Maxim Andronov
46fea0fe48
[CPU] Split dynamism support ( #8419 )
2021-11-16 14:13:02 +03:00
Aleksandr Korolev
da0b8a84b4
[IE][VPU] Fix memory leak ( #8554 )
...
[VPU] heap-use-after-free fix
2021-11-16 11:52:49 +03:00
Evgeny Kotov
6860fd3ef4
Substitute soft sign pass port to ngraph ( #8167 )
...
* add base ngraph::SoftSign operation wrapper; add substite softsign pass draft code
* add SoftSign convertor from ngraph to CNNNetwork
* add unit tests; write DoTransformation
* cpplint fixes
* add pass description
* cleanups; always use add layer
* remove bf16 since it is CPU specific
* add softsign evaluate unit test; code review fixes
* add unit tests on checking const values
* inherit softsign from :UnaryElementwiseArithmetic; code review fixes
* remove unneeded visit_attributes
* remove NGRAPH_TYPE_CASE macro
* use ngraph::op::util::get_single_value in pattern checking
* use legacy SubstituteSoftSignPass if there are FQ layers; build fix
* remvoe deprecated softsign tests
* fix deprecated error
* add draft unit tests on softsign operation with new api
* use new test API for softsign
* use another evaluate virtual method
2021-11-16 11:27:37 +03:00
Katarzyna Mitrus
95e1a423c6
[ONNX FE] ONNX Clip type aligned default min/max fix ( #8489 )
2021-11-16 09:25:21 +01:00
Anton Chetverikov
d0f16d205a
GatherND_8 reference implementation ( #8257 )
...
* Add GatherND_8 operation
* Update shape infer function and tests
* Initial commit for nGraph GatherND_8 operation
* Add GatherNDBase class implementation
* Fix base class errors
* Add missrd header
* Update base class
* Update GatherND_8 implementation
* Fix codestyle
* Fix wrong rank
* Implement tests for gatherND_8 shape inference function
* fix codestyle
* Add limitation to doc
* Siplyfy check in shape inference
* Add more test cases
* Update shape inference function
* Add more test cases to cover all case with dynamic input shapes
* Update shape inference function
* Refactor tests
* Initial commit for gatherND_8 reference implementation
* Add visitor tests for gatherND_8 operation
* Add visitor tests for gatherND_8 operation
* Correct comment
* Add additional check is shape inference function
* Update shape inference implementation for gathernd operartion
* Fix codestyle
* Remove restriction for data is fully defined
* Update shape inference functon
* Add gatherND_8 reference to evaluate map
* Add tests for gathernd_8 reference in batch_dims > 1
* Fix codestyle
* Fix codestyle
* Fix missed check for nonetype
* Remove redundant checks for batch_dims
* Use get_shape method instead of get_input_shape in GatherND reference implementation call
* update reference implementation call
* Properly add GatherND_8 to test opset table
* Update GatherND reference implementation for support opset8 version
* Add unit tests for gatherND_8 reference implementation
* Update gatherND reference implementation call in evaluate map
* Mark failed tests for missed plugin gatherND_8 implementations
* Fix codestyle
* Fix codestyle
* Fix codestyle
* Update tests
* Move common methods to base class
* Fix codestyle
* Revert clone_with_new_input function moving
* Add more test for reference
* partially revert API changes
2021-11-16 10:58:06 +03:00
Mikhail Letavin
b6bdc4a567
[GPU] Enable new OV2.0 infer request behavior tests ( #8358 )
2021-11-16 10:07:39 +03:00
Steve Yoo
90094e8a8a
Migrate Sequence (CTCGreedyDecoder-1, CTCGreedyDecoderSeqLen-6, GRUCell-3, LSTMCell-4, OneHot-1, RNNCell-1) and Sort (ExperimentalDetectronTopKROIs-6) ( #8314 )
2021-11-16 08:46:21 +03:00
Zhibin Li
4edb7c6f34
NMS: change back threshold for comparison ( #8553 )
2021-11-16 07:49:50 +03:00
Ilya Lavrenov
9676e643cf
Fixed ie_mark_target_as_cc ( #8608 )
2021-11-16 06:48:02 +03:00
Ilya Lavrenov
09653b0d9c
Fixed coverity issue ( #8572 )
2021-11-16 06:42:26 +03:00
song, bell
9ccc308523
Bell/revise lstm cell sequence ( #7638 )
...
