私的AI研究会 > OpenVINO8
OpenVINO™ツールキットのWindows版がしっくりこないのでLinux で試すことにする。
「Model Optimizer(MO) モデル変換ツール」の使用が目的。
sudo apt install openssh-server sudo apt install net-tools
$ vi ~/.vimrc set nocompatible set backspace=indent,eol,start set expandtab set tabstop=4 set shiftwidth=4 set autoindent
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*
~$ cd ダウンロード ~/ダウンロード$ ls l_openvino_toolkit_p_2021.2.185.tgz ~/ダウンロード$ tar -xvzf l_openvino_toolkit_p_2021.2.185.tgz
~/ダウンロード$ ls l_openvino_toolkit_p_2021.2.185 l_openvino_toolkit_p_2021.2.185.tgz ~/ダウンロード$ cd l_openvino_toolkit_p_2021.2.185 ~/ダウンロード/l_openvino_toolkit_p_2021.2.185$ ls EULA.txt install.sh install_openvino_dependencies.sh rpm PUBLIC_KEY.PUB install_GUI.sh pset silent.cfg ~/ダウンロード/l_openvino_toolkit_p_2021.2.185$ sudo ./install_GUI.sh Cannot run setup in graphical mode. Setup will be continued in command-line mode. -------------------------------------------------------------------------------- Initializing, please wait... -------------------------------------------------------------------------------- : :
~/ダウンロード/l_openvino_toolkit_p_2021.2.185$ cd /opt/intel/openvino_2021/install_dependencies /opt/intel/openvino_2021/install_dependencies$ sudo -E ./install_openvino_dependencies.sh This script installs the following OpenVINO 3rd-party dependencies: 1. GTK+, FFmpeg and GStreamer libraries used by OpenCV 2. libusb library required for Myriad plugin for Inference Engine 3. build dependencies for OpenVINO samples 4. build dependencies for GStreamer Plugins ヒット:1 http://jp.archive.ubuntu.com/ubuntu focal InRelease 取得:2 http://jp.archive.ubuntu.com/ubuntu focal-updates InRelease [114 kB] : :
/opt/intel/openvino_2021/install_dependencies$ 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。
/opt/intel/openvino_2021/install_dependencies$ cd /opt/intel/openvino_2021/deployment_tools/model_optimizer/install_prerequisites /opt/intel/openvino_2021/deployment_tools/model_optimizer/install_prerequisites$ sudo ./install_prerequisites.sh ヒット:1 http://jp.archive.ubuntu.com/ubuntu focal InRelease ヒット:2 http://jp.archive.ubuntu.com/ubuntu focal-updates InRelease ヒット:3 http://jp.archive.ubuntu.com/ubuntu focal-backports InRelease 取得:4 http://security.ubuntu.com/ubuntu focal-security InRelease [109 kB] 109 kB を 1秒 で取得しました (72.9 kB/s) : :
mizutu@ubuntu2004dk:/opt/intel/openvino_2021/deployment_tools/demo$ ./demo_security_barrier_camera.sh : Downloading Intel models target_precision = FP16 Run python3 /opt/intel/openvino_2021/deployment_tools/open_model_zoo/tools/downloader/downloader.py --name vehicle-license-plate-detection-barrier-0106 --output_dir /home/mizutu/openvino_models/ir --cache_dir /home/mizutu/openvino_models/cache ################|| Downloading vehicle-license-plate-detection-barrier-0106 ||################ : Run python3 /opt/intel/openvino_2021/deployment_tools/open_model_zoo/tools/downloader/downloader.py --name license-plate-recognition-barrier-0001 --output_dir /home/mizutu/openvino_models/ir --cache_dir /home/mizutu/openvino_models/cache ################|| Downloading license-plate-recognition-barrier-0001 ||################ : Run python3 /opt/intel/openvino_2021/deployment_tools/open_model_zoo/tools/downloader/downloader.py --name vehicle-attributes-recognition-barrier-0039 --output_dir /home/mizutu/openvino_models/ir --cache_dir /home/mizutu/openvino_models/cache ################|| Downloading vehicle-attributes-recognition-barrier-0039 ||################ : ################################################### Run Inference Engine security_barrier_camera demo Run ./security_barrier_camera_demo -d CPU -d_va CPU -d_lpr CPU -i /opt/intel/openvino_2021/deployment_tools/demo/car_1.bmp -m /home/mizutu/openvino_models/ir/intel/vehicle-license-plate-detection-barrier-0106/FP16/vehicle-license-plate-detection-barrier-0106.xml -m_lpr /home/mizutu/openvino_models/ir/intel/license-plate-recognition-barrier-0001/FP16/license-plate-recognition-barrier-0001.xml -m_va /home/mizutu/openvino_models/ir/intel/vehicle-attributes-recognition-barrier-0039/FP16/vehicle-attributes-recognition-barrier-0039.xml [ INFO ] InferenceEngine: API version ......... 2.1 Build ........... 2021.2.0-1877-176bdf51370-releases/2021/2 [ INFO ] Files were added: 1 [ INFO ] /opt/intel/openvino_2021/deployment_tools/demo/car_1.bmp [ INFO ] Loading device CPU [ INFO ] CPU MKLDNNPlugin version ......... 2.1 Build ........... 2021.2.0-1877-176bdf51370-releases/2021/2 [ INFO ] Loading detection model to the CPU plugin [ INFO ] Loading Vehicle Attribs model to the CPU plugin [ INFO ] Loading Licence Plate Recognition (LPR) model to the CPU plugin [ INFO ] Number of InferRequests: 1 (detection), 3 (classification), 3 (recognition) [ INFO ] 4 streams for CPU [ INFO ] Display resolution: 1920x1080 [ INFO ] Number of allocated frames: 3 [ INFO ] Resizable input with support of ROI crop and auto resize is disabled 0.1FPS for (3 / 1) frames Detection InferRequests usage: 0.0% [ INFO ] Execution successful ################################################### Demo completed successfully.
mizutu@ubuntu2004dk:/opt/intel/openvino_2021/deployment_tools/demo$ ./demo_squeezenet_download_convert_run.sh target_precision = FP16 [setupvars.sh] OpenVINO environment initialized Run python3 /opt/intel/openvino_2021/deployment_tools/open_model_zoo/tools/downloader/downloader.py --name squeezenet1.1 --output_dir /home/mizutu/openvino_models/models --cache_dir /home/mizutu/openvino_models/cache ################|| Downloading squeezenet1.1 ||################ : ################################################### Run Inference Engine classification sample Run ./classification_sample_async -d CPU -i /opt/intel/openvino_2021/deployment_tools/demo/car.png -m /home/mizutu/openvino_models/ir/public/squeezenet1.1/FP16/squeezenet1.1.xml [ INFO ] InferenceEngine: API version ............ 2.1 Build .................. 2021.2.0-1877-176bdf51370-releases/2021/2 Description ....... API [ INFO ] Parsing input parameters [ INFO ] Parsing input parameters [ INFO ] Files were added: 1 [ INFO ] /opt/intel/openvino_2021/deployment_tools/demo/car.png [ INFO ] Creating Inference Engine CPU MKLDNNPlugin version ......... 2.1 Build ........... 2021.2.0-1877-176bdf51370-releases/2021/2 [ INFO ] Loading network files [ INFO ] Preparing input blobs [ WARNING ] Image is resized from (787, 259) to (227, 227) [ INFO ] Batch size is 1 [ INFO ] Loading model to the device [ INFO ] Create infer request [ INFO ] Start inference (10 asynchronous executions) [ INFO ] Completed 1 async request execution [ INFO ] Completed 2 async request execution [ INFO ] Completed 3 async request execution [ INFO ] Completed 4 async request execution [ INFO ] Completed 5 async request execution [ INFO ] Completed 6 async request execution [ INFO ] Completed 7 async request execution [ INFO ] Completed 8 async request execution [ INFO ] Completed 9 async request execution [ INFO ] Completed 10 async request execution [ INFO ] Processing output blobs Top 10 results: Image /opt/intel/openvino_2021/deployment_tools/demo/car.png classid probability label ------- ----------- ----- 817 0.6853030 sports car, sport car 479 0.1835197 car wheel 511 0.0917197 convertible 436 0.0200694 beach wagon, station wagon, wagon, estate car, beach waggon, station waggon, waggon 751 0.0069604 racer, race car, racing car 656 0.0044177 minivan 717 0.0024739 pickup, pickup truck 581 0.0017788 grille, radiator grille 468 0.0013083 cab, hack, taxi, taxicab 661 0.0007443 Model T [ INFO ] Execution successful [ INFO ] This sample is an API example, for any performance measurements please use the dedicated benchmark_app tool ################################################### Demo completed successfully. ~
mizutu@ubuntu2004dk:/opt/intel/openvino_2021/deployment_tools/demo$ ./demo_benchmark_app.sh target_precision = FP16 [setupvars.sh] OpenVINO environment initialized Run python3 /opt/intel/openvino_2021/deployment_tools/open_model_zoo/tools/downloader/downloader.py --name squeezenet1.1 --output_dir /home/mizutu/openvino_models/models --cache_dir /home/mizutu/openvino_models/cache ################|| Downloading squeezenet1.1 ||################ : ################################################### Run Inference Engine benchmark app Run ./benchmark_app -d CPU -i /opt/intel/openvino_2021/deployment_tools/demo/car.png -m /home/mizutu/openvino_models/ir/public/squeezenet1.1/FP16/squeezenet1.1.xml -pc -niter 1000 [Step 1/11] Parsing and validating input arguments [ INFO ] Parsing input parameters [ INFO ] Files were added: 1 [ INFO ] /opt/intel/openvino_2021/deployment_tools/demo/car.png [Step 2/11] Loading Inference Engine [ INFO ] InferenceEngine: API version ............ 2.1 Build .................. 2021.2.0-1877-176bdf51370-releases/2021/2 Description ....... API [ INFO ] Device info: CPU MKLDNNPlugin version ......... 2.1 Build ........... 2021.2.0-1877-176bdf51370-releases/2021/2 [Step 3/11] Setting device configuration [ WARNING ] -nstreams default value is determined automatically for CPU device. Although the automatic selection usually provides a reasonable performance,but it still may be non-optimal for some cases, for more information look at README. [Step 4/11] Reading network files [ INFO ] Loading network files [ INFO ] Read network took 14.66 ms [Step 5/11] Resizing network to match image sizes and given batch [ INFO ] Network batch size: 1 [Step 6/11] Configuring input of the model [Step 7/11] Loading the model to the device [ INFO ] Load network took 137.29 ms [Step 8/11] Setting optimal runtime parameters [Step 9/11] Creating infer requests and filling input blobs with images [ INFO ] Network input 'data' precision U8, dimensions (NCHW): 1 3 227 227 [ WARNING ] Some image input files will be duplicated: 4 files are required but only 1 are provided [ INFO ] Infer Request 0 filling [ INFO ] Prepare image /opt/intel/openvino_2021/deployment_tools/demo/car.png [ WARNING ] Image is resized from (787, 259) to (227, 227) [ INFO ] Infer Request 1 filling [ INFO ] Prepare image /opt/intel/openvino_2021/deployment_tools/demo/car.png [ WARNING ] Image is resized from (787, 259) to (227, 227) [ INFO ] Infer Request 2 filling [ INFO ] Prepare image /opt/intel/openvino_2021/deployment_tools/demo/car.png [ WARNING ] Image is resized from (787, 259) to (227, 227) [ INFO ] Infer Request 3 filling [ INFO ] Prepare image /opt/intel/openvino_2021/deployment_tools/demo/car.png [ WARNING ] Image is resized from (787, 259) to (227, 227) [Step 10/11] Measuring performance (Start inference asynchronously, 4 inference requests using 4 streams for CPU, limits: 1000 iterations) [ INFO ] First inference took 10.22 ms [Step 11/11] Dumping statistics report [ INFO ] Pefrormance counts for 0-th infer request: data/mean_value_const_biases NOT_RUN layerType: Const realTime: 0 cpu: 0 execType: unknown_FP32 ; : [ INFO ] Pefrormance counts for 3-th infer request: data/mean_value_const_biases NOT_RUN layerType: Const realTime: 0 cpu: 0 execType: unknown_FP32 data/mean_value_const_weights NOT_RUN layerType: Const realTime: 0 cpu: 0 execType: unknown_FP32 data/mean_value EXECUTED layerType: ScaleShift realTime: 87 cpu: 87 execType: jit_avx2_I8 conv1 EXECUTED layerType: Convolution realTime: 719 cpu: 719 execType: jit_avx2_FP32 relu_conv1 NOT_RUN layerType: ReLU realTime: 0 cpu: 0 execType: undef pool1 EXECUTED layerType: Pooling realTime: 398 cpu: 398 execType: jit_avx_FP32 fire2/squeeze1x1 EXECUTED layerType: Convolution realTime: 103 cpu: 103 execType: jit_avx2_1x1_FP32 fire2/relu_squeeze1x1 NOT_RUN layerType: ReLU realTime: 0 cpu: 0 execType: undef fire2/expand1x1 EXECUTED layerType: Convolution realTime: 103 cpu: 103 execType: jit_avx2_1x1_FP32 fire2/relu_expand1x1 NOT_RUN layerType: ReLU realTime: 0 cpu: 0 execType: undef fire2/expand3x3 EXECUTED layerType: Convolution realTime: 735 cpu: 735 execType: jit_avx2_FP32 fire2/relu_expand3x3 NOT_RUN layerType: ReLU realTime: 0 cpu: 0 execType: undef fire2/concat EXECUTED layerType: Concat realTime: 4 cpu: 4 execType: unknown_FP32 fire3/squeeze1x1 EXECUTED layerType: Convolution realTime: 222 cpu: 222 execType: jit_avx2_1x1_FP32 fire3/relu_squeeze1x1 NOT_RUN layerType: ReLU realTime: 0 cpu: 0 execType: undef fire3/expand1x1 EXECUTED layerType: Convolution realTime: 102 cpu: 102 execType: jit_avx2_1x1_FP32 fire3/relu_expand1x1 NOT_RUN layerType: ReLU realTime: 0 cpu: 0 execType: undef fire3/expand3x3 EXECUTED layerType: Convolution realTime: 727 cpu: 727 execType: jit_avx2_FP32 fire3/relu_expand3x3 NOT_RUN layerType: ReLU realTime: 0 cpu: 0 execType: undef fire3/concat EXECUTED layerType: Concat realTime: 2 cpu: 2 execType: unknown_FP32 pool3 EXECUTED layerType: Pooling realTime: 196 cpu: 196 execType: jit_avx_FP32 fire4/squeeze1x1 EXECUTED layerType: Convolution realTime: 96 cpu: 96 execType: jit_avx2_1x1_FP32 fire4/relu_squeeze1x1 NOT_RUN layerType: ReLU realTime: 0 cpu: 0 execType: undef fire4/expand1x1 EXECUTED layerType: Convolution realTime: 89 cpu: 89 execType: jit_avx2_1x1_FP32 fire4/relu_expand1x1 NOT_RUN layerType: ReLU realTime: 0 cpu: 0 execType: undef fire4/expand3x3 EXECUTED layerType: Convolution realTime: 744 cpu: 744 execType: jit_avx2_FP32 fire4/relu_expand3x3 NOT_RUN layerType: ReLU realTime: 0 cpu: 0 execType: undef fire4/concat EXECUTED layerType: Concat realTime: 2 cpu: 2 execType: unknown_FP32 fire5/squeeze1x1 EXECUTED layerType: Convolution realTime: 197 cpu: 197 execType: jit_avx2_1x1_FP32 fire5/relu_squeeze1x1 NOT_RUN layerType: ReLU realTime: 0 cpu: 0 execType: undef fire5/expand1x1 EXECUTED layerType: Convolution realTime: 90 cpu: 90 execType: jit_avx2_1x1_FP32 fire5/relu_expand1x1 NOT_RUN layerType: ReLU realTime: 0 cpu: 0 execType: undef fire5/expand3x3 EXECUTED layerType: Convolution realTime: 746 cpu: 746 execType: jit_avx2_FP32 