- [Build Steps](#build-steps-3)
- [Use Custom OpenCV Builds for Inference Engine](#use-custom-opencv-builds-for-inference-engine)
- [Add Inference Engine to Your Project](#add-inference-engine-to-your-project)
-- [(Optional) Additional Installation Steps for the Intel® Movidius™ Neural Compute Stick and Neural Compute Stick 2](#optional-additional-installation-steps-for-the-intel-movidius-neural-compute-stick-and-neural-compute-stick-2)
+- [(Optional) Additional Installation Steps for the Intel® Neural Compute Stick 2](#optional-additional-installation-steps-for-the-intel-movidius-neural-compute-stick-and-neural-compute-stick-2)
- [For Linux, Raspbian Stretch* OS](#for-linux-raspbian-stretch-os)
- [Next Steps](#next-steps)
- [Additional Resources](#additional-resources)
| CPU plugin | Intel® Xeon® with Intel® AVX2 and AVX512, Intel® Core™ Processors with Intel® AVX2, Intel® Atom® Processors with Intel® SSE |
| GPU plugin | Intel® Processor Graphics, including Intel® HD Graphics and Intel® Iris® Graphics |
| GNA plugin | Intel® Speech Enabling Developer Kit, Amazon Alexa\* Premium Far-Field Developer Kit, Intel® Pentium® Silver processor J5005, Intel® Celeron® processor J4005, Intel® Core™ i3-8121U processor |
-| MYRIAD plugin | Intel® Movidius™ Neural Compute Stick powered by the Intel® Movidius™ Myriad™ 2, Intel® Neural Compute Stick 2 powered by the Intel® Movidius™ Myriad™ X |
+| MYRIAD plugin | Intel® Neural Compute Stick 2 powered by the Intel® Movidius™ Myriad™ X |
| Heterogeneous plugin | Heterogeneous plugin enables computing for inference on one network on several Intel® devices. |
## Build on Linux\* Systems
- GCC\* 4.8 or higher to build the Inference Engine
- Python 3.6 or higher for Inference Engine Python API wrapper
- (Optional) [Install Intel® Graphics Compute Runtime for OpenCL™ Driver package 19.41.14441].
-> **NOTE**: Building samples and demos from the Intel® Distribution of OpenVINO™ toolkit package requires CMake\* 3.10 or higher.
+> **NOTE**: Building samples and demos from the Intel® Distribution of OpenVINO™ toolkit package requires CMake\* 3.10 or higher.
### Build Steps
1. Clone submodules:
1. Install all additional packages listed in the
`/inference-engine/ie_bridges/python/requirements.txt` file:
```sh
- pip install -r requirements.txt
+ pip install -r requirements.txt
```
2. Use the `-DENABLE_PYTHON=ON` option. To specify an exact Python version, use the following
options:
- Microsoft\* Visual Studio 2017, 2019
- (Optional) Intel® Graphics Driver for Windows* (26.20) [driver package].
- Python 3.6 or higher for Inference Engine Python API wrapper
-> **NOTE**: Building samples and demos from the Intel® Distribution of OpenVINO™ toolkit package requires CMake\* 3.10 or higher.
+> **NOTE**: Building samples and demos from the Intel® Distribution of OpenVINO™ toolkit package requires CMake\* 3.10 or higher.
### Build Steps
the Intel® Graphics Driver for Windows (26.20) [driver package] before
running the build. If you don't want to use the GPU plugin, use the
`-DENABLE_CLDNN=OFF` CMake build option and skip the installation of the
- Intel® Graphics Driver.
+ Intel® Graphics Driver.
3. Create build directory:
```sh
mkdir build
- [CMake]\* 3.13 or higher
- Clang\* compiler from Xcode\* 10.1 or higher
- Python\* 3.6 or higher for the Inference Engine Python API wrapper
-> **NOTE**: Building samples and demos from the Intel® Distribution of OpenVINO™ toolkit package requires CMake\* 3.10 or higher.
+> **NOTE**: Building samples and demos from the Intel® Distribution of OpenVINO™ toolkit package requires CMake\* 3.10 or higher.
