Building opencv with Intel Inference Engine - opencv

Trying to load ssdlite v2 model with intel inference engine on raspberry Pi 3. For this, I need to build opencv-4.0 with Intel Inference API engine. I am unable to build open CV using CMAKE with -DWITH_INF_ENGINE=ON ^
-DENABLE_CXX11=ON flags. Does anyone know how to do it?

First you need install or compile this engine, see you Intel OpenVINO documentation.

Related

Using OpenCV with gpu support in anaconda

I'm using Windows with a GTX 1050.
Currently I'm working with OpenCV in object detecting using yolo model. I found it's quite slow at ~7fps. I tried to install OpenCV with GPU support but it's only run when I execute the Python script in cmd, i mean not in Anaconda.
Is there any possible way to install OpenCV with GPU support?

OpenCV error: No GPU support, cannot build with WITH_CUDA=ON

I am trying to make OpenCV project using GPU. I installed OpenCV v2.4.13 and NVidia CUDA Toolkit. I added additional include and library directories in configuration and OpenCV project works correctly without GPU functions. But when I'm trying to run openCV with GPU I get an error like this:
OpenCV Error: No GPU support (The library is compiled without CUDA support) in EmptyFuncTable::mallocPitch, file C:\builds\2_4_PackSlave_win32_vc12-shared\opencv\modules\dynamicuda\include\opencv2/dynamicuda/dynamicuda.hpp, line 126
Libary has been compiled without CUDA, so i tried to build the sources myself, with WITH_CUDA=ON in CMake, but when building Visual Studio 2013 has been giving me an errors that he cannot find opencv_core2413d.lib.
What can I do with this?

Build Opencv 3.1.0 with IPP ippicv_windows_20151201.zip

I'm trying to build OpenCV 3.1.0 on a stand alone computer (there is no internet access).
I have an Intel composer 2015 installed, which include IPP v8.
During CMake build configuration, I get the following message:
Cmake error at 3rdparty/downloader.cmake.73
for file: [..... /ippicv_windows_20151201.zip]
expected hash [...] actual hash [...]
I figure out that I need to manually download ippicv_windows_20151201.zip and place it in the sources sub - folder.
Do you know where I can download it from?
I can exclude the build flag: "WITH_IPP" , In that case, I'd not build with IPP at all, which is something I don't want.
I'd rather like to build OpenCV with my pre-installed IPP (Intel Composer), not the downloaded free version from OpenCV, Do you know how I can do that ?
BWT, What is the difference between build WITH_IPP and WITH_IPP_A flags ?
P.S. I posted the same question on OpenCV forum
If the downloader.cmake is not finding the hash perhaps is not available yet or there is some error when reaching the URL (downloading protocol maybe?). Download the previous version from here, it'll do the work. Just need to place it in the correct folder. I'm using OpenCV 3.1.0 with the 20141027 with no problem at all.
In case you have an Intel composer which includes IPP library.
Go to your Opencv CMake --> Add entry (right side) --> Insert variable as a path:
IPP_ROOT
Set with the library location
Thus, would compile Opencv with IPP library from the Intel Composer
IPP_A comes for asynchronous IPP which is currently experimental

opencv error: no GPU support

I have install Cuda 6.5 and opencv 2.4.9 with visual studio 2010, when I run gpu, I get error
Opencv Error: No GPU support(the library is compiled without PGU support) in the row_nogpu, file C:/builds/2_4_Packslave-win32-vc10-shared/opencv/modules/gpu/src/precomp.hpp line 135
I get this error, is any one can help what do I have to do?
Thanks
I believe, you have to actually build the libraries with CUDA support. I Imagine This Guide will be useful.
This can be caused because of following.
Use the flag WITH_CUDA=ON during cmake
You are trying to load the libraries which are compiled without GPU support, after you install opencv make sure you change the libraries path to that of GPU supported once.

Does OpenCV for Mac use the Accelerate framework?

The Accelerate framework is a Mac-specific framework that provides things like image convolutions and LAPACK, supposedly optimized to be as fast as possible on Macs. My question: Does OpenCV take advantage of this? Specifically, does the function "filter2D" use Accelerate?
It does not use the Accelerate framework, but it looks like it has been speeded up using the CUDA stuff in 2.2
The relevant files in OpenCV2.2 ...
/modules/gpu/include/opencv2/gpu/gpu.hpp
/modules/gpu/src/filtering.cpp
and
modules/imgproc/src/filter.cpp
for the non-gpu stuff
Not a mac expert but AFAIK openCV uses IPP (if installed) TBB (build option) and NVidia-CUDA (build option)
If you use the MacPorts version, you can specify the options
$ port variants opencv
opencv has the variants:
debug: Enable debug binaries
python26: Add Python 2.6 bindings
* conflicts with python27
python27: Add Python 2.7 bindings
* conflicts with python26
tbb: Use Intel TBB
universal: Build for multiple architectures
I have used
sudo port install py26-numpy
sudo port install opencv +python26 +tbb
with success. Concerning the Accelerate.framework specifically, this blog entry says "# Add Accelerate.framework which is used internally from OpenCV library.", but I have no clue as to know if it is the case here.

Resources