私的AI研究会 > Anaconda
「PyTorch ではじめる AI開発」で使用する Anaconda 環境での OpenVINO™ toolkit の使い方を調べる。
インテルのオフィシャルサイトにインストール方法について書かれているので、手順に従って進める。
→ Install Intel® Distribution of OpenVINO™ toolkit from Anaconda* Cloud
$ conda activate py37 (py37) $
(py37) $ conda update --all Collecting package metadata (current_repodata.json): done Solving environment: done ## Package Plan ## environment location: /home/mizutu/anaconda3/envs/py37 The following packages will be downloaded: package | build ---------------------------|----------------- atk-2.36.0 | 0 17 KB atk-1.0-2.36.0 | h28cd5cc_0 456 KB expat-2.4.1 | h2531618_2 168 KB gettext-0.21.0 | hf68c758_0 2.6 MB gnutls-3.6.15 | he1e5248_0 1.0 MB gobject-introspection-1.68.0| py37h2109141_1 1.4 MB icu-68.1 | h2531618_0 11.8 MB jasper-1.900.1 | hd497a04_4 198 KB krb5-1.19.2 | hac12032_0 1.2 MB lame-3.100 | h7b6447c_0 323 KB lerc-2.2.1 | h2531618_0 185 KB libcurl-7.78.0 | h0b77cf5_0 338 KB libdeflate-1.7 | h27cfd23_5 55 KB libgfortran-ng-9.3.0 | ha5ec8a7_17 22 KB libgfortran5-9.3.0 | ha5ec8a7_17 1.5 MB libidn2-2.3.2 | h7f8727e_0 81 KB libnghttp2-1.41.0 | hf8bcb03_2 667 KB libogg-1.3.5 | h27cfd23_1 199 KB libopus-1.3.1 | h7b6447c_0 491 KB libtasn1-4.16.0 | h27cfd23_0 58 KB libunistring-0.9.10 | h27cfd23_0 536 KB libvorbis-1.3.7 | h7b6447c_0 398 KB lz4-c-1.9.3 | h295c915_1 185 KB nettle-3.7.3 | hbbd107a_1 809 KB ninja-1.10.2 | hff7bd54_1 1.4 MB numpy-1.20.3 | py37h3dbb7de_0 23 KB numpy-base-1.20.3 | py37h39b7dee_0 4.5 MB pcre-8.45 | h295c915_0 207 KB wheel-0.37.0 | pyhd3eb1b0_0 32 KB ------------------------------------------------------------ Total: 30.7 MB The following NEW packages will be INSTALLED: gobject-introspec~ pkgs/main/linux-64::gobject-introspection-1.68.0-py37h2109141_1 libidn2 pkgs/main/linux-64::libidn2-2.3.2-h7f8727e_0 libtasn1 pkgs/main/linux-64::libtasn1-4.16.0-h27cfd23_0 libunistring pkgs/main/linux-64::libunistring-0.9.10-h27cfd23_0 ninja pkgs/main/linux-64::ninja-1.10.2-hff7bd54_1 numpy-base pkgs/main/linux-64::numpy-base-1.20.3-py37h39b7dee_0 The following packages will be REMOVED: font-ttf-dejavu-sans-mono-2.37-hab24e00_0 font-ttf-inconsolata-3.000-h77eed37_0 font-ttf-source-code-pro-2.038-h77eed37_0 font-ttf-ubuntu-0.83-hab24e00_0 fonts-conda-ecosystem-1-0 fonts-conda-forge-1-0 pthread-stubs-0.4-h36c2ea0_1001 xorg-kbproto-1.0.7-h7f98852_1002 xorg-libice-1.0.10-h7f98852_0 xorg-libsm-1.2.3-hd9c2040_1000 xorg-libx11-1.7.2-h7f98852_0 xorg-libxau-1.0.9-h7f98852_0 xorg-libxdmcp-1.1.3-h7f98852_0 xorg-libxext-1.3.4-h7f98852_1 xorg-libxrender-0.9.10-h7f98852_1003 xorg-renderproto-0.11.1-h7f98852_1002 xorg-xextproto-7.3.0-h7f98852_1002 xorg-xproto-7.0.31-h7f98852_1007 The following packages will be UPDATED: dbus conda-forge::dbus-1.13.6-h48d8840_2 --> pkgs/main::dbus-1.13.18-hb2f20db_0 expat conda-forge::expat-2.4.1-h9c3ff4c_0 --> pkgs/main::expat-2.4.1-h2531618_2 gettext conda-forge::gettext-0.19.8.1-h0b5b19~ --> pkgs/main::gettext-0.21.0-hf68c758_0 gmp conda-forge::gmp-6.2.1-h58526e2_0 --> pkgs/main::gmp-6.2.1-h2531618_2 gnutls conda-forge::gnutls-3.6.13-h85f3911_1 --> pkgs/main::gnutls-3.6.15-he1e5248_0 graphite2 conda-forge::graphite2-1.3.13-h58526e~ --> pkgs/main::graphite2-1.3.14-h23475e2_0 libedit conda-forge::libedit-3.1.20191231-he2~ --> pkgs/main::libedit-3.1.20210216-h27cfd23_1 libogg conda-forge::libogg-1.3.4-h7f98852_1 --> pkgs/main::libogg-1.3.5-h27cfd23_1 libxcb conda-forge::libxcb-1.13-h7f98852_1003 --> pkgs/main::libxcb-1.14-h7b6447c_0 nettle conda-forge::nettle-3.6-he412f7d_0 --> pkgs/main::nettle-3.7.3-hbbd107a_1 wheel 0.36.2-pyhd3eb1b0_0 --> 0.37.0-pyhd3eb1b0_0 The following packages will be SUPERSEDED by a higher-priority channel: atk conda-forge::atk-2.36.0-ha770c72_4 --> pkgs/main::atk-2.36.0-0 atk-1.0 conda-forge::atk-1.0-2.36.0-h3371d22_4 --> pkgs/main::atk-1.0-2.36.0-h28cd5cc_0 bzip2 conda-forge::bzip2-1.0.8-h7f98852_4 --> pkgs/main::bzip2-1.0.8-h7b6447c_0 c-ares conda-forge::c-ares-1.17.2-h7f98852_0 --> pkgs/main::c-ares-1.17.1-h27cfd23_0 cairo conda-forge::cairo-1.16.0-h6cf1ce9_10~ --> pkgs/main::cairo-1.16.0-hf32fb01_1 fontconfig conda-forge::fontconfig-2.13.1-hba837~ --> pkgs/main::fontconfig-2.13.1-h6c09931_0 freetype conda-forge::freetype-2.10.4-h0708190~ --> pkgs/main::freetype-2.10.4-h5ab3b9f_0 fribidi conda-forge::fribidi-1.0.10-h36c2ea0_0 --> pkgs/main::fribidi-1.0.10-h7b6447c_0 icu conda-forge::icu-68.1-h58526e2_0 --> pkgs/main::icu-68.1-h2531618_0 jasper conda-forge::jasper-1.900.1-h07fcdf6_~ --> pkgs/main::jasper-1.900.1-hd497a04_4 jbig conda-forge::jbig-2.1-h7f98852_2003 --> pkgs/main::jbig-2.1-hdba287a_0 krb5 conda-forge::krb5-1.19.2-hcc1bbae_0 --> pkgs/main::krb5-1.19.2-hac12032_0 lame conda-forge::lame-3.100-h7f98852_1001 --> pkgs/main::lame-3.100-h7b6447c_0 lerc conda-forge::lerc-2.2.1-h9c3ff4c_0 --> pkgs/main::lerc-2.2.1-h2531618_0 libcurl conda-forge::libcurl-7.78.0-h2574ce0_0 --> pkgs/main::libcurl-7.78.0-h0b77cf5_0 libdeflate conda-forge::libdeflate-1.7-h7f98852_5 --> pkgs/main::libdeflate-1.7-h27cfd23_5 libev conda-forge::libev-4.33-h516909a_1 --> pkgs/main::libev-4.33-h7b6447c_0 libgfortran-ng conda-forge::libgfortran-ng-11.1.0-h6~ --> pkgs/main::libgfortran-ng-9.3.0-ha5ec8a7_17 libgfortran5 conda-forge::libgfortran5-11.1.0-h6c5~ --> pkgs/main::libgfortran5-9.3.0-ha5ec8a7_17 libnghttp2 conda-forge::libnghttp2-1.43.0-h812cc~ --> pkgs/main::libnghttp2-1.41.0-hf8bcb03_2 libopus conda-forge::libopus-1.3.1-h7f98852_1 --> pkgs/main::libopus-1.3.1-h7b6447c_0 libpng conda-forge::libpng-1.6.37-h21135ba_2 --> pkgs/main::libpng-1.6.37-hbc83047_0 libssh2 conda-forge::libssh2-1.9.0-ha56f1ee_6 --> pkgs/main::libssh2-1.9.0-h1ba5d50_1 libuuid conda-forge::libuuid-2.32.1-h7f98852_~ --> pkgs/main::libuuid-1.0.3-h1bed415_2 libvorbis conda-forge::libvorbis-1.3.7-h9c3ff4c~ --> pkgs/main::libvorbis-1.3.7-h7b6447c_0 libwebp-base conda-forge::libwebp-base-1.2.0-h7f98~ --> pkgs/main::libwebp-base-1.2.0-h27cfd23_0 lz4-c conda-forge::lz4-c-1.9.3-h9c3ff4c_1 --> pkgs/main::lz4-c-1.9.3-h295c915_1 numpy conda-forge::numpy-1.21.1-py37h038b26~ --> pkgs/main::numpy-1.20.3-py37h3dbb7de_0 pango conda-forge::pango-1.48.7-hb8ff022_0 --> pkgs/main::pango-1.45.3-hd140c19_0 pcre conda-forge::pcre-8.45-h9c3ff4c_0 --> pkgs/main::pcre-8.45-h295c915_0 pixman conda-forge::pixman-0.40.0-h36c2ea0_0 --> pkgs/main::pixman-0.40.0-h7b6447c_0 Proceed ([y]/n)? y Downloading and Extracting Packages pcre-8.45 | 207 KB | ##################################### | 100% gobject-introspectio | 1.4 MB | ##################################### | 100% libogg-1.3.5 | 199 KB | ##################################### | 100% icu-68.1 | 11.8 MB | ##################################### | 100% nettle-3.7.3 | 809 KB | ##################################### | 100% gnutls-3.6.15 | 1.0 MB | ##################################### | 100% libdeflate-1.7 | 55 KB | ##################################### | 100% wheel-0.37.0 | 32 KB | ##################################### | 100% libgfortran5-9.3.0 | 1.5 MB | ##################################### | 100% krb5-1.19.2 | 1.2 MB | ##################################### | 100% libnghttp2-1.41.0 | 667 KB | ##################################### | 100% atk-2.36.0 | 17 KB | ##################################### | 100% jasper-1.900.1 | 198 KB | ##################################### | 100% libgfortran-ng-9.3.0 | 22 KB | ##################################### | 100% numpy-1.20.3 | 23 KB | ##################################### | 100% lz4-c-1.9.3 | 185 KB | ##################################### | 100% lame-3.100 | 323 KB | ##################################### | 100% numpy-base-1.20.3 | 4.5 MB | ##################################### | 100% lerc-2.2.1 | 185 KB | ##################################### | 100% atk-1.0-2.36.0 | 456 KB | ##################################### | 100% expat-2.4.1 | 168 KB | ##################################### | 100% gettext-0.21.0 | 2.6 MB | ##################################### | 100% libcurl-7.78.0 | 338 KB | ##################################### | 100% libopus-1.3.1 | 491 KB | ##################################### | 100% libtasn1-4.16.0 | 58 KB | ##################################### | 100% libvorbis-1.3.7 | 398 KB | ##################################### | 100% libidn2-2.3.2 | 81 KB | ##################################### | 100% ninja-1.10.2 | 1.4 MB | ##################################### | 100% libunistring-0.9.10 | 536 KB | ##################################### | 100% Preparing transaction: done Verifying transaction: done Executing transaction: done
(py37) $ conda install openvino-ie4py-ubuntu20 -c intel Collecting package metadata (current_repodata.json): done Solving environment: done ## Package Plan ## environment location: /home/mizutu/anaconda3/envs/py37 added / updated specs: - openvino-ie4py-ubuntu20 The following packages will be downloaded: package | build ---------------------------|----------------- ca-certificates-2020.12.5 | 0 138 KB intel certifi-2020.12.5 | py37he139614_0 143 KB intel intelpython-2021.3.0 | 7 8 KB intel openssl-1.1.1k | h14c3975_1 2.2 MB intel openvino-ie-2021.4 |ubuntu20_intel_582 45.1 MB intel openvino-ie4py-2021.4 |py37_ubuntu20_intel_582 570 KB intel openvino-ie4py-ubuntu20-2021.4| intel_582 13 KB intel tbb-2020.3 | intel_304 945 KB intel ------------------------------------------------------------ Total: 49.1 MB The following NEW packages will be INSTALLED: intelpython intel/linux-64::intelpython-2021.3.0-7 openvino-ie intel/linux-64::openvino-ie-2021.4-ubuntu20_intel_582 openvino-ie4py intel/linux-64::openvino-ie4py-2021.4-py37_ubuntu20_intel_582 openvino-ie4py-ub~ intel/linux-64::openvino-ie4py-ubuntu20-2021.4-intel_582 tbb intel/linux-64::tbb-2020.3-intel_304 The following packages will be UPDATED: openssl pkgs/main::openssl-1.1.1k-h27cfd23_0 --> intel::openssl-1.1.1k-h14c3975_1 The following packages will be SUPERSEDED by a higher-priority channel: ca-certificates pkgs/main::ca-certificates-2021.7.5-h~ --> intel::ca-certificates-2020.12.5-0 certifi pkgs/main::certifi-2021.5.30-py37h06a~ --> intel::certifi-2020.12.5-py37he139614_0 Proceed ([y]/n)? y Downloading and Extracting Packages certifi-2020.12.5 | 143 KB | ##################################### | 100% ca-certificates-2020 | 138 KB | ##################################### | 100% openssl-1.1.1k | 2.2 MB | ##################################### | 100% openvino-ie-2021.4 | 45.1 MB | ##################################### | 100% tbb-2020.3 | 945 KB | ##################################### | 100% openvino-ie4py-ubunt | 13 KB | ##################################### | 100% openvino-ie4py-2021. | 570 KB | ##################################### | 100% intelpython-2021.3.0 | 8 KB | ##################################### | 100% Preparing transaction: done Verifying transaction: done Executing transaction: done
(py37) $ python -c "from openvino.inference_engine import IECore"エラーが出なければインストール OK
Images_20210510.tar.gz (10MB) 「~/Images」画像データ Videos_20210510.tar.gz (324MB) 「~/Videos」動画データ run_app3_20210811.tar.gz (5KB) 「~/run_app2」実行シェルスクリプト (パラメータ引き継ぎ) run_app2_20210819.tar.gz (5KB) 「~/run_app2」実行シェルスクリプト (マルチデバイス対応) run_app_20210624.tar.gz (9KB) 「~/run_app」実行シェルスクリプト workspace_20210820.tar.gz (561MB) 「~/workspace」アプリケーションフォルダ omz_demos_python_2021.4_20210818.tar.gz (21.5MB) 「~/omz_demos_python」OpenVINO™ Python デモ (修正済み) data_20210818.tar.gz (62.7kB) omz_demos_build_2021.4_20210820.tar.gz (9.1MB) 「~/omz_demos_build」OpenVINO™ C++ デモ (コンパイル済み) model_sub_2021.4_20210818.tar.gz (944MB) 「~/model」学習済みモデル - 必要モデルのみのサブセット版 -
