* Add initial version of u1 type support.
* Turn off u8_to_u1 test in IE.CPU.
* Fix compilation issue.
* Replace std::memset with std::fill.
* Add u4 type support.
* Add i4 support.
* LP types support generalized.
* Remove std::copy optimization.
* Fix backend test for LP types.
* Fixed arm plugin compilation.
* Add LP types to Serialization SLT.
* Add Convert to summarize.py report.
* batch support for interpolate
* hash update
* compilation errors solved
* changes in tests, so not to break other plugins
* changes in tests, so not to break other plugins
* Revert "changes in tests, so not to break other plugins"
This reverts commit 67e5c1e4ddba4f0cc858eb1293e50ce9d9ae0227.
* Revert "changes in tests, so not to break other plugins"
This reverts commit f6a537d2236f0b64f0ff028627af9e0e388a2d23.
* review corrections
* Firmware update
* Copy a string with an address of the booted device only when the device has been successfully been booted. Otherwise, we should free allocated by strdup memory or we will get a memory leak.
* Added tests for 2D DFT when we have signal_size and axes [0, 2].
* Rewritten reference implementation of DFT and IDFT.
* Code style fixes.
* Reverted changes.
* Added debug prints.
* Temporarily commented some functions.
* Reverted changes in (I)DFT reference.
* Added more debug prints (in evaluates_map.cpp, to evaluate() for IDFT).
* Added setting output shape for DFT and IDFT evaluate() in evaluates_map.cpp.
* Added more tests for signal_size case of DFT.
* Written tests for signal_size case of IDFT.
* Deleted debug prints from (I)DFT reference implementation (the file fft.cpp).
* Deleted debug prints from evaluate() for DFT and IDFT.
* Deleted debug prints from tests for DFT.
* Deleted debug prints from IDFT tests.
* Code style fixes.
* Enabled CPU evaluation tests for DFT and IDFT in CPU supported cases.
* Enabled CPU (I)DFT layer tests.
* Copied fix for specialization of function is_float() for (b)float16 from Pertovsky Aleksandr's PR 5654.
* Reverted changes in the function is_float() from ie_precision.h.
* Disabled BF16 CPU FuncTests for (I)DFT.
* Deleted filling 'buffer' by zeros. Simplified the function lengths_except_given_axis.
* Small fix.
* Code style fix.
* Reverted deleting 'std::fill(buffer.begin(), buffer.end(), complex_type{0.0f, 0.0f});'
* Reverted changes in the function lengths_except_given_axis().
* Changes in the function lengths_except_given_axis().
* Small fix.
* Deleted commented code.
* Simplifications in the function lengths_except_given_axis().
* Deleted commented code.
* Enabled BF16 (I)DFT CPU FuncTests.
* Fixed comments before disabled (I)DFT IE_CPU tests.
* Async auto-request, now with revamped SetCallback (after https://github.com/openvinotoolkit/openvino/pull/5645 merged) it is safe to set.
Also test modification to verify that the callback is called on the same (user's) request and e.g. not on the actual device's request
* Override CreateInferRequestImpl() instead of CreateInferRequest()
Signed-off-by: Shoujiang Ma <shoujiang.ma@intel.com>
Co-authored-by: myshevts <maxim.y.shevtsov@intel.com>
* Make order of port names determined in IR
Signed-off-by: Roman Kazantsev <roman.kazantsev@intel.com>
* Make port names in determined order and adopted tests
Signed-off-by: Roman Kazantsev <roman.kazantsev@intel.com>
* Multi plugin - override loading network from file
When caching is enabled, MULTI plugin will check all devices
- For devices with caching supported - call LoadNetwork(modelPath, ...)
