[DRAFT] Deform conv backend test fixes #13
Conversation
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
* Add GRN shared single layer test instance for CPU * Remove GRN backend tests from fused_op.in * Init GRN new template reference tests * Add more bias values to GRN single layer tests * Add more GRN template reference test cases * Remove unused parameter from GrnParams * Refactor GRN template referene tests and add more types * Add anonymous namespace * Add bf16 type to cpu single layer tests * Add Serialization test * Add GRN to revised ops
* Update detailed description * Update attrs description * Add Types section and Inputs Outputs description * Update example
…#6649) * Prepare `install` rule for time_tests * Prepare `install` rule for stress tests
* DeformableConv v8:reference implementation * ngraph codestyle * update reference iplementation * Disable tests on GPU * fix unit tests * Update DeformConv single layer tests * fix serialization tests
* Move detailed description up, add backtics to attr types * Add backtics for range in clip attr description, remove non-existing attributes * Adjusting the spec to review comments * floating-point instead of floating point, remove default value for mandatory attribute
* openvino namespace for benchmark tool * change readme wording * remove duplicated README.md
* new implementation of FakeQuantize * move FakeQuantize backend test to fake_quantize.in.cpp * enable some test for FakeQuantize * Add support for PDPD broadcasting and some backend tests * arm plugin expect less attributes in function call * try to fix arm plugin build * try to build arm plugin * start changing backend test * add check for attributes number in visitor test * fix backend test after refactoring * add default parameter value to runtime::reference::fake_quantize * Revert "add default parameter value to runtime::reference::fake_quantize" This reverts commit 9d2c00d. * add SLT for FakeQuantize * remove fesetround * change `v1` namesapce to `v0` in ref impl * add FakeQuantize-1 to VERIFIED_OP_REFERENCES * pass immutable reference to test functions
* LPT fix for Windows * LPT fix for Windows * Remove inference_engine_transformations_EXPORTS * [nGraph] Register new node in GraphRewrite * [LPT] nGraph alignment * [LPT] nGraph alignment: tests Co-authored-by: Ilya Lavrenov <ilya.lavrenov@intel.com>
* [GNA] KSOFunction test fix * Lambda for dimensions matching check
* Migrate Deployment Manager tool to Open Source * scripts/CMakeLists.txt: Added install rules for deployment manager
…oolkit#6358) * Rework model loading in FE manager, implement PDPD probing * Fix build * Fix build * Fix build * Fix unicode * Fix merge issues * Fix codestyle * Read frontends path from frontend_manager library location * Fix codestyle * Fix FE dependency * Fix dependencies * Fix codestyle * Check if model file exists * Revert adding model to lfs * Add test model * Fix cmake dependencies * Apply review feedback * Revert pugixml * make getFrontendLibraryPath not public API * Fix codestyle * Apply fix from Ilya Lavrenov * Add FE dependency in legacy tests * Remove not needed dependency * Better support Unicode * Fix build * Fix build * Fix build * Add dependency foe deprecated tests * Fix dependency * Fix typo * Revert adding FE dependency to IESharedTests * Remove relative paths from frontend unit tests * Apply review feedback * Fix typo * Return allow-undefined, since kmb dependecies fail to link * Fix merge conflict * Compare functions in reader tests * Simplify code to load from variants * Remove supported_by_arguments from public api * Fix codestyle * Fix build * Compare names in reader tests * Fix wchar in variant Co-authored-by: Ilya Churaev <ilya.churaev@intel.com>
* Update spec for MVN-1 and MVN-6. * Add reduction_axes attribute to MVN-1. * Fix mean value calculation using ReduceMean. * Correct reduction_axes attrbute name. * Restore default value for normalize_variance and eps_mode. * Remove dafult value for required attributes. * Correct typeo.
* update docs * add sign to intActivationTypes * add RTTI macro * update backend test * add type prp test * add visitor test * add visitor and type_prop test to CMakeList * add sign to constants.py * delete backend tests and create new reference tests * style fix * remoove sign backend test from CMakeList * create reference test for all supported types * remove boolean type from evaluate method
…6701) * Add prefix for conda build to cpack name for python api * use PYTHON_COMPONENT variable
* experiment * save * Undo exeprimental changes
…lkit#6644) * fixed crash related with loading model with fq and sigmoid * renamed multiple_input.* to multiple_input_fq.*; removed two unnecessary FQ layers from smoke_fq_fusion_with_sigmoid test; moved FQ params to test params
Check if CPACK_STRIP_FILES configured before setting it ON by default. This allows to configre it from command line when required.