(py37) $ tar xvzf Images_20210510.tar.gz (py37) $ tar xvzf Videos_20210510.tar.gz (py37) $ tar xvzf run_app3_20210811.tar.gz (py37) $ tar xvzf run_app2_20210819.tar.gz (py37) $ tar xvzf run_app_20210624.tar.gz (py37) $ tar xvzf workspace_20210820.tar.gz (py37) $ tar xvzf omz_demos_python_2021.4_20210818.tar.gz (py37) $ tar xvzf data_20210818.tar.gz (py37) $ tar xvzf omz_demos_build_2021.4_20210820.tar.gz (py37) $ tar xvzf model_sub_2021.4_20210818.tar.gz
(py37) $ conda search munkres Loading channels: done # Name Version Build Channel munkres 1.0.12 py_0 pkgs/main munkres 1.1.4 py_0 pkgs/main (py37) $ conda install munkres Collecting package metadata (current_repodata.json): done Solving environment: done ## Package Plan ## environment location: /home/mizutu/anaconda3/envs/py37 added / updated specs: - munkres The following packages will be downloaded: package | build ---------------------------|----------------- munkres-1.1.4 | py_0 13 KB ------------------------------------------------------------ Total: 13 KB The following NEW packages will be INSTALLED: munkres pkgs/main/noarch::munkres-1.1.4-py_0 The following packages will be UPDATED: ca-certificates intel::ca-certificates-2020.12.5-0 --> pkgs/main::ca-certificates-2021.7.5-h06a4308_1 certifi intel::certifi-2020.12.5-py37he139614~ --> pkgs/main::certifi-2021.5.30-py37h06a4308_0 The following packages will be SUPERSEDED by a higher-priority channel: openssl intel::openssl-1.1.1k-h14c3975_1 --> pkgs/main::openssl-1.1.1k-h27cfd23_0 Proceed ([y]/n)? y Downloading and Extracting Packages munkres-1.1.4 | 13 KB | ##################################### | 100% Preparing transaction: done Verifying transaction: done Executing transaction: done
■ AI 学習済み推論モデルの実践編 $ cd /run_app2/
(py37) $ cd ~/run_app2/ (py37) $ ./face_mask.sh [face_mask.sh] 'face_mask' Run !! DEVICE: CPU COMMAND: python3 face_mask.py -m_dt ./models/face-detection-adas-0001.xml -m_mk ./models/face_mask.xml -d CPU --- Face Mask Check --- 4.5.2 OpenVINO inference_engine: 2021.4.0-3839-cd81789d294-releases/2021/4 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 : CPU - 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: 1.90 Finished.
(py37) $ cd ~/run_app2/ (py37) $ ./virtual_fitting.sh [virtual_fitting.sh] virtual_Fitting.py Run !! itemidx.: 0 program : virtual_fitting.py model1. : -m_dt /home/mizutu/model/intel/FP32/face-detection-retail-0005.xml model2. : -m_lm /home/mizutu/model/intel/FP32/landmarks-regression-retail-0009.xml device. : CPU input.. : -i /home/mizutu/Images/photo.jpg output. : MODEL: FP32 DEVICE: CPU COMMAND: python3 virtual_fitting.py -item 0 -m_dt /home/mizutu/model/intel/FP32/face-detection-retail-0005.xml -m_lm /home/mizutu/model/intel/FP32/landmarks-regression-retail-0009.xml -i /home/mizutu/Images/photo.jpg -d CPU --- Virtual Fitting --- 4.5.2 OpenVINO inference_engine: 2021.4.0-3839-cd81789d294-releases/2021/4 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/FP32/face-detection-retail-0005.xml - m_recognition: /home/mizutu/model/intel/FP32/landmarks-regression-retail-0009.xml - Device : CPU - Program Title: y - Speed flag : y - Processed out: non FPS average: 15.80 Finished.
(py37) $ ./virtual_fitting_eyepoint_tool.sh [virtual_fitting_eyepoint_tool.sh] Aplication Run command itemidx.: 0 program : virtual_fitting_eyepoint_tool.py ../../Images/parts/glass01.png
(py37) $ cd ~/run_app2/ (py37) $ ./emotion2.sh [emotion2.sh] emotion2.py Run !! program : emotion2.py model1. : -m_dt /home/mizutu/model/intel/FP32/face-detection-adas-0001.xml model2. : -m_re /home/mizutu/model/intel/FP32/emotions-recognition-retail-0003.xml device. : CPU input.. : -i /home/mizutu/Images/emo2.jpg output. : MODEL: FP32 DEVICE: CPU COMMAND: python3 emotion2.py -m_dt /home/mizutu/model/intel/FP32/face-detection-adas-0001.xml -m_re /home/mizutu/model/intel/FP32/emotions-recognition-retail-0003.xml -d CPU -i /home/mizutu/Images/emo2.jpg --- Emotion Recognition 2 --- 4.5.2 OpenVINO inference_engine: 2021.4.0-3839-cd81789d294-releases/2021/4 Emotion Recognition 2: Starting application... - Image File : /home/mizutu/Images/emo2.jpg - m_detect : /home/mizutu/model/intel/FP32/face-detection-adas-0001.xml - m_recognition: /home/mizutu/model/intel/FP32/emotions-recognition-retail-0003.xml - Device : CPU - 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: 5.70 Finished.
(py37) $ cd ~/run_app2/ (py37) $ ./age_gender2.sh [age_gender2.sh] age_gender2.py Run !! program : age_gender2.py model1. : -m_dt /home/mizutu/model/intel/FP32/face-detection-adas-0001.xml model2. : -m_re /home/mizutu/model/intel/FP32/age-gender-recognition-retail-0013.xml device. : CPU input.. : -i /home/mizutu/Images/emo2.jpg output. : MODEL: FP32 DEVICE: CPU COMMAND: python3 age_gender2.py -m_dt /home/mizutu/model/intel/FP32/face-detection-adas-0001.xml -m_re /home/mizutu/model/intel/FP32/age-gender-recognition-retail-0013.xml -d CPU -i /home/mizutu/Images/emo2.jpg --- Age/Gender Recognition 2 --- 4.5.2 OpenVINO inference_engine: 2021.4.0-3839-cd81789d294-releases/2021/4 Age/Gender Recognition 2: Starting application... - Image File : /home/mizutu/Images/emo2.jpg - m_detect : /home/mizutu/model/intel/FP32/face-detection-adas-0001.xml - m_recognition: /home/mizutu/model/intel/FP32/age-gender-recognition-retail-0013.xml - Device : CPU - 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: 7.80 Finished.
(py37) $ cd ~/run_app2/ (py37) $ ./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/FP32/yolo-v3-tiny-tf.xml model2. : device. : CPU input.. : -i /home/mizutu/Videos/car.mp4 output. : MODEL: FP32 DEVICE: CPU COMMAND: python3 object_detect_yolo3_2.py --ir /home/mizutu/model/public/FP32/yolo-v3-tiny-tf.xml -i /home/mizutu/Videos/car.mp4 -d CPU --- TinyYOLO V3 Object detection --- 4.5.2 OpenVINO inference_engine: 2021.4.0-3839-cd81789d294-releases/2021/4 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/FP32/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 : CPU - 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: 8.70 Finished.