### Build Steps
```sh
-DPYTHON_EXECUTABLE=/usr/local/Cellar/python/3.7.7/Frameworks/Python.framework/Versions/3.7/bin/python3.7m \
-DPYTHON_LIBRARY=/usr/local/Cellar/python/3.7.7/Frameworks/Python.framework/Versions/3.7/lib/libpython3.7m.dylib \
- -DPYTHON_INCLUDE_DIR=/usr/local/Cellar/python/3.7.7/Frameworks/Python.framework/Versions/3.7/include/python3.7m
+ -DPYTHON_INCLUDE_DIR=/usr/local/Cellar/python/3.7.7/Frameworks/Python.framework/Versions/3.7/include/python3.7m
```
- - If you installed Python another way, you can use the following commands to find where the `dylib` and `include_dir` are located, respectively:
+ - If you installed Python another way, you can use the following commands to find where the `dylib` and `include_dir` are located, respectively:
```sh
find /usr/ -name 'libpython*m.dylib'
find /usr/ -type d -name python3.7m
- [CMake]\* 3.13 or higher
- Android NDK (this guide has been validated with r20 release)
-> **NOTE**: Building samples and demos from the Intel® Distribution of OpenVINO™ toolkit package requires CMake\* 3.10 or higher.
+> **NOTE**: Building samples and demos from the Intel® Distribution of OpenVINO™ toolkit package requires CMake\* 3.10 or higher.
### Build Steps
target_link_libraries(${PROJECT_NAME} ${InferenceEngine_LIBRARIES} dl)
```
-## (Optional) Additional Installation Steps for the Intel® Movidius™ Neural Compute Stick and Neural Compute Stick 2
+## (Optional) Additional Installation Steps for the Intel® Neural Compute Stick 2
-> **NOTE**: These steps are only required if you want to perform inference on
-Intel® Movidius™ Neural Compute Stick or the Intel® Neural Compute Stick 2 using
-the Inference Engine MYRIAD Plugin. See also [Intel® Neural Compute Stick 2 Get Started].
+> **NOTE**: These steps are only required if you want to perform inference on the
+Intel® Neural Compute Stick 2 using the Inference Engine MYRIAD Plugin. See also
+[Intel® Neural Compute Stick 2 Get Started].
### For Linux, Raspbian\* Stretch OS
sudo usermod -a -G users "$(whoami)"
```
-2. To perform inference on Intel® Movidius™ Neural Compute Stick and Intel®
- Neural Compute Stick 2, install the USB rules as follows:
+2. To perform inference on Intel® Neural Compute Stick 2, install the USB rules
+as follows:
```sh
cat <<EOF > 97-myriad-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
The OpenVINO™ toolkit:
* Enables CNN-based deep learning inference on the edge
-* Supports heterogeneous execution across an Intel® CPU, Intel® Integrated Graphics, Intel® Movidius™ Neural Compute Stick and Intel® Neural Compute Stick 2
+* Supports heterogeneous execution across an Intel® CPU, Intel® Integrated Graphics, Intel® Neural Compute Stick 2
* Speeds time-to-market via an easy-to-use library of computer vision functions and pre-optimized kernels
* Includes optimized calls for computer vision standards including OpenCV\*, OpenCL™, and OpenVX\*
This Guide provides overview of the Inference Engine describing the typical workflow for performing
inference of a pre-trained and optimized deep learning model and a set of sample applications.
-> **NOTES:**
+> **NOTES:**
> - Before you perform inference with the Inference Engine, your models should be converted to the Inference Engine format using the Model Optimizer or built directly in run-time using nGraph API. To learn about how to use Model Optimizer, refer to the [Model Optimizer Developer Guide](../MO_DG/Deep_Learning_Model_Optimizer_DevGuide.md). To learn about the pre-trained and optimized models delivered with the OpenVINO™ toolkit, refer to [Pre-Trained Models](@ref omz_models_intel_index).
> - [Intel® System Studio](https://software.intel.com/en-us/system-studio) is an all-in-one, cross-platform tool suite, purpose-built to simplify system bring-up and improve system and IoT device application performance on Intel® platforms. If you are using the Intel® Distribution of OpenVINO™ with Intel® System Studio, go to [Get Started with Intel® System Studio](https://software.intel.com/en-us/articles/get-started-with-openvino-and-intel-system-studio-2019).