* revise LSTM spec
Signed-off-by: fishbell <bell.song@intel.com>
* add param check and related test case
Signed-off-by: fishbell <bell.song@intel.com>
* fix clang-format
Signed-off-by: fishbell <bell.song@intel.com>
* use static_cast to replace c style force conversion
Signed-off-by: fishbell <bell.song@intel.com>
2021-11-16 06:13:26 +03:00
Steve Yoo
f66d9216ef
Migrate Movement 2 (BatchToSpace-2, DepthToSpace-1, Roll-7, ShuffleCha… ( #8158 )
...
* Migrate Movement2 (BatchToSpace-2, DepthToSpace-1, Roll-7, ShuffleChannels-1, SpaceToBatch-2, SpaceToDepth-1)
* Fix typos while copying
* Update to opset namespace and add i4, u4, bf16 tests when available
* Remove i4, u4 tests from BatchToSpace and Roll
2021-11-16 03:32:29 +03:00
Mateusz Tabaka
c5d0dc3e5f
[GPU] fix constant shape if its user has scalar inputs ( #8564 )
...
* [GPU] fix constant shape if its user has scalar inputs
Currently for nodes like:
```
Multiply(input{}, mul_const{2}) -> mul{2}
```
cldnn sets 'mul_const' shape to (1, 2, 1, 1), which may not be correct if it's followed by
```
Add(mul{2}, add_const{2}) -> add{2}
```
because 'mul' shape is (1, 2, 1, 1), 'add_const' shape is (2, 1, 1, 1)
and the result becomes (2, 2, 1, 1) instead of expected (2, 1, 1, 1)
* Add tests for the issue
2021-11-15 22:08:02 +03:00
Artur Kulikowski
2e9f83d705
Axis normalizing in ArgMin/ArgMax operations ( #8589 )
2021-11-15 16:10:24 +01:00
song, bell
e279ec5962
borrow device memory for AUTO:GPU case to avoid performance gap ( #8389 )
...
* borrow device memory for AUTO:GPU case to avoid performance gap
Signed-off-by: fishbell <bell.song@intel.com>
* simplify the logic
Signed-off-by: fishbell <bell.song@intel.com>
2021-11-15 17:59:09 +03:00
Anton Romanov
cac45e4f29
Fixed cnpy coverity issues ( #8515 )
2021-11-15 17:24:48 +03:00
Vladimir Paramuzov
3b34f09a9b
[GPU] Fixed friendly name of out transpose, improve Pad performance ( #8546 )
...
* Fixed friendly names in post-processing nodes
* [GPU] Added fsv16 support for pad operation
2021-11-15 17:07:58 +03:00
Alexandra Sidorova
5352c2b370
commented test ( #8596 )
2021-11-15 17:01:02 +03:00
Anastasia Popova
f800993e6f
Fix of ReverseInputChannels for NHWC layout. ( #8504 )
...
* Fixed ReverseInputChannels for new api.
* Renamed function, added node name in assert, code refactoring.
* Added ReverseChannels propagation through transposes.
* Refactored get_fw_index() method.
* Fixed wrong name.
* Added negative axis support.
2021-11-15 15:24:46 +03:00
Victor Kuznetsov
925e24525a
Move unit_tests from test_pkg/tools to test_pkg/tests ( #8548 )
...
* add performance hint to time infer
* move unit_tests to tests pkg
* change unit_tests path in azure lin
* change path to mo in bom test
* fix tests_path
* change mo dir path
2021-11-15 14:18:16 +03:00
Alexey Lebedev
4a1cfdc9ff
[PYTHON API] update InferQueue ( #8513 )
...