(py37) $ cd ~/run_app2/ (py37) $ ./person-tracking2.sh [person-tracking2.sh] person-tracking2.py Run !! program : person-tracking2.py model1. : -m_dt /home/mizutu/model/intel/FP32/person-detection-retail-0013.xml model2. : -m_re /home/mizutu/model/intel/FP32/person-reidentification-retail-0287.xml device. : CPU input.. : -i /home/mizutu/Videos/video002.mp4 output. : MODEL: FP32 DEVICE: CPU COMMAND: python3 person-tracking2.py -m_dt /home/mizutu/model/intel/FP32/person-detection-retail-0013.xml -m_re /home/mizutu/model/intel/FP32/person-reidentification-retail-0287.xml -d CPU -i /home/mizutu/Videos/video002.mp4 --- Person Tracking 2 --- 4.5.2 OpenVINO inference_engine: 2021.4.0-3839-cd81789d294-releases/2021/4 Person Tracking 2: Starting application... - Image File : /home/mizutu/Videos/video002.mp4 - m_detect : /home/mizutu/model/intel/FP32/person-detection-retail-0013.xml - m_redient. : /home/mizutu/model/intel/FP32/person-reidentification-retail-0287.xml - Device : CPU - Threshold : 0.8 - Speed flag : y - Processed out: non ------------------- 1.0 (463,90)-(559,294) 1.0 (348,94)-(418,280) 0.9 (426,119)-(473,273) ==================== input: 3 DB:3 persionId:0 0.9999999999999998 distance:0.0 persionId:1 0.9999999999999984 distance:0.0 persionId:2 0.9999999999999986 distance:0.0 : : 1.0 (174,110)-(295,324) 1.0 (328,154)-(389,326) 0.9 (524,202)-(640,360) ==================== input: 4 DB:3 persionId:0 0.6184502687682235 distance:18.384776310850235 persionId:1 0.7520857277155804 distance:58.180752831155424 persionId:2 0.6851582559345559 distance:22.80350850198276 persionId:2 0.12058635422455298 distance:69.1158447825099 [0 1 2 2] [ 0 1 2 -1] FPS average: 15.80 Finished.
(py37) $ cd ~/run_app2/ (py37) $ ./face-tracking2.sh [face-tracking2.sh] face-tracking2.py Run !! program : face-tracking2.py model1. : -m_dt /home/mizutu/model/intel/FP32/face-detection-0200.xml model2. : -m_re /home/mizutu/model/intel/FP32/face-reidentification-retail-0095.xml device. : CPU input.. : -i /home/mizutu/Videos/video001.mp4 output. : MODEL: FP32 DEVICE: CPU COMMAND: python3 face-tracking2.py -m_dt /home/mizutu/model/intel/FP32/face-detection-0200.xml -m_re /home/mizutu/model/intel/FP32/face-reidentification-retail-0095.xml -d CPU -i /home/mizutu/Videos/video001.mp4 --- Face Tracking 2 --- 4.5.2 OpenVINO inference_engine: 2021.4.0-3839-cd81789d294-releases/2021/4 Face Tracking 2: Starting application... - Image File : /home/mizutu/Videos/video001.mp4 - m_detect : /home/mizutu/model/intel/FP32/face-detection-0200.xml - m_redient. : /home/mizutu/model/intel/FP32/face-reidentification-retail-0095.xml - Device : CPU - Threshold : 0.5 - Speed flag : y - Processed out: non ------------------- 1.0 (169,87)-(191,118) 0.9 (231,48)-(254,80) 0.9 (138,48)-(159,76) 0.7 (263,63)-(287,98) ==================== input: 4 DB:4 persionId:0 0.9999999999999988 conf:0.955000102519989 persionId:1 0.9999999999999991 conf:0.8864630460739136 : : [9 6] ------------------- 1.0 (154,54)-(208,125) 1.0 (345,65)-(400,136) 0.6 (455,75)-(488,111) ==================== input: 3 DB:21 persionId:9 0.3791677744051556 conf:0.9986664056777954 persionId:6 0.31571819613113794 conf:0.9984273910522461 persionId:20 0.4203415339233143 conf:0.598606288433075 [ 9 6 20] [ 9 6 20] FPS average: 21.70 Finished.
(py37) $ cd ~/run_app2/ (py37) $ ./sentiment_analysis2.sh [sentiment_analysis2.sh] sentiment_analysis2.py Run !! program : sentiment_analysis2.py model1. : -m_dt /home/mizutu/model/intel/FP32/face-detection-retail-0004.xml model2. : -m_re /home/mizutu/model/intel/FP32/emotions-recognition-retail-0003.xml device. : CPU input.. : -i /home/mizutu/Images/emo2.jpg output. : MODEL: FP32 DEVICE: CPU COMMAND: python3 sentiment_analysis2.py -m_dt /home/mizutu/model/intel/FP32/face-detection-retail-0004.xml -m_re /home/mizutu/model/intel/FP32/emotions-recognition-retail-0003.xml -d CPU -i /home/mizutu/Images/emo2.jpg --- Real-time sentiment analysis 2 --- 4.5.2 OpenVINO inference_engine: 2021.4.0-3839-cd81789d294-releases/2021/4 Real-time sentiment analysis 2: Starting application... - Image File : /home/mizutu/Images/emo2.jpg - m_detect : /home/mizutu/model/intel/FP32/face-detection-retail-0004.xml - m_recognition: /home/mizutu/model/intel/FP32/emotions-recognition-retail-0003.xml - Device : CPU - Language : jp - Program Title: y - Speed flag : y - Processed out: non FPS average: 25.40 Finished.
(py37) $ cd ~/run_app2/ (py37) $ ./image_classification.sh [image_classification.sh] image_classification.py Run !! program : image_classification.py model1. : -m /home/mizutu/model/public/FP32/squeezenet1.1.xml model2. : device. : CPU input.. : -i /home/mizutu/Images/cat.jpg output. : MODEL: FP32 DEVICE: CPU COMMAND: python3 image_classification.py -m /home/mizutu/model/public/FP32/squeezenet1.1.xml -i /home/mizutu/Images/cat.jpg -d CPU --- Image Classification --- 4.5.2 OpenVINO inference_engine: 2021.4.0-3839-cd81789d294-releases/2021/4 Image Classification: Starting application... - Image File : /home/mizutu/Images/cat.jpg - Model : /home/mizutu/model/public/FP32/squeezenet1.1.xml - Device : CPU - Label : ./synset_words_jp.txt - Program Title: y - Speed flag : y - Processed out: non FPS average: 7.80 Finished.
■ OpenVINO™ Toolkit の使い方 編 $ cd /run_app3/
(py37) $ cd ~/run_app3/ (py37) $ ./dbface-infer.sh [dbface-infer.sh] 'dbface-infer2.py' Run !! DIR: /home/mizutu/workspace/apps3/dbface-on-openvino-master COMMAND: python3 dbface-infer2.py --- DBFace single-stage face detector 2 --- 4.5.2 OpenVINO inference_engine: 2021.4.0-3839-cd81789d294-releases/2021/4 DBFace single-stage face detector 2: Starting application... - Image File : selfie.jpg - model : ./ir-models/dbface-4vga-fp16/dbface.xml - Device : CPU - Program Title: y - Speed flag : y - Processed out: non dbface-infer2.py:234: 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. inblobs = (list(net.inputs.keys())) ['x'] ['Conv_525', 'Exp_527', 'Sigmoid_526'] [[1, 3, 960, 1280]] [[1, 10, 240, 320], [1, 4, 240, 320], [1, 1, 240, 320]] FPS average: 1.10 Finished.