## Introducing MYRIAD Plugin
-The Inference Engine MYRIAD plugin is developed for inference of neural networks on Intel® Movidius™ Neural Compute Stick and Intel® Neural Compute Stick 2.
+The Inference Engine MYRIAD plugin is developed for inference of neural networks on Intel® Neural Compute Stick 2.
## Installation on Linux* OS
* GoogleNet (Inception) v1, v2, v4
* VGG family (VGG16, VGG19)
* SqueezeNet v1.0, v1.1
-* ResNet v1 family (18\*\* \*\*\*, 50, 101, 152)
+* ResNet v1 family (18\*\*\*, 50, 101, 152)
* MobileNet (mobilenet-v1-1.0-224, mobilenet-v2)
* Inception ResNet v2
-* DenseNet family\*\* (121,161,169,201)
+* DenseNet family (121,161,169,201)
* SSD-300, SSD-512, SSD-MobileNet, SSD-GoogleNet, SSD-SqueezeNet
**TensorFlow\***:
**MXNet\***:
* AlexNet and CaffeNet
-* DenseNet family\*\* (121,161,169,201)
+* DenseNet family (121,161,169,201)
* SqueezeNet v1.1
* MobileNet v1, v2
* NiN
* VGG family (VGG16, VGG19)
* SSD-Inception-v3, SSD-MobileNet, SSD-ResNet-50, SSD-300
-\*\* Network is tested on Intel® Movidius™ Neural Compute Stick with BatchNormalization fusion optimization disabled during Model Optimizer import
-
\*\*\* Network is tested on Intel® Neural Compute Stick 2 with BatchNormalization fusion optimization disabled during Model Optimizer import
## Supported Configuration Parameters
## Device allocation <a name="MYRIAD_DEVICE_ALLOC"> </a>
Each `IExecutableNetwork` instance tries to allocate new device on `InferenceEngine::Core::LoadNetwork`, but if all available devices are already allocated it will use the one with the minimal number of uploaded networks.
-The maximum number of networks single device can handle depends on device memory capacity and the size of the networks.
+The maximum number of networks single device can handle depends on device memory capacity and the size of the networks.
-If `KEY_VPU_MYRIAD_FORCE_RESET` option is set to `YES` the plugin will reset all VPU devices in the system.
+If `KEY_VPU_MYRIAD_FORCE_RESET` option is set to `YES` the plugin will reset all VPU devices in the system.
Single device cannot be shared across multiple processes.
```sh
cd fpga_support_files
```
-
+
5. Source `setup_env.sh` to set your environment variables:
```sh
source /home/<user>/Downloads/fpga_support_files/setup_env.sh
```
-
+
6. Configure the FPGA Driver Blacklist:
```sh
sudo mv config/blacklist-altera-cvp.conf /etc/modprobe.d
```sh
sudo su
```
-
+
8. Use the `setup_env.sh` script from `fpga_support_files.tgz` to set your environment variables:
```sh
source /home/<user>/Downloads/fpga_support_files/setup_env.sh
```
-
+
9. Change directory to `Downloads/fpga_support_files/`:
```sh
cd /home/<user>/Downloads/fpga_support_files/
```
-
+
10. Run the FPGA dependencies script, which allows OpenCL to support Ubuntu* and recent kernels:
```sh
./install_openvino_fpga_dependencies.sh
```
-11. When asked, select the FPGA card, Intel® GPU, and Intel® Movidius™ Neural Compute Stick, then you can install the correct dependencies.
+11. When asked, select the FPGA card, Intel® GPU, and Intel® Neural Compute Stick 2, then you can install the correct dependencies.
12. If you installed the 4.14 kernel as part of the installation script, you will need to reboot the machine and select the new kernel in the Ubuntu (grub) boot menu. You will also need to rerun `setup_env.sh` to set up your environmental variables again.
