IntenseWebs/openvino
3
0 Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity
13,118 Commits 38 Branches 54 Tags
c20d52dc4fe9c5300baf1a6afcef8fc9e04cdef7
Commit Graph
5332 Commits
Author SHA1 Message Date
Tomasz Jankowski 0effa37811 [core] Migrate HSigmoid operator to new API (#20836) 
* Drop ngraph remains

* Use ov::Tensor

instaed of ngraph::HostTensor
 2023-11-03 09:10:32 +01:00
Vitaliy Urusovskij 0955faef93 Remove use of convertOps2Nodes() & convert2OutVect() (#20837) 2023-11-03 11:00:33 +04:00
Vitaliy Urusovskij caa81a0b3c Remove use of legacy ng/runtime/shared_buffer.hpp (#20840) 2023-11-03 09:09:49 +04:00
Andrei Gorbachev ff7b49c14d add a few tests (#20824) 2023-11-02 16:40:47 +00:00
Pawel RaaszandTomasz Jankowski 8e4c4c3510 [core]Drop host tensor support in TensorAccessor (#20831) 
* Remove functions`get_tensor_data_as for HostTensor

* Remove HostTensor support in TA

* Update doxy comments

Co-authored-by: Tomasz Jankowski <tomasz1.jankowski@intel.com>

---------

Co-authored-by: Tomasz Jankowski <tomasz1.jankowski@intel.com>
 2023-11-02 16:15:52 +00:00
Aleksandr Voron e8f21eefae [CPU] Add FP16 support to MatrixNms (#20804) 2023-11-02 14:40:32 +00:00
Pawel Raasz f8cd53bb77 [core]Migrate Floor operator to new API (#20830) 
* Migrate Floor operator to new API

* Remove `visit_attributes` is same as base class
 2023-11-02 12:35:05 +00:00
Roman Kazantsev 4a6e6e64c5 [TF FE] Fix conversion of FILM of keras.Model format (#20825) 
Signed-off-by: Kazantsev, Roman <roman.kazantsev@intel.com>
 2023-11-02 12:46:57 +04:00
Gorokhov Dmitriy 3ff85ae70a [CPU] Fixed port mismatch in Eltwise fusion graph optimization (#20782) 2023-11-02 11:33:37 +04:00
Vladimir Paramuzov 2afb64b9ea [GPU] Refactor KV cache test (#20802) 2023-11-02 09:54:19 +04:00
Zhang Yi 88c3171742 [CPU] Fix avx2 gather of bfloat16 (#20683) 2023-11-02 09:46:03 +04:00
Mateusz Tabaka 4084e9acc0 Handle Reshape's special zero in SimplifySecondInputOfReshape (#20785) 
* Handle Reshape's special zero in SimplifySecondInputOfReshape

SimplifySecondInputOfReshape detects ShapeOf->Gather->Concat
subgraphs on Reshape's second input and replaces ShapeOf->Gather
with a Constant with zero(s). Currently it works only with Reshapes
that have special_zero set to true, but it can work for Reshapes
with special_zero == false if non-Gather inputs to Concat are Constants
and don't contain any zero.

Ticket: CVS-123434

* fix no default output
 2023-11-01 18:02:36 +04:00
Nikolay Shchegolev e6ff5edc3d [CPU] Empty tensor used with a custom op leads to CPU plugin exception. (#19733) 2023-11-01 15:42:25 +04:00
Surya Siddharth Pemmaraju bb0e4f8ecf Fixed issue with cat in fx backend (#20744) 
* Added fix for cat in torchfx

* Added batch_norm_legit_no_training op

* Fixed coding style

* Fixed clang format

* Addressed PR comments
 2023-11-01 08:36:19 +01:00
Roman Kazantsev 26c9c41b8e Revert "[TF FE] Switch off TF1 While support totally (#20774)" (#20800) 
This reverts commit 38b6092120.
 2023-10-31 22:53:35 +04:00
Irina Efode dd10a520e3 [DO NOT REVIEW OR MERGE] LLM in SubgraphsDumper (#20756) 2023-10-31 16:57:41 +01:00
Sofya Balandina 65f6950f56 [apiConformance][TEMPLATE] Add too get_profiling_info info about ops (#20697) 2023-10-31 16:14:36 +01:00
Irina Efode 8eee1b52ed [IE TESTS] ImportExport reporting + extension of base class (#20765) 
* [IE TESTS] ImportExport reporting + extension of base class