(py37) $ cd ~/run_app3/ (py37) $ ./objdet-adaptive-partitioning.sh [objdet-adaptive-partitioning.sh] 'objdet-adaptive-partitioning2.py' Run !! DIR: /home/mizutu/workspace/apps3/object-detection-with-adaptive-partitioning-master COMMAND: python3 objdet-adaptive-partitioning2.py --- Object Detection with adaptive partitioning 2 --- 4.5.2 OpenVINO inference_engine: 2021.4.0-3839-cd81789d294-releases/2021/4 Object Detection with adaptive partitioning 2: Starting application... - Image File : image.jpg - model : /home/mizutu/model/intel/FP16/face-detection-0200.xml - Device : CPU - Processed out: non Displaying regions boudary boxes for 3 seconds. Displaying detection result for 10 seconds.
(py37) $ cd ~/run_app3/ (py37) $ ./object-detection-and-line-cross.sh [object-detection-and-line-cross.sh] 'object-detection-and-line-cross2.py' Run !! DIR: /home/mizutu/workspace/apps3/object-tracking-line-crossing-area-intrusion-master COMMAND: python3 object-detection-and-line-cross2.py --- Object Tracking with Line Crossing 2 --- 4.5.2 OpenVINO inference_engine: 2021.4.0-3839-cd81789d294-releases/2021/4 Object Tracking with Line Crossing 2: Starting application... - Image File : people-detection.264 - Device : CPU - Program Title: y - Speed flag : y - Processed out: non Discarded : id 0 Discarded : id 1 Discarded : id 2 Discarded : id 3 : FPS average: 25.90 Finished.
(py37) $ cd ~/run_app3/ (py37) $ ./gaze-estimation.sh [gaze-estimation.sh] 'gaze-estimation2.py' Run !! DIR: /home/mizutu/workspace/apps3/gaze-estimation-with-laser-sparking-master COMMAND: python3 gaze-estimation2.py --- Gaze Estimation Demo with Sparking Laser Beam 2 --- 4.5.2 OpenVINO inference_engine: 2021.4.0-3839-cd81789d294-releases/2021/4 Gaze Estimation Demo with Sparking Laser Beam 2: Starting application... - Image File : 0 - Device : CPU - Program Title: y - Speed flag : y - Processed out: non Gaze estimation demo 'f': Flip image 'l': Laser mode on/off 's': Spark mode on/off 'b': Boundary box on/off FPS average: 17.20 Finished.
(py37) $ cd ~/run_app3/ (py37) $ ./image-inpainting.sh [image-inpainting.sh] 'image-inpainting2.py' Run !! DIR: /home/mizutu/workspace/apps3/interactive-image-inpainting-master COMMAND: python3 image-inpainting2.py --- image inpainting 2 --- 4.5.2 OpenVINO inference_engine: 2021.4.0-3839-cd81789d294-releases/2021/4 image inpainting 2: Starting application... - Image File : image.jpg - Device : CPU - Processed out: non inpainting... process end !! >> edit start inpainting... process end !! >> edit start
(py37) $ cd ~/run_app3/ (py37) $ ./handwritten-japanese-OCR-touch-panel-demo.sh [handwritten-japanese-OCR-touch-panel-demo.sh] 'handwritten-japanese-OCR-touch-panel-demo2.py' Run !! DIR: /home/mizutu/workspace/apps3/handwritten-japanese-ocr-master COMMAND: python3 handwritten-japanese-OCR-touch-panel-demo2.py --- Handwritten Japanese OCR demo 2 --- 4.5.2 OpenVINO inference_engine: 2021.4.0-3839-cd81789d294-releases/2021/4 Handwritten Japanese OCR Demo ESC: Quit Mouse L-Button: Draw Mouse R-Button: Erase Threshold = Text area detect threshold Handwritten Japanese OCR demo 2: Starting application... - Device : CPU - Processed out: non text detection... handwritten-japanese-OCR-touch-panel-demo2.py:167: DeprecationWarning: `np.bool` is a deprecated alias for the builtin `bool`. To silence this warning, use `bool` by itself. Doing this will not modify any behavior and is safe. If you specifically wanted the numpy scalar type, use `np.bool_` here. Deprecated in NumPy 1.20; for more details and guidance: https://numpy.org/devdocs/release/1.20.0-notes.html#deprecations pixel_mask = np.full((h*w,), False, dtype=np.bool) text detection - completed OCR result (0): ['入カテスト'] process end !! >> edit start
(py37) $ cd ~/run_app3/ (py37) $ ./ir-summary.sh -h [ir-summary.sh] 'ir-summary.py' Run !! DIR: /home/mizutu/workspace/apps3/openvino-ir-utility-master COMMAND: python3 ir-summary.py -h usage: ir-summary.py [-h] [-m MODEL] [-d DIR] [-v] optional arguments: -h, --help show this help message and exit -m MODEL, --model MODEL input IR model path -d DIR, --dir DIR input IR model directory -v, --verbose output detailed information
OpenVINO™ Toolkit for Linux「2021.4 LTS」(l_openvino_toolkit_p_2021.4.582.tgz) インストール時に配置されるデモソフトがランタイム版で動作するかを確認する。
インストール後に「/opt/intel/openvino_2021/deployment_tools/open_model_zoo/demos/」に配置される Python 関連ファイルを「~/omz_demos_Python/」において動作確認を行う。
当然ながらシステム環境に相違があるのですべてが動作するわけではない。
結果として Python デモの一部が動作する。
■ 問題なく動作するデモソフト $ cd /run_app2/
(py37) $ cd ~/run_app2/ (py37) $ source ~/omz_demos_build/omz_demos.sh (py37) $ ./_human_pose_estimation_3d_demo.sh [human_pose_estimation_3d_demo.sh] 'human_pose_estimation_3d_demo' Run !! MODEL: FP32 DEVICE: CPU COMMAND: python3 human_pose_estimation_3d_demo.py -m /home/mizutu/model/public/FP32/human-pose-estimation-3d-0001.xml -i /home/mizutu/Videos/driver.mp4 -d CPU
(py37) $ cd ~/run_app2/ (py37) $ ./_action_recognition.sh [action_recognition_demo.sh] 'action_recognition_demo' Run !! MODEL: FP32 DEVICE: CPU COMMAND: python3 action_recognition_demo.py -m_en /home/mizutu/model/intel/FP32/driver-action-recognition-adas-0002-encoder.xml -at en-de -m_de /home/mizutu/model/intel/FP32/driver-action-recognition-adas-0002-decoder.xml -i /home/mizutu/Videos/driver.mp4 -lb driver_actions.txt -d CPU 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% -- 8.17ms Frame 16: Safe driving - 87.28% -- 11.45ms Frame 17: Safe driving - 89.16% -- 11.94ms : : Frame 367: Safe driving - 94.98% -- 16.18ms Frame 368: Safe driving - 94.02% -- 15.90ms Frame 369: Safe driving - 93.38% -- 14.01ms finishing <action_recognition_demo.steps.RenderStep object at 0x7f689d5c5a50> Data total: 0.91ms (+/-: 1.49) 1097.12fps Data own: 0.90ms (+/-: 1.49) 1113.64fps Encoder total: 9.37ms (+/-: 4.61) 106.71fps Encoder own: 9.35ms (+/-: 4.61) 106.90fps Decoder total: 1.49ms (+/-: 2.73) 673.20fps Decoder own: 1.47ms (+/-: 2.72) 678.63fps Render total: 33.28ms (+/-: 51.82) 30.04fps Render own: 33.18ms (+/-: 50.93) 30.14fps QObject::~QObject: Timers cannot be stopped from another thread