* Bind exec core ov (#50 )
* Output const node python tests (#52 )
* add python bindings tests for Output<const ov::None>
* add proper tests
* add new line
* rename ie_version to version
* Pszmel/bind infer request (#51 )
* remove set_batch, get_blob and set_blob
* update InferRequest class
* change InferenceEngine::InferRequest to ov::runtime::InferRequest
* update set_callback body
* update bindings to reflect ov::runtime::InferRequest
* bind set_input_tensor and get_input_tensor
* style fix
* clen ie_infer_queue.cpp
* Bind exec core ov (#50 )
* bind core, exec_net classes
* rm unused function
* add new line
* rename ie_infer_request -> infer_request
* update imports
* update __init__.py
* update ie_api.py
* Replace old containers with the new one
* create impl for create_infer_request
* comment out infer_queue to avoid errors with old infer_request
* update infer_request bind to reflect new infer_request api
* comment out inpuit_info from ie_network to avoid errors with old containers
* Register new containers and comment out InferQueue
* update infer request tests
* style fix
* remove unused imports
* remove unused imports and 2 methods
* add tests to cover all new methods from infer_request
* style fix
* add test
* remove registration of InferResults
* update name of exception_ptr parameter
* update the loops that iterate through inputs and outputs
* clean setCustomCallbacks
* style fix
* add Tensor import
* style fix
* update infer and normalize_inputs
* style fix
* rename startTime and endTime
* Create test for mixed keys as infer arguments
* update infer function
* update return type of infer
Co-authored-by: Bartek Szmelczynski <bartosz.szmelczynski@intel.com>
* fix get_version
* fix opaque issue
* some cosmetic changes
* fix codestyle in tests
* make tests green
* Extend python InferRequest
* Extend python Function
* Change return value of infer call
* Fix missing precisions conversions in CPU plugin
* Rework of runtime for new tests
* Fixed onnx reading in python tests
* Edit compatibility tests
* Edit tests
* Add FLOAT_LIKE xfails
* [Python API] bind ProfilingInfo (#55 )
* bind ProfilingInfo
* Add tests
* Fix code style
* Add property
* fix codestyle
* Infer new request method (#56 )
* fix conflicts, add infer_new_request function
* remove redundant functions, fix style
* revert the unwanted changes
* revert removal of the Blob
* revert removal of isTblob
* add add_extension from path
* codestyle
* fix win build
* add inputs-outputs to function
* update infer queue
* fix code style
* Hot-fix CPU plugin with precision
* fix start_async
* add performance hint to time infer (#8480 )
* Updated common migration pipeline (#8176 )
* Updated common migration pipeline
* Fixed merge issue
* Added new model and extended example
* Fixed typo
* Added v10-v11 comparison
* Avoid redundant graph nodes scans (#8415 )
* Refactor work with env variables (#8208 )
* del MO_ROOT
* del MO_ROOT from common_utils.py
* add MO_PATH to common_utils.py
* change mo_path
* [IE Sample Scripts] Use cmake to build samples (#8442 )
* Use cmake to build samples
* Add the option to set custom build output folder
* Remove opset8 from compatibility ngraph python API (#8452 )
* [GPU] OneDNN gpu submodule update to version 2.5 (#8449 )
* [GPU] OneDNN gpu submodule update to version 2.5
* [GPU] Updated onednn submodule and added layout optimizer fix
* Install rules for static libraries case (#8384 )
* Proper cmake install for static libraries case
* Added an ability to skip template plugin
* Added install rules for VPU / GPU
* Install more libraries
* Fixed absolute TBB include paths
* Disable GNA
* Fixed issue with linker
* Some fixes
* Fixed linkage issues in tests
* Disabled some tests
* Updated CI pipelines
* Fixed Windows linkage
* Fixed custom_opset test for static casr
* Fixed CVS-70313
* Continue on error
* Fixed clanf-format
* Try to fix Windows linker
* Fixed compilation
* Disable samples
* Fixed samples build with THREADING=SEQ
* Fixed link error on Windows
* Fixed ieFuncTests
* Added static Azure CI
* Revert "Fixed link error on Windows"
This reverts commit 78cca36fd2
2021-11-15 14:12:24 +03:00
Svetlana Dolinina
e6884c3fd7
Remove ExecutableNetwork::QueryState ( #8034 )
...
* removed ExecutableNetwork::QueryState from code
* removed ExecutableNetwork::QueryStates from tests (not checked)
* buildable version
* remove unneeded change and fix cpplint error
* remove extra space
* remove QueryState from GNAExecutableNetwork
* clean up GNA tests for QueryState in tests_deprecated (without replacement because deprecated)
* fix tests after merge
* remove tests again after merge
* fixed tests with _REGULAR_API suffix
2021-11-15 13:58:26 +03:00
Xiping Yan
3354275da1
Xp/revise embedding bag ( #7694 )
...
* Fix: variable writing error.
mas_dimension -> max_dimension
Signed-off-by: Yan, Xiping <xiping.yan@intel.com>
* Update description.
Signed-off-by: Yan, Xiping <xiping.yan@intel.com>
* Update EmbeddingBagOffsetsSum comment, it will be easy to understand how to calculate bag.