fire5/relu_expand3x3 NOT_RUN layerType: ReLU realTime: 0 cpu: 0 execType: undef fire5/concat EXECUTED layerType: Concat realTime: 2 cpu: 2 execType: unknown_FP32 pool5 EXECUTED layerType: Pooling realTime: 80 cpu: 80 execType: jit_avx_FP32 fire6/squeeze1x1 EXECUTED layerType: Convolution realTime: 66 cpu: 66 execType: jit_avx2_1x1_FP32 fire6/relu_squeeze1x1 NOT_RUN layerType: ReLU realTime: 0 cpu: 0 execType: undef fire6/expand1x1 EXECUTED layerType: Convolution realTime: 51 cpu: 51 execType: jit_avx2_1x1_FP32 fire6/relu_expand1x1 NOT_RUN layerType: ReLU realTime: 0 cpu: 0 execType: undef fire6/expand3x3 EXECUTED layerType: Convolution realTime: 434 cpu: 434 execType: jit_avx2_FP32 fire6/relu_expand3x3 NOT_RUN layerType: ReLU realTime: 0 cpu: 0 execType: undef fire6/concat EXECUTED layerType: Concat realTime: 1 cpu: 1 execType: unknown_FP32 fire7/squeeze1x1 EXECUTED layerType: Convolution realTime: 99 cpu: 99 execType: jit_avx2_1x1_FP32 fire7/relu_squeeze1x1 NOT_RUN layerType: ReLU realTime: 0 cpu: 0 execType: undef fire7/expand1x1 EXECUTED layerType: Convolution realTime: 50 cpu: 50 execType: jit_avx2_1x1_FP32 fire7/relu_expand1x1 NOT_RUN layerType: ReLU realTime: 0 cpu: 0 execType: undef fire7/expand3x3 EXECUTED layerType: Convolution realTime: 445 cpu: 445 execType: jit_avx2_FP32 fire7/relu_expand3x3 NOT_RUN layerType: ReLU realTime: 0 cpu: 0 execType: undef fire7/concat EXECUTED layerType: Concat realTime: 1 cpu: 1 execType: unknown_FP32 fire8/squeeze1x1 EXECUTED layerType: Convolution realTime: 140 cpu: 140 execType: jit_avx2_1x1_FP32 fire8/relu_squeeze1x1 NOT_RUN layerType: ReLU realTime: 0 cpu: 0 execType: undef fire8/expand1x1 EXECUTED layerType: Convolution realTime: 92 cpu: 92 execType: jit_avx2_1x1_FP32 fire8/relu_expand1x1 NOT_RUN layerType: ReLU realTime: 0 cpu: 0 execType: undef fire8/expand3x3 EXECUTED layerType: Convolution realTime: 779 cpu: 779 execType: jit_avx2_FP32 fire8/relu_expand3x3 NOT_RUN layerType: ReLU realTime: 0 cpu: 0 execType: undef fire8/concat EXECUTED layerType: Concat realTime: 1 cpu: 1 execType: unknown_FP32 fire9/squeeze1x1 EXECUTED layerType: Convolution realTime: 179 cpu: 179 execType: jit_avx2_1x1_FP32 fire9/relu_squeeze1x1 NOT_RUN layerType: ReLU realTime: 0 cpu: 0 execType: undef fire9/expand1x1 EXECUTED layerType: Convolution realTime: 91 cpu: 91 execType: jit_avx2_1x1_FP32 fire9/relu_expand1x1 NOT_RUN layerType: ReLU realTime: 0 cpu: 0 execType: undef fire9/expand3x3 EXECUTED layerType: Convolution realTime: 779 cpu: 779 execType: jit_avx2_FP32 fire9/relu_expand3x3 NOT_RUN layerType: ReLU realTime: 0 cpu: 0 execType: undef fire9/concat EXECUTED layerType: Concat realTime: 1 cpu: 1 execType: unknown_FP32 conv10 EXECUTED layerType: Convolution realTime: 2713 cpu: 2713 execType: jit_avx2_1x1_FP32 relu_conv10 NOT_RUN layerType: ReLU realTime: 0 cpu: 0 execType: undef pool10/reduce EXECUTED layerType: Pooling realTime: 61 cpu: 61 execType: jit_avx_FP32 prob EXECUTED layerType: SoftMax realTime: 3 cpu: 3 execType: jit_avx2_FP32 prob_nChw8c_nchw_out_prob EXECUTED layerType: Reorder realTime: 7 cpu: 7 execType: jit_uni_FP32 out_prob NOT_RUN layerType: Output realTime: 0 cpu: 0 execType: unknown_FP32 Total time: 11437 microseconds Full device name: Intel(R) Core(TM) i7-6700 CPU @ 3.40GHz Count: 1000 iterations Duration: 2918.03 ms Latency: 9.65 ms Throughput: 342.70 FPS ################################################### Inference Engine benchmark app completed successfully.