* [MyriadX] Abs op support
* Add visitor test. * Add Serialization SLT. * Add Select-1 to summarize.py. * Remove select from evaluates map. * Remove few Select cases from manifest. * Fix style. * Refactor CoordinateTransform usage for NUMPY. * Refactor CoordinateTransform usage for PDPD. * Migrate backend tests to template_plugin. * Revert "Fix style." This reverts commit 8298c90. * Add more template plugin tests. * Fixes for PDPD broadcasting. * Align Select type prop tests with PDPP broadcasting to new implementation. * Remove ngraph:: from types in tests.
…it#6709) * Fix node name issue introduced by openvinotoolkit#5854 * Compare names in TransposeFuse tests
* Fix for cmake 3.21.x * Removed a lot -Wno-* compile options
* added ChangeRangeOutputType.py * applied review comments * corrected error message - warn user to use FP32 * renamed ChangeCastOutputType.py et ell. * merged ChangeRangeOutputType.py, ChangeCastOutputType.py into a singe file * corrections * typo fix * applied comments: faster find_and_replace loop, wording correction
- removed obsolete dependencies.
* Fixed Windows public precommit * ONNX LTO
* Added nGraph as a public dependency * Fixed Windows warning * Fixed CMake * Fixed constant op * Fixed typo * Fixed comments * Revert ngraph libraries * Fixed build * Fixed IE::ngraph * Fixed git merge
…#6893) * Fixing cmake command removing temp data for ie_wheel * rm -> remove_directory Co-authored-by: Alexander Zhogov <alexander.zhogov@intel.com>
Co-authored-by: Ilya Lavrenov <ilya.lavrenov@intel.com>
* Initial version of v8::MaxPool op class * Type instead of Type_t to indicate element type * Attribute visitor test * Common MaxPoolBase base class * More refactoring * v8::MaxPool cleanup * Pooling ops inference helper extension - window dilation * New MaxPool 3D type prop tests * Common part of MaxPool validation part extracted to the base class * MaxPool-8 shape inference with base class utils * infer_batched_pooling_forward arguments reorder to avoid compilation errors * Align the rounding type attribute name for both MaxPool version * MaxPool-8 axis attribute * Missing attributes * Code formatting * PR feedback * MaxPool-1 RTTI definition adjustment
* Moved current IE API to separate folder * Fix install * Fix documentation * Fixed install path * Try to fix CI * Changed installation path * Use ONNXRuntime rel-1.8.1 version
* Move to Ubuntu 20.04 * Fix pytest
* update docs * add host tensors validation * create type_prop tests * create serialization single layer test * create visitor test * create op_reference test * add logicalAnd to constants.py * create additional op_reference tests * add check for number of visited attributes in visitor test * update auto_broadcast description * remoove backend test * update LogicalNot params name * remove backend test from CMakeList * create util function for type_prop tests * update op_reference tests * remove typo in docs * remove unsupported types from evaluate * fix bug in op_reference test * refactor visitor test * update math formula in the spec * update has_evaluate types
* Azure CI: Move Linux check to Ubuntu 20.04 * Fix onnx * Fix onnx docker install * add dockerd-rootless-setuptool.sh install * add uidmap * sudo docker
* update spec, add visitors, backend test * remove visitors test as it is implemented in another PR * remove visitors test from CMakeLists * remove old backend tests, refactor minor parts of the code * add namespace * refaactor template test for less_equal op
* Merged ONNX editor and ONNX importer to the one folder * Try to migrate to original ONNX * Remove ONNX_BUILD_SHARED_LIBS * Update ONNX
* Separate executable for paddlepaddle unit tests * Fix CI * Move PaddlePaddle-specific python requirements to paddlepaddle test folder Also produce build time warning when paddle test models generation is disabled * Renamed back PADDLE_TEST_MODELS_DIRNAME to TEST_PADDLE_MODELS_DIRNAME * Add dependency on CPU plugin (PaddlePaddle fuzzy tests use CPU plugin for inference) * Fix code style * Fix review comments #2 * Code style fix * Add dependency of 'paddlepaddle_test_models' to 'test_model_zoo'
yury-intel
force-pushed
the
deform_conv/some_cpu_fixes_savechanges
branch
from
e6af0f8
to
b3d6c60
Compare
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
Details:
Tickets: