OpenVino framework installationhttps://software.intel.com/en-us/articl ... tall-linux tar xvf l_openvino_toolkit_p_2018.5.445_online.tgz
cd l_openvino_toolkit_p_2018.5.445_online
sudo -E ./install_cv_sdk_dependencies.sh
sudo -E ./install_GUI.sh
#OpenVino installed in
/opt/intel/computer_vision_sdk_2018.5.445/
#add the following to ~/.bashrc
source /opt/intel/computer_vision_sdk/bin/setupvars.sh
Configure the NCS USB driver cat <<EOF > 97-usbboot.rules
SUBSYSTEM=="usb", ATTRS{idProduct}=="2150", ATTRS{idVendor}=="03e7", GROUP="users", MODE="0666", ENV{ID_MM_DEVICE_IGNORE}="1"
SUBSYSTEM=="usb", ATTRS{idProduct}=="2485", ATTRS{idVendor}=="03e7", GROUP="users", MODE="0666", ENV{ID_MM_DEVICE_IGNORE}="1"
SUBSYSTEM=="usb", ATTRS{idProduct}=="f63b", ATTRS{idVendor}=="03e7", GROUP="users", MODE="0666", ENV{ID_MM_DEVICE_IGNORE}="1"
EOF
sudo cp 97-usbboot.rules /etc/udev/rules.d/
sudo udevadm control --reload-rules
sudo udevadm trigger
sudo ldconfig
rm 97-usbboot.rules
#optionaly perofrm a sanity check, this will ensure there are no invalid key/value pair errors. This would indicate an issue with the udev rules
sudo udevadm test /dev/sda
# ensure VPU support
sudo apt install libusb-1.0-0 libboost-program-options1.58.0 libboost-thread1.58.0 libboost-filesystem1.58.0 libssl1.0.0 libudev1 libjson-c2
Run the demos#Image classification
#first configure the ModelOptimizer for various ML frameworks, incl. Tensorflow, Caffe etc.
cd ~/intel/computer_vision_sdk/deployment_tools/model_optimizer/install_prerequisites/
./install_prerequisites.sh
cd ~/intel/computer_vision_sdk/deployment_tools/demo
./demo_squeezenet_download_convert_run.sh -d MYRIAD
#object detection (traffic camera)
cd ~/intel/computer_vision_sdk/deployment_tools/demo
./demo_security_barrier_camera.sh -d MYRIAD
#run only the inference
cd ~/inference_engine_samples/intel64/Release
./security_barrier_camera_demo -i ~/intel/computer_vision_sdk/deployment_tools/demo/car_1.bmp -d MYRIAD -m ~/intel/computer_vision_sdk/deployment_tools/intel_models/vehicle-license-plate-detection-barrier-0106/FP16/vehicle-license-plate-detection-barrier-0106.xml -d_va MYRIAD -m_va ~/intel/computer_vision_sdk/deployment_tools/intel_models/vehicle-attributes-recognition-barrier-0039/FP16/vehicle-attributes-recognition-barrier-0039.xml -d_lpr MYRIAD -m_lpr ~/intel/computer_vision_sdk/deployment_tools/intel_models/license-plate-recognition-barrier-0001/FP16/license-plate-recognition-barrier-0001.xml
#Face, Emotion, Age, Gender, and Pose Detection (requires a webcam)
cd ~/inference_engine_samples/intel64/Release
./interactive_face_detection_demo -d MYRIAD -m ~/intel/computer_vision_sdk/deployment_tools/intel_models/face-detection-retail-0004/FP16/face-detection-retail-0004.xml -d_ag MYRIAD -m_ag ~/intel/computer_vision_sdk/deployment_tools/intel_models/age-gender-recognition-retail-0013/FP16/age-gender-recognition-retail-0013.xml -d_em MYRIAD -m_em ~/intel/computer_vision_sdk/deployment_tools/intel_models/emotions-recognition-retail-0003/FP16/emotions-recognition-retail-0003.xml -d_hp MYRIAD -m_hp ~/intel/computer_vision_sdk/deployment_tools/intel_models/head-pose-estimation-adas-0001/FP16/head-pose-estimation-adas-0001.xml
Run pre-trained models on NCS2#Download the pretrained models
cd ~/intel/computer_vision_sdk/deployment_tools/model_downloader
# List what is avilable for OpenVINO
python3 downloader.py --print_all
# download GoogLeNet V2
python3 downloader.py --name googlenet-v2
# the model is available here
model_downloader/classification/googlenet/v2/caffe/googlenet-v2.caffemodel
model_downloader/classification/googlenet/v2/caffe/googlenet-v2.prototxt
#convert the models into IR files
cd ~/intel/computer_vision_sdk/deployment_tools/model_downloader/classification/googlenet/v2/caffe
# init the OpenVINO env
source ~/intel/computer_vision_sdk/bin/setupvars.sh
# Use model optimizer to convert googlenet.caffemodel to IR
mo.py --data_type FP16 --input_model googlenet-v2.caffemodel --input_proto googlenet-v2.prototxt
# the IR file is svailable here
model_downloader/classification/googlenet/v2/caffe/googlenet-v2.bin
model_downloader/classification/googlenet/v2/caffe/googlenet-v2.mapping
model_downloader/classification/googlenet/v2/caffe/googlenet-v2.xml
#Run the IR model
cd ~/intel/computer_vision_sdk/deployment_tools/inference_engine/samples/python_samples
# get a test image
wget -N
https://upload.wikimedia.org/wikipedia/ ... n_snow.jpg# init OpenVino
source ~/intel/computer_vision_sdk/bin/setupvars.sh
# Run an inference on this image using a built-in sample code
python3 classification_sample.py -m ~/intel/computer_vision_sdk/deployment_tools/model_downloader/classification/googlenet/v2/caffe/googlenet-v2.xml -i Felis_catus-cat_on_snow.jpg -d MYRIAD --labels