* [GPU] Fix levit-128s accuracy issue
Wrong batch dims for fused eltwise of gemm.
-> The issue is getting incorrect batch size of fused eltwise used by gemm.
Its rank is different from src tensor. Eltwise tensor rank was reduced by mistake.
It is only reproduce in batch 1 and full tensor.
The batch size in here means all of non spatial dims, but previous implementation was default batch dim role.
Signed-off-by: hyunback <hyunback.kim@intel.com>
* use oneTBB for arm64
* force THREADING=TBB
* test: remove TBB_DIR for linux arm64
* update linux and mac arm64 packages
* update SHA256
* add comment
* disable add_rpath for tbb libraries on mac arm64
---------
Co-authored-by: Chen Peter <peter.chen@intel.com>
* [GPU] Resolve failed unit-tests on dGPU
+ Modified unit-tests of asymetric conv with per channel(WA for oneDNN issue)
+ Modified conv unit-tests with padded input or output
+ For testing oneDNN conv, it needs to query oneDNN about format. Applied this to conv tests.
+ Modified accuracy checking logic in unit-tests which have different format on dGPU.
+ reorder from fsv16 to bfyx should not be optimized out if not aligned by 16
Signed-off-by: Min, Byungil <byungil.min@intel.com>
* Fix of class conflicts in different frameworks.
* Remove commented code.
* Moved FakeQuantWithMinMaxVars to common part.
* Fixed BOM package test.
* Removed not needed code.
* Removed not needed code.
* Path retrieval fix
* More detailed messages in the failing test
* Exe path with model name
---------
Co-authored-by: Michal Lukaszewski <michal.lukaszewski@intel.com>
* [GPU] Fix dump_graph failure issue in levit-128s model.
1. to_string() in strided_slice always access begin/end/stride param id from dependencies
regardless of max dependencies.
2. Add an exception in dump_full_node(). It helps below.
- Avoid a dump failure. Usually, graph dump are used during debugging,
which reduces unnecessary debugging time due to graph dump failure.
- You can immediately see which node has failed, making it easy to find it.
Signed-off-by: hyunback <hyunback.kim@intel.com>
* Revert "Revert "[CPU] optimize shape infer of Reshape (#16537)" (#16703)"
This reverts commit 06cacfe2a7.
* fix reshape connext with nonzero issue
Signed-off-by: Hu Yuan2 <yuan2.hu@intel.com>
* add nonzero connect with reshape testcase
Signed-off-by: Hu Yuan2 <yuan2.hu@intel.com>
* add debug code
Signed-off-by: Hu Yuan2 <yuan2.hu@intel.com>
* fix test case issue
fix shape_nonzero testcase issue
fix a bug in origin test case
Signed-off-by: Hu Yuan2 <yuan2.hu@intel.com>
* Revert "add debug code"
This reverts commit c305464c8c.
* fix other review comments except test case
Signed-off-by: Hu Yuan2 <yuan2.hu@intel.com>
---------
Signed-off-by: Hu Yuan2 <yuan2.hu@intel.com>
* Fix Interpolate-11 in MO
* Add forgotten file
* Fix output type of TopK-11
* Do not force precision on port 1 for mode scales
* Update tools/mo/openvino/tools/mo/ops/interpolate.py
---------
Co-authored-by: Ilya Lavrenov <ilya.lavrenov@intel.com>
Co-authored-by: Andrei Kochin <andrei.kochin@intel.com>
Co-authored-by: Roman Kazantsev <roman.kazantsev@intel.com>