- For others - ReadNetwork once and then LoadNetwork(cnnNetwork) for each device
Caching unit test is added for both cases
Additional helper methods:
- ICore::ToExecutableNetwork - converts internal ExeNetwork to ExecutableNetwork
- ICore::DeviceSupportsImportExport - checks if device supports import and export functionality. Used by Hetero and Multi
* Updated according to review comments
* fixed sporadic failure of 'multi-device' test cases
Root cause:
Currently only one 'ExecutableNetwork' object is created for each LoadNetwork
For Multi-testing several threads could call simultaneously setNetworkInputs/Outputs/SetPointerToPlugin
It caused race condition and invalid data structures
* Fix build issues after rebase
* Multi: Set network inputs/outputs/pointerToPlugin for load-from-file case
Overloaded function doesn't call these methods, thus multi executable network was unusable
Added caching test verifying that inputs/outputs are copied now from first loaded device network
* adding conv2d decomposition
* save point
* build of conv_2d factorization succeeds
* working 2d conv decomposing transform
* added pseudo code for handling larger kernels
* fix conv splitting due to size
* active work on convolution 1xK without dilation
* validated NHWC ordered networks with convolution kernel sizes:
3x3
3x1
5x1
1x5
1x3
TODO: 2d max pooling
* removed debug printouts
* fusing max pooling/bias/af when -disable_nhwc_to_nchw option is used
* code cleanup
* [GNA] Fixes for CI run
* [GNA] Add tests, fix transform
* [GNA] Fix padded2valid and conv2d decomposition coexistence
* [GNA] Temporarily disable tests due to mock call count issues
* [GNA] Split tests for different hw versions
Co-authored-by: prozen <piotr.rozen@intel.com>
* Exclude xbyak from install
* Added automatically generated InferenceEngineConfig.cmake
* Reverted a version back
* Fixed issues with target aliases
* Make TBB dependency private
* Made ie_parallel.cmake self-sufficient
* Don't expose ie_paralle.cmake to end users
* Fixed compilation with TBB
* Fixes for TBB
* Fixed vpu_graph_transformer compilation
* Fixed tests compilation
* Added install of ie_parallel.cmake
* Switched ENABLE_ALTERNATIVE_TEMP to OFF. Fixed COMPONENTS for TBB
* Fixed file name in install rules
* Added find_dependency for TBB in ie_parallel.cmake
* WA for cmake bug with PACKAGE_PREFIX_DIR
* Fixed no-deprecation to fix speech-library build
* Reverted version from 2.1.0 to 2.1
* Revert "Reverted version from 2.1.0 to 2.1"
This reverts commit 7cb5d1563c.
* Added versions to cmake
* Added versions to ie_version.hpp
* Returned custom version file back
* Added InferenceEngineConfig-version.cmake to share as well
* Disabled one more GPU test
* Added one more WA for CI
* WA for CI issue for C API
* Added InferenceEngineConfig-version.cmake to share as well
* Added verison parsing from ie_version.hpp
* Revert "[CPU] Add Roll support (#5112)"
This reverts commit 5d8f209df6.
* Revert "[CPU] windows_Interpolate_fused-FQ_nearest-mode_nspc-layout_fix (#5317)"
This reverts commit 0808975a37.
* Revert "[INT8][BF16] INT8 + BF16 feature was enabled (#5059)"
This reverts commit 7d2ec02d65.
* Support for components
* No version for IEDevScripts package
* Removed IE_VS_VER_HAS_VERSION from vs_version.rc.in
* Added compatibility for 2.x old versioning
* Update SelectDevice policy in auto plugin
Signed-off-by: Zhengtian Xie <zhengtian.xie@intel.com>
* Implement limit device list for AUTO plugin
Signed-off-by: Shoujiang Ma <shoujiang.ma@intel.com>
* Add tests for AUTO limit device feature
Signed-off-by: Shoujiang Ma <shoujiang.ma@intel.com>
* Add gpu tests for auto-plugin
Signed-off-by: Shoujiang Ma <shoujiang.ma@intel.com>
* Fix CI cpuFuncTests issue due to BATCHED_BLOB
Signed-off-by: Shoujiang Ma <shoujiang.ma@intel.com>
* Override LoadNetwork(modelPath, config) in AUTO plugin
Signed-off-by: Shoujiang Ma <shoujiang.ma@intel.com>
* Update SelectDevice() logic for LoadNetwork(model, config)
Signed-off-by: Shoujiang Ma <shoujiang.ma@intel.com>
* Update GetNetworkPrecision logic for auto-plugin
Signed-off-by: Zhengtian Xie <zhengtian.xie@intel.com>
* Address reviewers' comments
Signed-off-by: Shoujiang Ma <shoujiang.ma@intel.com>
* Add tests for AUTO:GPU,CPU case
Signed-off-by: Shoujiang Ma <shoujiang.ma@intel.com>
* Update logic in GetNetworkPrecision for auto-plugin
Signed-off-by: Zhengtian Xie <zhengtian.xie@intel.com>
* Address reviewer's comment: clean and simplify code
Signed-off-by: Shoujiang Ma <shoujiang.ma@intel.com>
* Fix wrong usage of convolution weight index
Signed-off-by: Shoujiang Ma <shoujiang.ma@intel.com>
* Address reviewer comment: fix get network precision logic
Signed-off-by: Shoujiang Ma <shoujiang.ma@intel.com>
* Fix rebase issue
Signed-off-by: Shoujiang Ma <shoujiang.ma@intel.com>
* Fix ie_core.cpp header change
Signed-off-by: Shoujiang Ma <shoujiang.ma@intel.com>
Co-authored-by: zhengtian.xie <zhengtian.xie@intel.com>
* Fix errors in VariadicSplit layer restored from serialized IR
* Update VariadicSplit specification and error message to allow 1D tensors on 1st input
* Update spec
* Resolve comments
* Apply comments, add unit tests
* Update unit tests
Original source code repo: https://github.com/llohse/libnpy
SHA of original commit: d3fd88697889cefb466b647d3034c1d7b7f615ff
In OpenVINO repo there are some modifications, thus Intel's copyrights are kept as well