Signed-off-by: Yan, Xiping <xiping.yan@intel.com>
* Add attribute description for md
Signed-off-by: Yan, Xiping <xiping.yan@intel.com>
* WIP: Add correctness test.
Known issue:
1: weight fp16 issue.
2: default idx(1), don't choose in segment id. why?
Signed-off-by: Yan, Xiping <xiping.yan@intel.com>
* change param order.
Signed-off-by: Yan, Xiping <xiping.yan@intel.com>
* Support test T_IND type (int32 and int64)
Signed-off-by: Yan, Xiping <xiping.yan@intel.com>
* weight support multiple type input.
Signed-off-by: Yan, Xiping <xiping.yan@intel.com>
* refactor correctness test code.
Signed-off-by: Yan, Xiping <xiping.yan@intel.com>
* embeddingbag offset sum correctness test pass.
Signed-off-by: Yan, Xiping <xiping.yan@intel.com>
* embeddingbag packed sum correctness test pass.
Signed-off-by: Yan, Xiping <xiping.yan@intel.com>
* Add visitor without attribute test.
Signed-off-by: Yan, Xiping <xiping.yan@intel.com>
* Add EmbeddingSegmentsSum serialization test.
Signed-off-by: Yan, Xiping <xiping.yan@intel.com>
* Add EmbeddingBagPackedSum, EmbeddingBagOffsetsSum serialization test.
Signed-off-by: Yan, Xiping <xiping.yan@intel.com>
* fix build error after rebase.
Signed-off-by: Yan, Xiping <xiping.yan@intel.com>
* unify name: from ngraph:: to ov::
Signed-off-by: Yan, Xiping <xiping.yan@intel.com>
* add fp64 support
Signed-off-by: Yan, Xiping <xiping.yan@intel.com>
* Remove my MACRO define wrappers.
Signed-off-by: Yan, Xiping <xiping.yan@intel.com>
* Remove useless header file.
* tmp. pass.
* Remove MACRO warpper for embeddingbag_offsetsum
* Remove myown wrapper header, and update template plugin.
Signed-off-by: Yan, Xiping <xiping.yan@intel.com>
* Change vector to ov::Shape.
Signed-off-by: Yan, Xiping <xiping.yan@intel.com>
* Rename CreateConstantVV-> CreateConstant
Signed-off-by: Yan, Xiping <xiping.yan@intel.com>
* Fix rebase issue. duplicate case ov::element::f64:
Signed-off-by: Yan, Xiping <xiping.yan@intel.com>
2021-11-15 13:49:21 +03:00
Ilya Lavrenov
8cb17ca218
Enable GPU in static build w/o oneDNN ( #8563 )
...
* Enable LTO for oneDNN GPU
* Use importer target for onednn_gpu
* Fixed install of OpenCL, ittapi
* Try to enable samples build
* Fixed ie_wheel build
* Disabled samples
* Fixed incorrect install of pugixml in dynamic build
2021-11-15 13:44:11 +03:00
Alexandra Sidorova
c82744e435
[CPU] Added dynamism support for Pad ( #8396 )
2021-11-15 13:37:34 +03:00
Indira Salyahova
29a3f56003
[POT] Add pattern se blocks ( #8425 )
...
* fix(patterns): add pattern se_block
* update reference
2021-11-15 12:53:07 +03:00
Alexandra Sidorova
c981d2f0dd
[CPU] Added dynamism support for DepthToSpace ( #8375 )
2021-11-15 12:06:41 +03:00
Vladimir Paramuzov
f3e1dc25b2
[GPU] GPU Remote tensor API update ( #8485 )
2021-11-15 09:58:12 +03:00
Steve Yoo
b320061ea3
Migrate Movement 1 (Gather-1, Gather-7, Pad-1) ( #8414 )
2021-11-15 04:31:59 +03:00
Pavel Zamelin
beaec484bb
fix skip in wait, io_tensor tests ( #8503 )
2021-11-15 03:16:36 +03:00
Maksim Kutakov
3c985ed592
[CPU] Reference node shape infer is now always called ( #8517 )
2021-11-14 11:16:36 +03:00
Tingqian Li
57900a4a18
Add constructor to allow implict convertion at compile-time but not at run-time ( #8525 )
...
