

• 実行例「Ubuntu on VirtualBox Core™ i7-2620M」+ NCS2

  $ cd ~/run_app/
  $ ./_human_pose_estimation_demo_16.sh 
  [human_pose_estimation_demo_16.sh] 'human_pose_estimation_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 ] Loading model to the device
  
  [ INFO ] Metric reports:
  Latency: 591.5 ms
  FPS: 7.5
  [ INFO ] 
  
  [ INFO ] The execution has completed successfully

速度比較 †

　※「2021.3」で変更あり。比較データ無し。

Object Detection C++ Demo †

デモの実行 †

• 実行例「Ubuntu on VirtualBox Core™ i7-2620M」

  $ 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: 297.2 ms
  FPS: 6.1
  [ INFO ] 
  
  [ INFO ] The execution has completed successfully

• 実行例「Ubuntu on VirtualBox Core™ i7-2620M」+ 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: 360.8 ms
  FPS: 12.7
  [ INFO ] 
  
  [ INFO ] The execution has completed successfully

速度比較 †

Smart Classroom C++ Demo †

デモの実行 †

• 実行例「Ubuntu on VirtualBox Core™ i7-2620M」

  $ cd ~/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 ........... 2021.3.0-2787-60059f2c755-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: 1.74649
  [ INFO ] Frames processed: 954
  
  [ INFO ] Execution successful

• 実行例「Ubuntu on VirtualBox Core™ i7-2620M」+ NCS2

  $ cd ~/omz_demos_build/intel64/Release
  $ ./smart_classroom_demo -m_act ~/model/intel/FP16/person-detection-action-recognition-0005.xml -m_fd ~/model/intel/FP16/face-detection-adas-0001.xml -i ~/Videos/classroom_s.mp4 -d_act MYRIAD -d_fd MYRIAD
  [ 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: 2.50199
  [ INFO ] Frames processed: 44
  
  E: [global] [    545624] [smart_classroom] XLink_sem_wait:94     XLink_sem_inc(sem) method call failed with an error: -1
  E: [global] [    545624] [smart_classroom] XLinkResetRemote:257 can't wait dispatcherClosedSem
  
  [ INFO ] Execution successful

速度比較 †

Pedestrian Tracker C++ Demo †

デモの実行 †

• 実行例「Ubuntu on VirtualBox Core™ i7-2620M」

  $ 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

• 実行例「Ubuntu on VirtualBox Core™ i7-2620M」+ NCS2

  $ cd ~/omz_demos_build/intel64/Release
  $ ./pedestrian_tracker_demo -i ~/Videos/video003_m.mp4 -m_det ~/model/intel/FP16/person-detection-retail-0013.xml -m_reid ~/model/intel/FP16/person-reidentification-retail-0288.xml -d_det MYRIAD
  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
  
  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
  
  E: [global] [    911266] [pedestrian_trac] XLink_sem_wait:94     XLink_sem_inc(sem) method call failed with an error: -1
  E: [global] [    911267] [pedestrian_trac] XLinkResetRemote:257 can't wait dispatcherClosedSem
  
  Execution successful

  　※シェルスクリプト起動はうまくいかなかった。ので直接実行。
  

Super Resolution C++ Demo †

デモの実行 †

• 実行例「Ubuntu on VirtualBox Core™ i7-2620M」

  $ 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

• 実行例「Ubuntu on VirtualBox Core™ i7-2620M」+ 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
  E: [global] [     88858] [super_resolutio] XLink_sem_wait:94     XLink_sem_inc(sem) method call failed with an error: -1
  E: [global] [     88858] [super_resolutio] XLinkResetRemote:257 can't wait dispatcherClosedSem
  
  [ 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 on VirtualBox Core™ i7-2620M」

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

• 実行例「Ubuntu on VirtualBox Core™ i7-2620M」+ NCS2

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

速度比較 †

Interactive Face Detection C++ Demo †

デモの実行 †

• 実行例「Ubuntu on VirtualBox Core™ i7-2620M」

  $ 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: 33
  [ INFO ] Total image throughput: 1.36412 fps
  
  [ INFO ] Execution successful

• 実行例「Ubuntu on VirtualBox Core™ i7-2620M」+ 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: 20
  [ INFO ] Total image throughput: 1.59717 fps
  
  E: [global] [    809766] [interactive_fac] XLink_sem_wait:94     XLink_sem_inc(sem) method call failed with an error: -1
  E: [global] [    809767] [interactive_fac] XLinkResetRemote:257 can't wait dispatcherClosedSem
  
  [ INFO ] Execution successful

速度比較 †

Gaze Estimation Demo †

デモの実行 †

• 実行例「Ubuntu on VirtualBox Core™ i7-2620M」

  $ cd ~/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

• 実行例「Ubuntu on VirtualBox Core™ i7-2620M」+ 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
  
  E: [global] [     10488] [Scheduler00Thr] dispatcherEventSend:53    Write failed (header) (err -4) | event XLINK_READ_REL_RESP
  
  E: [xLink] [     10491] [Scheduler00Thr] sendEvents:998 Event sending failed
  E: [global] [     10493] [Scheduler00Thr] dispatcherEventSend:53    Write failed (header) (err -4) | event XLINK_WRITE_REQ
      :
      :
  E: [global] [     10544] [gaze_estimation] XLinkReadData:156    Condition failed: (addEventWithPerf(&event, &opTime))
  E: [ncAPI] [     10544] [gaze_estimation] getGraphMonitorResponseValue:1905 XLink error, rc: X_LINK_ERROR
  *** stack smashing detected ***: terminated
  Aborted (core dumped)

速度比較] †

Security Barrier Camera C++ Demo †

デモの実行] †

• 実行例「Ubuntu Core™ i7-2620M」

  $ 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 ] 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
  14.8FPS for (375 / 1) frames
  Detection InferRequests usage: 100.0%
  
  [ INFO ] Execution successful

• 実行例「Ubuntu on VirtualBox Core™ i7-2620M」+ 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
  20.6FPS for (375 / 1) frames
  Detection InferRequests usage: 100.0%
  
  E: [global] [    381468] [security_barrie] XLink_sem_wait:94	 XLink_sem_inc(sem) method call failed with an error: -1
  E: [global] [    381469] [security_barrie] XLinkResetRemote:257	can't wait dispatcherClosedSem
  
  [ INFO ] Execution successful

速度比較 †

テスト環境 †

• IntelR NUC キット BXNUC10I5FNH
  
  • CPU Intel® Core™ i5-10210U CPU
    
  • OS Ubuntu20.04LTS
    
  • OpenVINO™ Toolkit for Linux 2021.2
    
  • OpenVINO™ Toolkit for Linux 2021.3
    

• 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
    
  • OpenVINO™ Toolkit for Linux 2021.3
    

• IntelR 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
    
  • OpenVINO™ Toolkit for Linux 2021.3
    

• 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
    
  • OS Ubuntu20.04LTS (VirtualBox on Windows 10 Pro 64 bit)
    
  • OpenVINO™ Toolkit for Linux 2021.3
    

更新履歴 †

• 2021/04/26 初版
• 2021/05/14 デモ実行結果更新
   

参考資料 †

• オフィシャルサイト
  • Intel® OpenVINO™ Toolkit Storage
    
  • Install Intel® Distribution of OpenVINO™ toolkit for Linux*「latest」
    
  • Get Started with OpenVINO™ Toolkit on Linux*
    
  • Open Model Zoo Demos「latest」
    
• Neural Compute Stick 2 (NCS2) に関するエラーについての対処
  
  • Can not init Myriad device: NC_ERROR
    
  • Installation and Configuration with a Virtual Machine