-
+
13. Install OpenCL™ devices. Enter **Y** when prompted to install:
```sh
aocl install
```
-
+
14. Reboot the machine:
```sh
reboot
```
-
+
15. Use the `setup_env.sh` script from `fpga_support_files.tgz` to set your environment variables:
```sh
source /home/<user>/Downloads/fpga_support_files/setup_env.sh
```
-
+
16. Run `aocl diagnose`:
```sh
aocl diagnose
```sh
sudo cp -rf a10_1150_sg1 /opt/altera/aocl-pro-rte/aclrte-linux64/board/
```
-
+
3. Convert the BSP files from DOS to UNIX:
```sh
sudo chmod +x a10_1150_sg1
find a10_1150_sg1 -type f -print0 | xargs -0 dos2unix
```
-
+
4. Set up the USB Blaster:
-
+
1. Connect the cable between the board and the host system. Use the letter codes in the diagram below for the connection points:
-
+
2. Connect the B end of the cable to point B on the board.
3. Connect the F end of the cable to point F on the FPGA download cable.
-
+
4. From point F end of the cable to point F on the FPGA download cable, the connection is as shown:
![](../img/VisionAcceleratorJTAG.png)
```sh
source /home/<user>/Downloads/fpga_support_files/setup_env.sh
```
-
-6. Update the Intel® FPGA Download Cable rules to program the board without root permissions and to flash the initialization bitstreams so that the Intel® FPGA Download Cable can communicate with the board:
+
+6. Update the Intel® FPGA Download Cable rules to program the board without root permissions and to flash the initialization bitstreams so that the Intel® FPGA Download Cable can communicate with the board:
```sh
sudo cp config/51-usbblaster.rules /etc/udev/rules.d
```
-
+
7. Load the USB rules:
```sh
sudo udevadm control --reload-rules && udevadm trigger
```
-
+
8. Unplug and re-plug the Intel® FPGA Download Cable to enable JTAG connection.
9. Run `jtagconfig` to ensure that your Intel FPGA Download Cable driver is ready to use:
Your output is similar to:
```sh
1) USB-Blaster [1-6]
-02E660DD 10AX115H1(.|E2|ES)/10AX115H2/..
+02E660DD 10AX115H1(.|E2|ES)/10AX115H2/..
```
10. Download [Intel® Quartus® Prime Software Lite Edition 17.1](http://fpgasoftware.intel.com/17.1/?edition=lite). Install the Intel® Quartus® Prime Software Lite to the `/home/<user>/intelFPGA/17.1` directory.
> **NOTE**: You will need the complete the Intel® Quartus® Prime Software Lite version when you want to program the `boardtest_1ddr_top.aocx` into the flash for permanent availability.
-
+
11. Export the Intel® Quartus® Prime Software Lite environment variable:
```sh
export QUARTUS_ROOTDIR=/home/<user>/intelFPGA/17.1/quartus
```
-
+
12. Use `jtagconfig` to slow the clock:
```sh
jtagconfig --setparam 1 JtagClock 6M
```
-
+
13. (OPTIONAL) Confirm the clock is set to 6M:
```sh
jtagconfig --getparam 1 JtagClock
```sh
cd /opt/altera/aocl-pro-rte/aclrte-linux64/board/a10_1150_sg1/bringup
```
-
+
15. Program the `boardtest_1ddr_top.aocx` file to the flash to be made permanently available even after power cycle:
```sh
aocl flash acl0 boardtest_1ddr_top.aocx
```sh
source /home/<user>/Downloads/fpga_support_file/setup_env.sh
```
-
+
19. Uninstall the previous BSP before installing the OpenCL drivers for the R5 BSP:
```sh
aocl uninstall /opt/altera/aocl-pro-rte/aclrte-linux64/board/<BSP_package>/
```
-
+
20. Export and source the environment script:
```sh
export AOCL_BOARD_PACKAGE_ROOT=/opt/altera/aocl-pro-rte/aclrte-linux64/board/a10_1150_sg1
```sh
aocl install
```
-
+
22. Run the `diagnose` command:
```sh
aocl diagnose
```
You should see `DIAGNOSTIC_PASSED` before proceeding to the next steps.
-
+
## 3. Program a Bitstream
The bitstream you program should correspond to the topology you want to deploy. In this section, you program a SqueezeNet bitstream and deploy the classification sample with a SqueezeNet model that you used the Model Optimizer to convert in the steps before.
