Ilya Lavrenov
0df7dab345
* OV new package structure * Fixes * More fixes * Fixed code style in ngraph tests * Fixes * Paths to setupvars inside demo scripts * Fixed demo_security_barrier_camera.sh * Added setupvars.sh to old location as well * Fixed path * Fixed MO install path in .co * Fixed install of public headers * Fixed frontends installation * Updated DM config files * Keep opencv in the root * Improvements * Fixes for demo scripts * Added path to TBB * Fix for MO unit-tests * Fixed tests on Windows * Reverted arch * Removed arch * Reverted arch back: second attemp * System type * Fix for Windows * Resolve merge conflicts * Fixed path * Path for Windows * Added debug for Windows * Added requirements_dev.txt to install * Fixed wheel's setup.py * Fixed lin build * Fixes after merge * Fix 2 * Fixes * Frontends path * Fixed deployment manager * Fixed Windows * Added cldnn unit tests installation * Install samples * Fix samples * Fix path for samples * Proper path * Try to fix MO hardcodes * samples binary location * MO print * Added install for libopencv_c_wrapper.so * Added library destination * Fixed install rule for samples * Updated demo scripts readme.md * Samples * Keep source permissions for Python samples * Fixed python * Updated path to fast run scripts * Fixed C samples tests * Removed debug output * Small fixes * Try to unify prefix
2.0 KiB
OpenVINO™ MonoDepth Python Demo
This tutorial describes the example from the following YouTube* video: ///
To learn more about how to run the MonoDepth Python* demo application, refer to the documentation.
Tested on OpenVINO™ 2021, Ubuntu 18.04.
1. Set Environment
Define the OpenVINO™ install directory:
export OV=/opt/intel/openvino_2022/
Define the working directory. Make sure the directory exist:
export WD=~/MonoDepth_Python/
2. Install Prerequisits
Initialize OpenVINO™:
source $OV/setupvars.sh
Install the Model Optimizer prerequisites:
cd $OV/tools/model_optimizer/install_prerequisites/
sudo ./install_prerequisites.sh
Install the Model Downloader prerequisites:
cd $OV/extras/open_model_zoo/tools/downloader/
python3 -mpip install --user -r ./requirements.in
sudo python3 -mpip install --user -r ./requirements-pytorch.in
sudo python3 -mpip install --user -r ./requirements-caffe2.in
3. Download Models
Download all models from the Demo Models list:
python3 $OV/extras/open_model_zoo/tools/downloader/downloader.py --list $OV/deployment_tools/inference_engine/demos/python_demos/monodepth_demo/models.lst -o $WD
4. Convert Models to Intermediate Representation (IR)
Use the convert script to convert the models to ONNX*, and then to IR format:
cd $WD
python3 $OV/extras/open_model_zoo/tools/downloader/converter.py --list $OV/deployment_tools/inference_engine/demos/python_demos/monodepth_demo/models.lst
5. Run Demo
Install required Python modules, for example, kiwisolver or cycler, if you get missing module indication.
Use your input image:
python3 $OV/inference_engine/demos/python_demos/monodepth_demo/monodepth_demo.py -m $WD/public/midasnet/FP32/midasnet.xml -i input-image.jpg
Check the result depth image:
eog disp.png &
You can also try to use another model. Note that the algorithm is the same, but the depth map will be different.