* Implement ExperimentalDetectronDetectionOutput shape infer.
Signed-off-by: Luwei Zhou <luwei.zhou@intel.com>
* Update on the review comments.
* Update based on review
* replace AUTO_DEVICE_LIST with MULTI_DEVICE_PRIORITY in test case
Signed-off-by: Hu, Yuan2 <yuan2.hu@intel.com>
* remove KEY_AUTO_DEVICE_LIST
Signed-off-by: Hu, Yuan2 <yuan2.hu@intel.com>
* NV12 Ref impl: Align with Legacy NV12 conversion
Little-endian tricks are completely not needed finally
Basic tests of OV20 preprocessing vs Legacy preprocessing:
- Mean/Scale
- Resize (Linear vs Bilinear)
- NV12 color conversion
* Register Template plugin in legacy core before CNNNetwork compliance test
NV12: round to nearest integer for 'u8' mode
Fix preprocess-reference NV12 tests (swap U & V)
* Decreased default threshold and use random distribution for inputs generation
* Added tests RefImpl vs OpenCV - NV12 color conversion
Added CPU accuracy tests + nightly (including all RGB color combinations)
* Fix build issue after rebase
* Remove test code
* Fix comments
Disable OpenCV tests on CI (some machines can't load opencv_imgproc during test)
* Remove fp16 of Convert layer test from skip_tests.config.cpp as it works now
* update repo
* add op reference test of group_convolution and group_convolution_backpropdata
* update reference test of group_convolution/group_convolution_backpropdata and remove their ngraph backend test
* Remove fp16 of Convert layer test from skip_tests.config.cpp as it works now
* update repo
* add initial version of op reference test of deformable convolution
* update reference test
* update reference test 2
* update deformable_convolution referencet est
* add deformable_convolution_opset8 op reference test
* update skip_test_config.cpp
* remove backend test and add visitor api test
* merge test code of deformable_convolution v1 and v8 in a single file
* merge deformable_convolition_opset8 of visitor api test into single file
* Add qlinear_matmul files
* Extend matmul helpers
* register op in bridge
* Add test for 2d
* newlines at end of files
* Codestyle changes
* Re-use of nodes inputs
* Remove xfails
* Register as set1
* reshape inputs as scalars
* remove fixed xfail issue residues
* update changes to fit the newest master
Co-authored-by: dkozykowski <dawid.kozykowski@intel.com>
* tmp
* Fix atanh correctness test issue and veriyf pass.
Signed-off-by: Yan, Xiping <xiping.yan@intel.com>
* Only keep available input value for correctness test.
Signed-off-by: Yan, Xiping <xiping.yan@intel.com>
* [GPU] Add fused operation test for concat.
And fused test and enable post ops in concat onednn integration.
Signed-off-by: hyunback <hyunback.kim@intel.com>
* Add depence code when machine does not support imad.
oneDNN post operation has issue.
Signed-off-by: hyunback <hyunback.kim@intel.com>
* Add test cases for PReLU in cpu plugin
* For case when slope is vector
* Add Bucketize and NonZero template plugin reference tests
* Apply supported types for NonZero
* Edit float_t and double_t to float and double
* Edit std::vector<bool> to std::vector<char>
* [GPU] Fix incorrect reusage of OneDNN postops configurations
* [GPU] Add OneDNN's convolutions and deconvolutions support
* [GPU] Do not run fusing unittest when imad is not supported
Co-authored-by: Sergey, Shlyapnikov <sergey.shlyapnikov@intel.com>
* fixed dealing with None values in then/else branches of Select
* generalized solution when condition is non one elemental
* fix when both branches are None
* minor corrections
* rewritten Select unit-tests; fixed for condition with [True] mask
* removed mutable default arg from build_graph, added a few more test cases with masked condition, other minor corrections
* corrected output_shape calculation when broadcasting is off
* layer tests fixed: relaxed assert for condition shape to let pass TF Select
* corrected shape calculation when condition is not elementwise equal, calculated calculation for TF, corrected calculation of shape when values are not set
* fixed a typo for Select from TF Where