```sh
source /home/<user>/Downloads/fpga_support_files/setup_env.sh
```
-
+
3. Change to your home directory:
```sh
cd /home/<user>
```
-
+
4. Program the bitstream for the Intel® Vision Accelerator Design with Intel® Arria® 10 FPGA:
```sh
aocl program acl0 /opt/intel/openvino/bitstreams/a10_vision_design_bitstreams/5-0_PL1_FP11_SqueezeNet.aocx
```
-
+
### Optional Steps to Flash the FPGA Card
> **NOTE**:
```sh
jtagconfig
```
-
+
3. Use `jtagconfig` to slow the clock:
```sh
jtagconfig --setparam 1 JtagClock 6M
```
-
+
4. Store the Intel® Vision Accelerator Design with Intel® Arria® 10 FPGA bistream on the board:
```sh
aocl flash acl0 /opt/intel/openvino/bitstreams/a10_vision_design_bitstreams/5-0_PL1_FP11_SqueezeNet.aocx
```sh
mkdir /home/<user>/squeezenet1.1_FP16
```
-
+
2. Go to `/home/<user>/squeezenet1.1_FP16`:
```sh
cd /home/<user>/squeezenet1.1_FP16
```
-
+
3. Use the Model Optimizer to convert an FP16 SqueezeNet Caffe* model into an optimized Intermediate Representation (IR):
```sh
python3 /opt/intel/openvino/deployment_tools/model_optimizer/mo.py --input_model /home/<user>/openvino_models/FP32/classification/squeezenet/1.1/caffe/squeezenet1.1.caffemodel --data_type FP16 --output_dir .
```
-
+
4. The `squeezenet1.1.labels` file contains the classes `ImageNet` uses. This file is included so that the inference results show text instead of classification numbers. Copy `squeezenet1.1.labels` to the your optimized model location:
```sh
cp /home/<user>/openvino_models/ir/squeezenet1.1/FP32/squeezenet1.1.labels .
```
-
+
5. Copy a sample image to the release directory. You will use this with your optimized model:
```sh
sudo cp /opt/intel/openvino/deployment_tools/demo/car.png ~/inference_engine_samples/intel64/Release
```
-
+
## 5. Run a Sample Application
1. Go to the samples directory
include(dependency_solver)
-set(VPU_SUPPORTED_FIRMWARES usb-ma2450 usb-ma2x8x pcie-ma248x)
+set(VPU_SUPPORTED_FIRMWARES usb-ma2x8x pcie-ma248x)
#
# Default packages
string(TOUPPER "${firmware_name}" firmware_name_upper)
set(var_name VPU_FIRMWARE_${firmware_name_upper}_FILE)
- set(firmware_out_file "${CMAKE_LIBRARY_OUTPUT_DIRECTORY}/${firmware_name}.mvcmd")
+ set(firmware_out_file "${CMAKE_LIBRARY_OUTPUT_DIRECTORY}/${CMAKE_CFG_INTDIR}/${firmware_name}.mvcmd")
# Handle PCIe elf firmware for Windows
if (WIN32 AND "${firmware_name}" STREQUAL "pcie-ma248x")
- set(firmware_out_file "${CMAKE_LIBRARY_OUTPUT_DIRECTORY}/${firmware_name}.elf")
+ set(firmware_out_file "${CMAKE_LIBRARY_OUTPUT_DIRECTORY}/${CMAKE_CFG_INTDIR}/${firmware_name}.elf")
endif ()
list(APPEND all_firmware_files ${firmware_out_file})
COMMAND
${CMAKE_COMMAND} -E copy ${${var_name}} ${firmware_out_file}
MAIN_DEPENDENCY ${${var_name}}