Signed-off-by: Li, Tingqian <tingqian.li@intel.com>
2021-11-13 14:05:09 +03:00
Ilya Lavrenov
8abf1eca7a
Fixed ie_wheel build ( #8565 )
2021-11-12 23:05:53 +03:00
Maxim Vafin
fbf1343ff5
Check if argv has compress_fp16 attribute ( #8545 )
2021-11-12 22:54:10 +03:00
Ilya Znamenskiy
c565799c71
[GPU] Moving onednn post ops logic into cldnn::program_node ( #8511 )
2021-11-12 22:48:55 +03:00
Anastasia Kuporosova
2c9a4c59f2
[Python API] add new api ( #8149 )
...
* Bind exec core ov (#50 )
* Output const node python tests (#52 )
* add python bindings tests for Output<const ov::None>
* add proper tests
* add new line
* rename ie_version to version
* Pszmel/bind infer request (#51 )
* remove set_batch, get_blob and set_blob
* update InferRequest class
* change InferenceEngine::InferRequest to ov::runtime::InferRequest
* update set_callback body
* update bindings to reflect ov::runtime::InferRequest
* bind set_input_tensor and get_input_tensor
* style fix
* clen ie_infer_queue.cpp
* Bind exec core ov (#50 )
* bind core, exec_net classes
* rm unused function
* add new line
* rename ie_infer_request -> infer_request
* update imports
* update __init__.py
* update ie_api.py
* Replace old containers with the new one
* create impl for create_infer_request
* comment out infer_queue to avoid errors with old infer_request
* update infer_request bind to reflect new infer_request api
* comment out inpuit_info from ie_network to avoid errors with old containers
* Register new containers and comment out InferQueue
* update infer request tests
* style fix
* remove unused imports
* remove unused imports and 2 methods
* add tests to cover all new methods from infer_request
* style fix
* add test
* remove registration of InferResults
* update name of exception_ptr parameter
* update the loops that iterate through inputs and outputs
* clean setCustomCallbacks
* style fix
* add Tensor import
* style fix
* update infer and normalize_inputs
* style fix
* rename startTime and endTime
* Create test for mixed keys as infer arguments
* update infer function
* update return type of infer
Co-authored-by: Bartek Szmelczynski <bartosz.szmelczynski@intel.com>
* fix get_version
* fix opaque issue
* some cosmetic changes
* fix codestyle in tests
* make tests green
* Extend python InferRequest
* Extend python Function
* Change return value of infer call
* Fix missing precisions conversions in CPU plugin
* Rework of runtime for new tests
* Fixed onnx reading in python tests
* Edit compatibility tests
* Edit tests
* Add FLOAT_LIKE xfails
* [Python API] bind ProfilingInfo (#55 )
* bind ProfilingInfo
* Add tests
* Fix code style
* Add property
* fix codestyle
* Infer new request method (#56 )
* fix conflicts, add infer_new_request function
* remove redundant functions, fix style
* revert the unwanted changes
* revert removal of the Blob
* revert removal of isTblob
* add add_extension from path
* codestyle
* fix win build
* add inputs-outputs to function
* Hot-fix CPU plugin with precision
* fix start_async
* add performance hint to time infer (#8480 )
* Updated common migration pipeline (#8176 )
* Updated common migration pipeline
* Fixed merge issue
* Added new model and extended example
* Fixed typo
* Added v10-v11 comparison
* Avoid redundant graph nodes scans (#8415 )
* Refactor work with env variables (#8208 )
* del MO_ROOT
* del MO_ROOT from common_utils.py
* add MO_PATH to common_utils.py
* change mo_path
* [IE Sample Scripts] Use cmake to build samples (#8442 )
* Use cmake to build samples
* Add the option to set custom build output folder
* Remove opset8 from compatibility ngraph python API (#8452 )
* [GPU] OneDNN gpu submodule update to version 2.5 (#8449 )
* [GPU] OneDNN gpu submodule update to version 2.5
* [GPU] Updated onednn submodule and added layout optimizer fix
* Install rules for static libraries case (#8384 )
* Proper cmake install for static libraries case
* Added an ability to skip template plugin
* Added install rules for VPU / GPU
* Install more libraries
* Fixed absolute TBB include paths
* Disable GNA
* Fixed issue with linker
* Some fixes
* Fixed linkage issues in tests
* Disabled some tests
* Updated CI pipelines
* Fixed Windows linkage
* Fixed custom_opset test for static casr
* Fixed CVS-70313
* Continue on error
* Fixed clanf-format
* Try to fix Windows linker
* Fixed compilation
* Disable samples
* Fixed samples build with THREADING=SEQ
* Fixed link error on Windows
* Fixed ieFuncTests
* Added static Azure CI
* Revert "Fixed link error on Windows"
This reverts commit 78cca36fd2
2021-11-12 22:44:44 +03:00
Ilya Lavrenov
a0b5de0c88
Fixed incorrect install of pugixml in dynamic build ( #8566 )
2021-11-12 22:42:27 +03:00
Ilya Znamenskiy
57eff5c287
[GPU] Fixed pooling_imad kernel error and expanded corresponding tests ( #8527 )
2021-11-12 22:19:58 +03:00
Mateusz Tabaka
b305a01e21
[ONNX] don't set friendly names after processing Identity node ( #8432 )
...
unless the Identity node is connected to output
Ticket: 69827
2021-11-12 16:10:50 +01:00
Mateusz Tabaka
b36fe0d966
Add support for ONNX operator com.microsoft.Attention ( #8008 )
...
Ticket: 62890
2021-11-12 15:35:46 +01:00
Svetlana Dolinina
ae6b16c084
Add outputs for nodes from loops ( #7844 )
...
* initial version of transformation workable for loop
* moved transformation to back + minor changes in result names
* fixed mistake: to concatenate results of all iterations Unsqueeze should be added
* added shape inference for new nodes and extend test
* added support of TensorIterator
* If support + test;
fix to save model with TI after transformation
* fix code and tests according to run with ir_reader
* added finding max internal_layer_id in sub-graph + added comments to code
* turn off transformation because it should not be used in MO scenarios
* refactor code to find out iterations count for TensorIterator
* chenged name of final result to srtucture loop1.loop2.node for path [loop1, loop2, node]
* change port number to index of added output
* return list of new nodes
* change naming of output to standard way;
return result node as output of transformation
* refactor transformation, add more comments; fine up tests
* review fixes: add more comments, refactoring of infer function, fix in iterations count calculation
* added processing of dynamic iterations count + tests
* moved iterations count calculation to TI
* fixed bug in iterations count calculation
* fix bug with adding iterations count to wrong dimension + test
* review fixes: minor renaming + fixed bug with unset stride for TI
* move logic with output record outside function calculation iteration count;
fix case with negative start/end;
fix case when division result is not integer;
added tests for such cases
* review fixes: refactoring of toerations count calculation
2021-11-12 17:02:15 +03:00
Min, Byungil
338aad25db
[GPU] Resolve performance regression by selecting ref kernel ( #8550 )
...
- Not to select fsv16 for u8 to fp32 conv
Signed-off-by: Min, Byungil <byungil.min@intel.com>
2021-11-12 16:39:47 +03:00
Alexey Varyzgin
1f597321de
[CPU][BF16] Concat layer properly handle mixed precision input ( #7715 )
2021-11-12 16:03:16 +03:00
Anastasia Kuporosova
2d27b73de9
[Python API] Integrate pyopenvino into wheel ( #8536 )
2021-11-12 13:34:57 +03:00
Ilya Churaev
7c33a0c609
Fixed clone_with_new_inputs for type_relaxed ops ( #8541 )
...
* Fixed clone_with_new_inputs for type_relaxed ops
* Fixed comment
2021-11-12 13:28:01 +03:00
Steve Yoo
7a7ea100ec
Migrate Movement 1 Operations (StridedSlice-1) ( #8221 )
...
* Migrate StridedSlice-1
* Update generate function to literals for bf16 and f16
* Add shapes to tensors
2021-11-12 12:19:19 +03:00
hyunback kim
e707338909
[GPU] Fix input memory calcuation in allocate_output. ( #8463 )
2021-11-12 12:07:06 +03:00
Ilya Churaev
471211bc4c
Fixed coverity issue ( #8529 )
2021-11-12 11:23:47 +03:00
Ivan Tikhonov
00c7da0f5f
[TF FE] Implement and refactor tensorflow layer tests ( #8051 )
...
* Revert submodule changes
* Fix build on Win
* Fix precommit: set correct shapes for broadcasting; disable check with ref for use_new_frontend mode
* fix precommit
* Fix precommits
* Temporary skip new tests on GPU with FP16
* Resolve review comments, trigger CI
* Resolve review comments
* Resolve review comments
2021-11-12 11:03:45 +03:00
Alexey Varyzgin
6ac18bbd1b
[CPU] Deconvolution fusing for 1x1 kernel and 2x2 stride ( #7958 )
2021-11-12 09:50:32 +03:00