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。
$ python3 /opt/intel/openvino_2021/deployment_tools/tools/model_downloader/converter.py --all : : FAILED: cocosnet colorization-siggraph colorization-v2 densenet-121-caffe2 efficientnet-b0-pytorch efficientnet-b5-pytorch efficientnet-b7-pytorch faceboxes-pytorch googlenet-v3-pytorch hbonet-0.25 hbonet-0.5 hbonet-1.0 hrnet-v2-c1-segmentation human-pose-estimation-3d-0001 midasnet mobilenet-v2-pytorch resnest-50-pytorch resnet-18-pytorch resnet-34-pytorch resnet-50-caffe2 resnet-50-pytorch shufflenet-v2-x1.0 single-human-pose-estimation-0001 squeezenet1.1-caffe2 vgg19-caffe2 yolact-resnet50-fpn-pytorch変換できないファイルも結構ある。
mizutu@ubuntu2004dk:~/model$ python3 $INTEL_OPENVINO_DIR/deployment_tools/tools/model_downloader/converter.py --name human-pose-estimation-3d-0001 ========== Converting human-pose-estimation-3d-0001 to ONNX Conversion to ONNX command: /bin/python3 /opt/intel/openvino_2021/deployment_tools/tools/model_downloader/pytorch_to_onnx.py --model-path=/home/mizutu/model/public/human-pose-estimation-3d-0001 --model-name=PoseEstimationWithMobileNet --model-param=is_convertible_by_mo=True --import-module=model --weights=/home/mizutu/model/public/human-pose-estimation-3d-0001/human-pose-estimation-3d-0001.pth --input-shape=1,3,256,448 --input-names=data --output-names=features,heatmaps,pafs --output-file=/home/mizutu/model/public/human-pose-estimation-3d-0001/human-pose-estimation-3d-0001.onnx Traceback (most recent call last): File "/opt/intel/openvino_2021/deployment_tools/tools/model_downloader/pytorch_to_onnx.py", line 10, in <module> import torch ModuleNotFoundError: No module named 'torch' FAILED: human-pose-estimation-3d-0001オフィシャルサイト PyTorch FROM RESEARCH TO PRODUCTION にアクセスして、インストールパラメータを取得する。
pip install torch==1.8.0+cpu torchvision==0.9.0+cpu torchaudio==0.8.0 -f https://download.pytorch.org/whl/torch_stable.html
mizutu@ubuntu2004dk:~/model$ pip3 install torch==1.8.0+cpu torchvision==0.9.0+cpu torchaudio==0.8.0 -f https://download.pytorch.org/whl/torch_stable.html Looking in links: https://download.pytorch.org/whl/torch_stable.html Collecting torch==1.8.0+cpu Downloading https://download.pytorch.org/whl/cpu/torch-1.8.0%2Bcpu-cp38-cp38-linux_x86_64.whl (169.1 MB) |████████████████████████████████| 169.1 MB 39 kB/s Collecting torchvision==0.9.0+cpu Downloading https://download.pytorch.org/whl/cpu/torchvision-0.9.0%2Bcpu-cp38-cp38-linux_x86_64.whl (13.3 MB) |████████████████████████████████| 13.3 MB 14.6 MB/s Collecting torchaudio==0.8.0 Downloading torchaudio-0.8.0-cp38-cp38-manylinux1_x86_64.whl (1.9 MB) |████████████████████████████████| 1.9 MB 3.9 MB/s Requirement already satisfied: numpy in /usr/local/lib/python3.8/dist-packages (from torch==1.8.0+cpu) (1.18.5) Requirement already satisfied: typing-extensions in /usr/local/lib/python3.8/dist-packages (from torch==1.8.0+cpu) (3.7.4.3) Requirement already satisfied: pillow>=4.1.1 in /usr/lib/python3/dist-packages (from torchvision==0.9.0+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-1.8.0+cpu torchaudio-0.8.0 torchvision-0.9.0+cpu
$ python3 /opt/intel/openvino_2021/deployment_tools/tools/model_downloader/converter.py --all : : FAILED: cocosnet efficientdet-d0-tf efficientdet-d1-tfかなりエラーが少なくなった。(2021/03/21)
~/model/intel/FP16 ~/model/intel/FP32 ~/model/public/FP16 ~/model/public/FP32