* OpenVINO no longer supports vpu so remove the vpu PACKAGECONFIG and
references.
* Now allows snappy compression to be used for TF frontend so allow
system installed snappy.
* Flatbuffers is now needed for TF Lite frontend.
* Refresh patches.
Signed-off-by: Yogesh Tyagi <yogesh.tyagi@intel.com>
Signed-off-by: Anuj Mittal <anuj.mittal@intel.com>
Brings in support for NumPy 1.24 and support for system installed
OpenCL. Includes a newer version of myriad firmware as well.
Signed-off-by: Anuj Mittal <anuj.mittal@intel.com>
Switch to using variables defined for RPM generation as it more closely
aligns with how we install libraries and remove the tweak done for
debian variables.
Also fixes packaging issues when BASELIB is set to lib64:
| 20:18:42 ERROR: openvino-inference-engine-2022.3.0-r0 do_package: QA Issue: openvino-inference-engine: Files/directories were installed but not shipped in any package:
| 20:18:42 /usr/lib/python3.10/site-packages/_pyngraph.cpython-310-x86_64-linux-gnu.so
| 20:18:42 /usr/lib/python3.10/site-packages/requirements.txt
...
| 20:18:42 /usr/lib/python3.10/site-packages/openvino/inference_engine/ie_api.cpython-310-x86_64-linux-gnu.so
| 20:18:42 /usr/lib/python3.10/site-packages/openvino/inference_engine/constants.cpython-310-x86_64-linux-gnu.so
| 20:18:42 /usr/lib/python3.10/site-packages/openvino/inference_engine/__init__.py
Signed-off-by: Anuj Mittal <anuj.mittal@intel.com>
* OpenVINO now installs libraries and headers correctly so we don't need
the local patches anymore.
* Switch to using pybind11 from system. json-schema-validator is no
longer used and open model zoo submodule is only used when building a
specific tool so these submodules have been removed.
* Tweak build scripts to include Yocto specific changes.
License-Update: xbyak deleted the Japaneses translation from COPYRIGHT
and nlohmann_json updated copyright years.
Signed-off-by: Yogesh Tyagi <yogesh.tyagi@intel.com>
Signed-off-by: Anuj Mittal <anuj.mittal@intel.com>
- Change gflag to shared as we are not building with static library.
- We are using zlib from yocto recipe, so don't add zlib as third party package
- Third party package mkl-dnn name changed to onednn upstream in openvino repo so changed
the name accordingly in openvino-inference-engine recipe
- Refresh patches
Release Notes:
https://github.com/openvinotoolkit/openvino/releases/tag/2022.2.0
Signed-off-by: Yogesh Tyagi <yogesh.tyagi@intel.com>
Signed-off-by: Naveen Saini <naveen.kumar.saini@intel.com>
Signed-off-by: Anuj Mittal <anuj.mittal@intel.com>
Enable an option that's is available now to use TBB from system and
refresh patches accordingly. This version also switches to using system
installed OpenCV and Intel version is not included.
Release notes:
https://github.com/openvinotoolkit/openvino/releases/tag/2022.1.1
Signed-off-by: Anuj Mittal <anuj.mittal@intel.com>
Prevent host paths from getting into target packages. Also prevents
buildpaths warnings for files:
| File /usr/lib/libopenvino.so in package openvino-inference-engine contains reference to TMPDIR [buildpaths]
| File /usr/lib/python3.10/site-packages/openvino/inference_engine/ie_api.so in package openvino-inference-engine-python3 contains reference to TMPDIR [buildpaths]
| File /usr/src/debug/openvino-inference-engine/2022.1-r0/build/src/plugins/intel_cpu/cross-compiled/proposal_imp_disp.cpp in package openvino-inference-engine-src contains reference to TMPDIR
Signed-off-by: Anuj Mittal <anuj.mittal@intel.com>
When included in a project using find_package, it goes and looks for
headers and cmake module at an incorrect path.
Make sure that we are able to locate the headers and cmake module file.
Signed-off-by: Anuj Mittal <anuj.mittal@intel.com>
Include the header explicitly to avoid failures:
| inference-engine/src/plugin_api/ie_system_conf.h:21:31: error: 'exception_ptr' in namespace 'std' does not name a type; did you mean 'exception'?
| 21 | INFERENCE_ENGINE_API_CPP(std::exception_ptr&) CurrentException();
| | ^~~~~~~~~~~~~
Signed-off-by: Anuj Mittal <anuj.mittal@intel.com>
Release notes:
https://github.com/openvinotoolkit/openvino/releases/tag/2021.3
Remove a patch that isn't needed anymore and refresh the rest. Remove
dependency on onednn as it's using a forked version.