(py37) $ cd ~/run_app2/ (py37) $ ./_handwritten_text_recognition_demo.sh [handwritten_text_recognition_demo.sh] 'handwritten_text_recognition_demo' Run !! MODEL: FP32 DEVICE: CPU COMMAND: python3 handwritten_text_recognition_demo.py -i ./data/handwritten_japanese_test.png -m /home/mizutu/model/intel/FP32/handwritten-japanese-recognition-0001.xml -d CPU [ 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: 860.0423336029053 ms
(py37) $ cd ~/run_app2/ (py37) $ ./_single_human_pose_estimation_demo.sh [single_human_pose_estimation_demo.sh] 'single_human_pose_estimation_demo' Run !! MODEL: FP32 DEVICE: CPU COMMAND: python3 single_human_pose_estimation_demo.py -m_od /home/mizutu/model/public/FP32/mobilenet-ssd.xml -m_hpe /home/mizutu/model/public/FP32/single-human-pose-estimation-0001.xml -i /home/mizutu/Videos/person_m.mp4 -d CPU
(py37) $ cd ~/run_app2/ (py37) $ ./_image_inpainting_demo.sh [image_inpainting_demo.sh] 'image_inpainting_demo' Run !! MODEL: FP32 DEVICE: CPU COMMAND: python3 image_inpainting_demo.py -m /home/mizutu/model/public/FP32/gmcnn-places2-tf.xml -i /home/mizutu/Images/car_m.jpg -ar -d CPU image_inpainting_demo.py:76: DeprecationWarning: `np.int` is a deprecated alias for the builtin `int`. To silence this warning, use `int` by itself. Doing this will not modify any behavior and is safe. When replacing `np.int`, you may wish to use e.g. `np.int64` or `np.int32` to specify the precision. If you wish to review your current use, check the release note link for additional information. Deprecated in NumPy 1.20; for more details and guidance: https://numpy.org/devdocs/release/1.20.0-notes.html#deprecations next_y = np.clip(next_y, 0, h - 1).astype(np.int)
(py37) $ cd ~/run_app2/ (py37) $ ./_image_inpainting_demo.sh [image_inpainting_demo.sh] 'image_inpainting_demo' Run !! MODEL: FP32 DEVICE: CPU COMMAND: python3 image_inpainting_demo.py -m /home/mizutu/model/public/FP32/gmcnn-places2-tf.xml -i /home/mizutu/Images/car_m.jpg -ar -d CPU image_inpainting_demo.py:76: DeprecationWarning: `np.int` is a deprecated alias for the builtin `int`. To silence this warning, use `int` by itself. Doing this will not modify any behavior and is safe. When replacing `np.int`, you may wish to use e.g. `np.int64` or `np.int32` to specify the precision. If you wish to review your current use, check the release note link for additional information. Deprecated in NumPy 1.20; for more details and guidance: https://numpy.org/devdocs/release/1.20.0-notes.html#deprecations next_y = np.clip(next_y, 0, h - 1).astype(np.int) (py37) mizutu@ubuntu-vbox:~/run_app2$ ./_colorization_demo.sh [colorization_demo.sh] 'colorization_demo' Run !! MODEL: FP32 DEVICE: CPU COMMAND: python3 colorization_demo.py -m /home/mizutu/model/public/FP32/colorization-v2.xml -i /home/mizutu/Videos/mono03.mp4 -d CPU
(py37) $ cd ~/run_app2/ (py37) $ ./_hello_query_device.sh [hello_query_device.sh] 'hello_query_device' Run !! [ INFO ] Creating Inference Engine [ INFO ] Available devices: [ INFO ] CPU : [ INFO ] SUPPORTED_METRICS: [ INFO ] AVAILABLE_DEVICES: [ INFO ] FULL_DEVICE_NAME: Intel(R) Core(TM) i7-6700 CPU @ 3.40GHz [ INFO ] OPTIMIZATION_CAPABILITIES: FP32, FP16, INT8, BIN [ INFO ] RANGE_FOR_ASYNC_INFER_REQUESTS: 1, 1, 1 [ INFO ] RANGE_FOR_STREAMS: 1, 4 [ INFO ] [ INFO ] SUPPORTED_CONFIG_KEYS (default values): [ INFO ] CPU_BIND_THREAD: YES [ INFO ] CPU_THREADS_NUM: 0 [ INFO ] CPU_THROUGHPUT_STREAMS: 1 [ INFO ] DUMP_EXEC_GRAPH_AS_DOT: [ INFO ] DYN_BATCH_ENABLED: NO [ INFO ] DYN_BATCH_LIMIT: 0 [ INFO ] ENFORCE_BF16: NO [ INFO ] EXCLUSIVE_ASYNC_REQUESTS: NO [ INFO ] PERF_COUNT: NO [ INFO ]
■ エラーとなるデモソフト $ cd /run_app2/
(py37) $ cd ~/run_app2/ (py37) $ ./_object_detection_python_demo.sh [object_detection_demo.sh] 'object_detection_demo' Run !! MODEL: FP32 DEVICE: CPU COMMAND: python3 object_detection_demo.py -m /home/mizutu/model/intel/FP32/person-vehicle-bike-detection-crossroad-yolov3-1020.xml -i /home/mizutu/Videos/car_person.mp4 -at yolo -d CPU Traceback (most recent call last): File "object_detection_demo.py", line 33, in <module> import models File "/home/mizutu/omz_demos_python/common/python/models/__init__.py", line 23, in <module> from .open_pose import OpenPose File "/home/mizutu/omz_demos_python/common/python/models/open_pose.py", line 18, in <module> import ngraph as ng ModuleNotFoundError: No module named 'ngraph'
(py37) $ cd ~/run_app2/ (py37) $ ./_human_pose_estimation.sh [human_pose_estimation_demo.sh] 'human_pose_estimation_demo' Run !! MODEL: FP32 DEVICE: CPU COMMAND: python3 human_pose_estimation_demo.py -i /home/mizutu/Videos/driver.mp4 -m /home/mizutu/model/intel/FP32/human-pose-estimation-0001.xml -at openpose -d CPU Traceback (most recent call last): File "human_pose_estimation_demo.py", line 29, in <module> import models File "/home/mizutu/omz_demos_python/common/python/models/__init__.py", line 23, in <module> from .open_pose import OpenPose File "/home/mizutu/omz_demos_python/common/python/models/open_pose.py", line 18, in <module> import ngraph as ng ModuleNotFoundError: No module named 'ngraph'
(py37) $ cd ~/run_app2/ (py37) $ ./_gesture_recognition_demo.sh [gesture_recognition_demo.sh] 'gesture_recognition_demo' Run !! MODEL: FP32 DEVICE: CPU COMMAND: python3 gesture_recognition_demo.py -m_a /home/mizutu/model/intel/FP32/asl-recognition-0004.xml -m_d /home/mizutu/model/intel/FP32/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 CPU Traceback (most recent call last): File "gesture_recognition_demo.py", line 256, in <module> sys.exit(main() or 0) File "gesture_recognition_demo.py", line 116, in main assert class_map is not None AssertionError