- COMMENT "[VPU] Copy ${${var_name}} to ${CMAKE_LIBRARY_OUTPUT_DIRECTORY}"
+ COMMENT "[VPU] Copy ${${var_name}} to ${CMAKE_LIBRARY_OUTPUT_DIRECTORY}/${CMAKE_CFG_INTDIR}"
VERBATIM)
install(FILES ${${var_name}}
for %%A in ("%OPENCV%") do set OPENCV_FILENAME=%%~nxA
for %%A in ("%MYRIAD%") do set MYRIAD_FILENAME=%%~nxA
for %%A in ("%HDDL%") do set HDDL_FILENAME=%%~nxA
-for %%A in ("%VPU_FIRMWARE_MA2450%") do set VPU_FIRMWARE_MA2450_FILENAME=%%~nxA
for %%A in ("%VPU_FIRMWARE_MA2X8X%") do set VPU_FIRMWARE_MA2X8X_FILENAME=%%~nxA
for %%A in ("%TBB%") do set TBB_FILENAME=%%~nxA
)
)
-if not "%VPU_FIRMWARE_MA2450%"=="" (
- if not exist "%DL_SDK_TEMP%\test_dependencies\VPU\%VPU_FIRMWARE_MA2450_FILENAME%" (
- mkdir "%DL_SDK_TEMP%\test_dependencies\VPU"
- powershell -command "iwr -outf '%DL_SDK_TEMP%\test_dependencies\VPU\_%VPU_FIRMWARE_MA2450_FILENAME%' %VPU_FIRMWARE_MA2450%"
- mkdir "%DL_SDK_TEMP%\test_dependencies\VPU\%VPU_FIRMWARE_MA2450_FILENAME%"
- call "C:\Program Files\7-Zip\7z.exe" x -y %DL_SDK_TEMP%\test_dependencies\VPU\_%VPU_FIRMWARE_MA2450_FILENAME% -o%DL_SDK_TEMP%\test_dependencies\VPU\%VPU_FIRMWARE_MA2450_FILENAME%
- del "%DL_SDK_TEMP%\test_dependencies\VPU\_%VPU_FIRMWARE_MA2450_FILENAME%" /F /Q
- )
-)
-
if not "%VPU_FIRMWARE_MA2X8X%"=="" (
if not exist "%DL_SDK_TEMP%\test_dependencies\VPU\%VPU_FIRMWARE_MA2X8X_FILENAME%" (
mkdir "%DL_SDK_TEMP%\test_dependencies\VPU"
if exist "%DL_SDK_TEMP%\test_dependencies\MYRIAD\%MYRIAD_FILENAME%%MYRIAD%\mvnc" (
echo xcopy.exe "%DL_SDK_TEMP%\test_dependencies\MYRIAD\%MYRIAD_FILENAME%%MYRIAD%" intel64 /S /I /Y /R
xcopy.exe "%DL_SDK_TEMP%\test_dependencies\MYRIAD\%MYRIAD_FILENAME%%MYRIAD%" intel64 /S /I /Y /R
- )
+ )
if exist "%DL_SDK_TEMP%\test_dependencies\MYRIAD\%MYRIAD_FILENAME%%MYRIAD%\..\bin\mvnc" (
echo xcopy.exe "%DL_SDK_TEMP%\test_dependencies\MYRIAD\%MYRIAD_FILENAME%%MYRIAD%\..\bin\*" intel64 /S /I /Y /R
)
)
-if not "%VPU_FIRMWARE_MA2450%"=="" (
- if exist "%DL_SDK_TEMP%\test_dependencies\VPU\%VPU_FIRMWARE_MA2450_FILENAME%" (
- echo xcopy.exe "%DL_SDK_TEMP%\test_dependencies\VPU\%VPU_FIRMWARE_MA2450_FILENAME%\*" intel64 /S /I /Y /R
- xcopy.exe "%DL_SDK_TEMP%\test_dependencies\VPU\%VPU_FIRMWARE_MA2450_FILENAME%\*" intel64 /S /I /Y /R
- )
-)
-
if not "%VPU_FIRMWARE_MA2X8X%"=="" (
if exist "%DL_SDK_TEMP%\test_dependencies\VPU\%VPU_FIRMWARE_MA2X8X_FILENAME%" (
echo xcopy.exe "%DL_SDK_TEMP%\test_dependencies\VPU\%VPU_FIRMWARE_MA2X8X_FILENAME%\*" intel64 /S /I /Y /R
fi
}
-runtimes=(MKL CLDNN MYRIAD GNA DLIA OPENCV VPU_FIRMWARE_USB-MA2450 VPU_FIRMWARE_USB-MA2X8X HDDL OMP TBB AOCL_RTE LIBUSB)
+runtimes=(MKL CLDNN MYRIAD GNA DLIA OPENCV VPU_FIRMWARE_USB-MA2X8X HDDL OMP TBB AOCL_RTE LIBUSB)
export_library_path() {
export LD_LIBRARY_PATH=$DL_SDK_TEMP/test_dependencies/$1:$LD_LIBRARY_PATH