Signed-off-by: Anuj Mittal <anuj.mittal@intel.com>
For release notes, see:
https://software.intel.com/content/www/us/en/develop/articles/openvino-relnotes.html
The recipe has been changed to:
- disable unit tests as they rely on an older version of googletest.
- remove a patch as it was merged upstream.
- backport a patch instead of using a local version.
- refresh other patches.
- download mkl-dnn separately instead of using the submodule. The
project downloads a lot of other modules as well and we don't
want/use those.
- not download lfs documentation content.
Signed-off-by: Anuj Mittal <anuj.mittal@intel.com>
Make sure that cmake files are installed at correct location so they
could be located using find_package.
Signed-off-by: Anuj Mittal <anuj.mittal@intel.com>
* Point to the renamed repository and change the project name to
openvino-inference-engine.
* Include ngraph as a submodule instead of using it as a separate
project.
* Use the new unit tests, the old ones have been deprecated.
Signed-off-by: Anuj Mittal <anuj.mittal@intel.com>
fix compile error:
inference-engine/src/mkldnn_plugin/mkldnn_memory_solver.hpp:60:9: error: 'int64_t' does not name a type
| 60 | int64_t size;
| | ^~~~~~~
include stdint.h to fix it.
Signed-off-by: Liwei Song <liwei.song@windriver.com>
Signed-off-by: Anuj Mittal <anuj.mittal@intel.com>
We don't want to install sample sources. So delete them and install the
binaries instead. Also make sure that we're installing the python
samples and modules at correct location. Remove the tweaks from local
patch and copy in the recipe itself.
Signed-off-by: Anuj Mittal <anuj.mittal@intel.com>
* otherwise components depending on them won't be able to find them
Signed-off-by: Martin Jansa <Martin.Jansa@gmail.com>
Signed-off-by: Anuj Mittal <anuj.mittal@intel.com>
Refresh patches so that they apply cleanly on 2019r3.
Signed-off-by: Chin Huat Ang <chin.huat.ang@intel.com>
Signed-off-by: Anuj Mittal <anuj.mittal@intel.com>
Install clDNN to /usr/lib to resolve the following inference engine
error when running with GPU plugin:
[ ERROR ] Failed to create plugin libclDNNPlugin.so for device GPU
Please, check your environment
Cannot load library 'libclDNNPlugin.so': libclDNNPlugin.so: cannot open
shared object file: No such file or directory
/usr/src/debug/dldt-inference-engine/2019r2-r0/git/inference-engine/include/details/os/lin_shared_object_loader.h:36
/usr/src/debug/dldt-inference-engine/2019r2-r0/git/inference-engine/src/inference_engine/ie_core.cpp:277
Signed-off-by: Chin Huat Ang <chin.huat.ang@intel.com>
Signed-off-by: Anuj Mittal <anuj.mittal@intel.com>
* Release notes:
https://software.intel.com/en-us/articles/OpenVINO-RelNotes
* Enable unit tests to be built and tested using ptest mechanism.
* Include patches from Clear Linux for build fixes.
* Switch to using python3 and threading to using TBB. Switch ENABLE_OPENCV
to off so opencv from system is used.
* Remove do_install and patch Makefiles instead to install libraries correctly.
Signed-off-by: Anuj Mittal <anuj.mittal@intel.com>
This recipe builds the inference engine from opencv/dldt 2019 R1.1
release.
OpenVINO™ toolkit, short for Open Visual Inference and Neural network
Optimization toolkit, provides developers with improved neural network
performance on a variety of Intel® processors and helps further unlock
cost-effective, real-time vision applications.
The toolkit enables deep learning inference and easy heterogeneous
execution across multiple Intel® platforms (CPU, Intel® Processor Graphics)—providing
implementations across cloud architectures to edge device.
For more details, see:
https://01.org/openvinotoolkit
The recipe needs components from meta-oe so move it to
dynamic-layers/openembedded-layer. GPU plugin support needs intel-compute-runtime
which can be built by including clang layer in the mix as well.
CPU and GPU plugins have been sanity tested to work using
classification_sample. Further fine-tuning is still needed to improve
the performance.
Original patch by Anuj Mittal.
Signed-off-by: Chin Huat Ang <chin.huat.ang@intel.com>
Signed-off-by: Anuj Mittal <anuj.mittal@intel.com>