(py37) $ cd ~/run_app2/ (py37) $ ./_deblurring_demo.sh [deblurring_demo.sh] 'deblurring_demo' Run !! MODEL: FP32 DEVICE: CPU COMMAND: python3 deblurring_demo.py -m /home/mizutu/model/public/FP32/deblurgan-v2.xml -i /home/mizutu/Images/deblurred_image.png --loop -d CPU Traceback (most recent call last): File "deblurring_demo.py", line 28, in <module> from models import Deblurring File "/home/mizutu/omz_demos_python/common/python/models/__init__.py", line 23, in <module> from .open_pose import OpenPose File "/home/mizutu/omz_demos_python/common/python/models/open_pose.py", line 18, in <module> import ngraph as ng ModuleNotFoundError: No module named 'ngraph'
OpenVINO™ Toolkit for Linux「2021.4 LTS」(l_openvino_toolkit_p_2021.4.582.tgz) インストール時に配置されるデモソフトがランタイム版で動作するかを確認する。
コンパイル済みの実行ファイルをインストール後と同じ場所「~/omz_demos_build/」において動作確認を行う。
Python 環境をターゲットとしたランタイムのようでで動作しない。同じエラーとなる。
■ エラーとなるデモソフト(すべて実行不可) $ cd /run_app2/
(py37) $ cd ~/run_app2/ (py37) $ ./_text_detection_demo.sh [text_detection_demo.sh] 'text_detection_demo' Run !! MODEL: FP32 DEVICE: CPU COMMAND: ./text_detection_demo -loop -m_td /home/mizutu/model/intel/FP32/text-detection-0004.xml -m_tr /home/mizutu/model/intel/FP32/text-recognition-0012.xml -i /home/mizutu/Images/text-img.jpg -d_td CPU -d_tr CPU ./text_detection_demo: error while loading shared libraries: libopencv_highgui.so.4.5: cannot open shared object file: No such file or directory
以下すべて同じエラー (py37) $ ./_text_detection_demo.sh (py37) $ ./_crossroad_camera_demo.sh (py37) $ ./_human_pose_estimation_demo.sh (py37) $ ./_object_detection_demo.sh (py37) $ ./_smart_classroom_demo.sh (py37) $ ./_pedestrian_tracker_demo.sh (py37) $ ./_interactive_face_detection_demo.sh (py37) $ ./_gaze_estimation_demo.sh (py37) $ ./_security_barrier_camera_demo.sh (py37) $ ./_benchmark_app.sh
(py37) $ python3 Python 3.7.11 (default, Jul 27 2021, 14:32:16) [GCC 7.5.0] :: Anaconda, Inc. on linux Type "help", "copyright", "credits" or "license" for more information. >>> import cv2 >>> print(cv2.getBuildInformation()) General configuration for OpenCV 4.5.2 ===================================== Version control: 2c752ba-dirty Extra modules: Location (extra): /home/conda/feedstock_root/build_artifacts/libopencv_1625513251586/work/opencv_contrib/modules Version control (extra): 2c752ba-dirty Platform: Timestamp: 2021-07-05T19:39:20Z Host: Linux 5.8.0-1036-azure x86_64 CMake: 3.20.5 CMake generator: Ninja CMake build tool: /home/conda/feedstock_root/build_artifacts/libopencv_1625513251586/_build_env/bin/ninja Configuration: Release CPU/HW features: Baseline: SSE SSE2 SSE3 requested: SSE3 Dispatched code generation: SSE4_1 SSE4_2 FP16 AVX AVX2 AVX512_SKX requested: SSE4_1 SSE4_2 AVX FP16 AVX2 AVX512_SKX SSE4_1 (15 files): + SSSE3 SSE4_1 SSE4_2 (1 files): + SSSE3 SSE4_1 POPCNT SSE4_2 FP16 (0 files): + SSSE3 SSE4_1 POPCNT SSE4_2 FP16 AVX AVX (4 files): + SSSE3 SSE4_1 POPCNT SSE4_2 AVX AVX2 (29 files): + SSSE3 SSE4_1 POPCNT SSE4_2 FP16 FMA3 AVX AVX2 AVX512_SKX (4 files): + SSSE3 SSE4_1 POPCNT SSE4_2 FP16 FMA3 AVX AVX2 AVX_512F AVX512_COMMON AVX512_SKX C/C++: Built as dynamic libs?: YES C++ standard: 11 C++ Compiler: /home/conda/feedstock_root/build_artifacts/libopencv_1625513251586/_build_env/bin/x86_64-conda-linux-gnu-c++ (ver 9.3.0) C++ flags (Release): -fvisibility-inlines-hidden -std=c++11 -fmessage-length=0 -march=nocona -mtune=haswell -ftree-vectorize -fPIC -fstack-protector-strong -fno-plt -O2 -ffunction-sections -pipe -isystem /home/mizutu/anaconda3/envs/py37/include -fdebug-prefix-map=/home/conda/feedstock_root/build_artifacts/libopencv_1625513251586/work=/usr/local/src/conda/libopencv-4.5.2 -fdebug-prefix-map=/home/mizutu/anaconda3/envs/py37=/usr/local/src/conda-prefix -D__STDC_CONSTANT_MACROS -fsigned-char -W -Wall -Werror=return-type -Werror=non-virtual-dtor -Werror=address -Werror=sequence-point -Wformat -Werror=format-security -Wmissing-declarations -Wundef -Winit-self -Wpointer-arith -Wshadow -Wsign-promo -Wuninitialized -Wsuggest-override -Wno-delete-non-virtual-dtor -Wno-comment -Wimplicit-fallthrough=3 -Wno-strict-overflow -fdiagnostics-show-option -Wno-long-long -pthread -fomit-frame-pointer -ffunction-sections -fdata-sections -msse -msse2 -msse3 -fopenmp -O3 -DNDEBUG -DNDEBUG C++ flags (Debug): -fvisibility-inlines-hidden -std=c++11 -fmessage-length=0 -march=nocona -mtune=haswell -ftree-vectorize -fPIC -fstack-protector-strong -fno-plt -O2 -ffunction-sections -pipe -isystem /home/mizutu/anaconda3/envs/py37/include -fdebug-prefix-map=/home/conda/feedstock_root/build_artifacts/libopencv_1625513251586/work=/usr/local/src/conda/libopencv-4.5.2 -fdebug-prefix-map=/home/mizutu/anaconda3/envs/py37=/usr/local/src/conda-prefix -D__STDC_CONSTANT_MACROS -fsigned-char -W -Wall -Werror=return-type -Werror=non-virtual-dtor -Werror=address -Werror=sequence-point -Wformat -Werror=format-security -Wmissing-declarations -Wundef -Winit-self -Wpointer-arith -Wshadow -Wsign-promo -Wuninitialized -Wsuggest-override -Wno-delete-non-virtual-dtor -Wno-comment -Wimplicit-fallthrough=3 -Wno-strict-overflow -fdiagnostics-show-option -Wno-long-long -pthread -fomit-frame-pointer -ffunction-sections -fdata-sections -msse -msse2 -msse3 -fopenmp -g -DDEBUG -D_DEBUG C Compiler: /home/conda/feedstock_root/build_artifacts/libopencv_1625513251586/_build_env/bin/x86_64-conda-linux-gnu-cc C flags (Release): -march=nocona -mtune=haswell -ftree-vectorize -fPIC -fstack-protector-strong -fno-plt -O2 -ffunction-sections -pipe -isystem /home/mizutu/anaconda3/envs/py37/include -fdebug-prefix-map=/home/conda/feedstock_root/build_artifacts/libopencv_1625513251586/work=/usr/local/src/conda/libopencv-4.5.2 -fdebug-prefix-map=/home/mizutu/anaconda3/envs/py37=/usr/local/src/conda-prefix -fsigned-char -W -Wall -Werror=return-type -Werror=address -Werror=sequence-point -Wformat -Werror=format-security -Wmissing-declarations -Wmissing-prototypes -Wstrict-prototypes -Wundef -Winit-self -Wpointer-arith -Wshadow -Wuninitialized -Wno-comment -Wimplicit-fallthrough=3 -Wno-strict-overflow -fdiagnostics-show-option -Wno-long-long -pthread -fomit-frame-pointer -ffunction-sections -fdata-sections -msse -msse2 -msse3 -fopenmp -O3 -DNDEBUG -DNDEBUG C flags (Debug): -march=nocona -mtune=haswell -ftree-vectorize -fPIC -fstack-protector-strong -fno-plt -O2 -ffunction-sections -pipe -isystem /home/mizutu/anaconda3/envs/py37/include -fdebug-prefix-map=/home/conda/feedstock_root/build_artifacts/libopencv_1625513251586/work=/usr/local/src/conda/libopencv-4.5.2 -fdebug-prefix-map=/home/mizutu/anaconda3/envs/py37=/usr/local/src/conda-prefix -fsigned-char -W -Wall -Werror=return-type -Werror=address -Werror=sequence-point -Wformat -Werror=format-security -Wmissing-declarations -Wmissing-prototypes -Wstrict-prototypes -Wundef -Winit-self -Wpointer-arith -Wshadow -Wuninitialized -Wno-comment -Wimplicit-fallthrough=3 -Wno-strict-overflow -fdiagnostics-show-option -Wno-long-long -pthread -fomit-frame-pointer -ffunction-sections -fdata-sections -msse -msse2 -msse3 -fopenmp -g -DDEBUG -D_DEBUG Linker flags (Release): -Wl,--exclude-libs,libippicv.a -Wl,--exclude-libs,libippiw.a -Wl,-O2 -Wl,--sort-common -Wl,--as-needed -Wl,-z,relro -Wl,-z,now -Wl,--disable-new-dtags -Wl,--gc-sections -Wl,-rpath,/home/mizutu/anaconda3/envs/py37/lib -Wl,-rpath-link,/home/mizutu/anaconda3/envs/py37/lib -L/home/mizutu/anaconda3/envs/py37/lib -Wl,--gc-sections -Wl,--as-needed Linker flags (Debug): -Wl,--exclude-libs,libippicv.a -Wl,--exclude-libs,libippiw.a -Wl,-O2 -Wl,--sort-common -Wl,--as-needed -Wl,-z,relro -Wl,-z,now -Wl,--disable-new-dtags -Wl,--gc-sections -Wl,-rpath,/home/mizutu/anaconda3/envs/py37/lib -Wl,-rpath-link,/home/mizutu/anaconda3/envs/py37/lib -L/home/mizutu/anaconda3/envs/py37/lib -Wl,--gc-sections -Wl,--as-needed ccache: NO Precompiled headers: NO Extra dependencies: dl m pthread rt 3rdparty dependencies: OpenCV modules: To be built: alphamat aruco bgsegm bioinspired calib3d ccalib core cvv datasets dnn dnn_objdetect dnn_superres dpm face features2d flann freetype fuzzy gapi hdf hfs highgui img_hash imgcodecs imgproc intensity_transform line_descriptor mcc ml objdetect optflow phase_unwrapping photo plot python3 quality rapid reg rgbd saliency shape stereo stitching structured_light superres surface_matching text tracking video videoio videostab wechat_qrcode xfeatures2d ximgproc xobjdetect xphoto Disabled: world Disabled by dependency: - Unavailable: cnn_3dobj cudaarithm cudabgsegm cudacodec cudafeatures2d cudafilters cudaimgproc cudalegacy cudaobjdetect cudaoptflow cudastereo cudawarping cudev java julia matlab ovis python2 sfm ts viz Applications: apps Documentation: NO Non-free algorithms: NO GUI: QT: YES (ver 5.12.1) QT OpenGL support: NO Media I/O: ZLib: /home/mizutu/anaconda3/envs/py37/lib/libz.so (ver 1.2.11) JPEG: /home/mizutu/anaconda3/envs/py37/lib/libjpeg.so (ver 90) WEBP: /home/mizutu/anaconda3/envs/py37/lib/libwebp.so (ver encoder: 0x020f) PNG: /home/mizutu/anaconda3/envs/py37/lib/libpng.so (ver 1.6.37) TIFF: /home/mizutu/anaconda3/envs/py37/lib/libtiff.so (ver 42 / 4.3.0) JPEG 2000: /home/mizutu/anaconda3/envs/py37/lib/libjasper.so (ver 1.900.1) OpenEXR: build (ver 2.3.0) HDR: YES SUNRASTER: YES PXM: YES PFM: YES Video I/O: FFMPEG: YES avcodec: YES (58.91.100) avformat: YES (58.45.100) avutil: YES (56.51.100) swscale: YES (5.7.100) avresample: YES (4.0.0) v4l/v4l2: YES (linux/videodev2.h) Parallel framework: OpenMP Trace: YES (with Intel ITT) Other third-party libraries: Intel IPP: 2020.0.0 Gold [2020.0.0] at: /home/conda/feedstock_root/build_artifacts/libopencv_1625513251586/work/build/3rdparty/ippicv/ippicv_lnx/icv Intel IPP IW: sources (2020.0.0) at: /home/conda/feedstock_root/build_artifacts/libopencv_1625513251586/work/build/3rdparty/ippicv/ippicv_lnx/iw Lapack: YES (lapack cblas) Eigen: YES (ver 3.3.9) Custom HAL: NO Protobuf: /home/mizutu/anaconda3/envs/py37/lib/libprotobuf.so (3.16.0) Python 3: Interpreter: /home/mizutu/anaconda3/envs/py37/bin/python (ver 3.7.8) Libraries: /home/mizutu/anaconda3/envs/py37/lib/libpython3.7.som (ver 3.7.8) numpy: /home/mizutu/anaconda3/envs/py37/lib/python3.7/site-packages/numpy/core/include (ver 1.17.5) install path: /home/mizutu/anaconda3/envs/py37/lib/python3.7/site-packages Python (for build): /home/mizutu/anaconda3/envs/py37/bin/python Java: ant: NO JNI: NO Java wrappers: NO Java tests: NO Install to: /home/mizutu/anaconda3/envs/py37 -----------------------------------------------------------------
(py37) $ ./_text_detection_demo.sh [text_detection_demo.sh] 'text_detection_demo' Run !! MODEL: FP32 DEVICE: CPU COMMAND: ./text_detection_demo -loop -m_td /home/mizutu/model/intel/FP32/text-detection-0004.xml -m_tr /home/mizutu/model/intel/FP32/text-recognition-0012.xml -i /home/mizutu/Images/text-img.jpg -d_td CPU -d_tr CPU ./text_detection_demo: error while loading shared libraries: libopencv_highgui.so.4.5: cannot open shared object file: No such file or directory
(py37) $ conda search libopencv_highgui.so.4.5 Loading channels: done No match found for: libopencv_highgui.so.4.5. Search: *libopencv_highgui.so.4.5* PackagesNotFoundError: The following packages are not available from current channels: - libopencv_highgui.so.4.5 Current channels: - https://repo.anaconda.com/pkgs/main/linux-64 - https://repo.anaconda.com/pkgs/main/noarch - https://repo.anaconda.com/pkgs/r/linux-64 - https://repo.anaconda.com/pkgs/r/noarch To search for alternate channels that may provide the conda package you're looking for, navigate to https://anaconda.org and use the search bar at the top of the page.
PukiWiki 1.5.2 © 2001-2019 PukiWiki Development Team. Powered by PHP 7.4.3-4ubuntu2.20. HTML convert time: 0.049 sec.