* reuse dynamic check
 2023-10-31 19:00:36 +04:00
Roman Kazantsev 8d6f56dd12 [TF FE] Fix translators for multiple output operations (#20787) 
Signed-off-by: Kazantsev, Roman <roman.kazantsev@intel.com>
 2023-10-31 13:22:09 +00:00
Mateusz Tabaka 48c9598892 Handle Reshape in SplitSqueezeConcatFusion (#20345) 
* Handle Reshape in SplitSqueezeConcatFusion

Ticket: CVS-122455

* move check for squeeze/reshape

* add some comments

* review comments

* add use_shapes flag to SplitSqueezeConcatFusion
 2023-10-31 17:05:21 +04:00
Nikolay Shchegolev 57571d36e6 [CPU] NMSRotated operation implementation. (#20410) 2023-10-31 12:10:52 +00:00
Pawel Raasz 3077bad26f [core]Migrate Sigmoid operator to new API (#20780) 
* Migrate Sigmoid operator to new API

* Add missing include
 2023-10-31 12:11:29 +01:00
Vladislav Golubev 2932e9e938 ReshapeBMatMul and ReshapeAMatMul: avoid circular dependencies creation (#20771) 2023-10-31 15:00:52 +04:00
Roman Kazantsev a20c9a5a22 [TF FE] Update TF FE dev docs with Inv (#20788) 
Signed-off-by: Kazantsev, Roman <roman.kazantsev@intel.com>
 2023-10-31 14:45:54 +04:00
Kelvin Choi bb28b71849 [GPU] if the reorder which is an user of reshpae has truncation mode, it should not split the reorder node (#20749) 2023-10-31 19:21:56 +09:00
Roman Kazantsev 38b6092120 [TF FE] Switch off TF1 While support totally (#20774) 
* [TF FE] Switch off TF1 While support totally

This is a total switch off due to GPU limitation

Signed-off-by: Kazantsev, Roman <roman.kazantsev@intel.com>

* Need additional fallback in Enter to avoid shapes problem

* Disable tests with While op

Signed-off-by: Kazantsev, Roman <roman.kazantsev@intel.com>

* Disable layer test for TF1 While

* Remove extra spaces

---------

Signed-off-by: Kazantsev, Roman <roman.kazantsev@intel.com>
 2023-10-31 12:46:36 +04:00
Pawel Raasz 38cd138d0d [core]Migrate Sqrt operator to new API (#20632) 
* Migrate Sqrt operator to new API

* Remove 'visit_attributes' is same as base
 2023-10-31 08:34:49 +00:00
Min, Byungil 00705e6e58 [GPU] Bugfix adjust padding size for reshape optimizing (#20773) 
Signed-off-by: Min, Byungil <byungil.min@intel.com>
 2023-10-31 17:24:35 +09:00
Vitaliy Urusovskij 1b46c73b51 Remove commented code from Proposal layer test (#20781) 2023-10-31 11:42:44 +04:00
rsato10andRoman Kazantsev 53820c0cf2 [TF FE]Support Inv operation for TensorFlow models (#20720) 
* [TF FE]Support Inv operation for TensorFlow models

* added test tests/layer_tests/tensorflow_tests/test_tf_Inv.py and src/frontends/tensorflow_common/src/op/inv.cpp

* Update tests/layer_tests/tensorflow_tests/test_tf_Inv.py

* Update tests/layer_tests/tensorflow_tests/test_tf_Inv.py

* Update tests/layer_tests/tensorflow_tests/test_tf_Inv.py

---------

Co-authored-by: Roman Kazantsev <roman.kazantsev@intel.com>
 2023-10-31 11:39:16 +04:00
Katarzyna Mitrus 1384471849 [ONNX][Code refactor] ONNX GroupNormalization - Optimize getting inputs 
* Optimize getting inputs and use more const

* Fix typo
 2023-10-31 11:19:11 +04:00
Vitaliy Urusovskij 991b9848fa PSROIPooling and Proposal layer tests to API2.0 (#20761) 
* `PSROIPoolingLayerTest` to API2.0

* `ProposalLayerTest` to API2.0
 2023-10-31 10:21:20 +04:00
River Li 9e97d7ef1a [C-API] add ov_get_last_error_msg() API (#20643) 2023-10-31 13:53:47 +08:00
Andrei GorbachevandPavel Durandin 44925b580f [GPU] Refactor Comparison, Conversion, ConvertColorI420 (#20374) 
* Comparison

* Conversion

* ConvertColorI420

* fix

* Comparison

* Conversion

* ConvertColorI420

* fix

* fix after review

* fix after review

* fix after review

* fixed comparison

---------

Co-authored-by: Pavel Durandin <pavel.durandin@intel.com>
 2023-10-31 09:50:20 +04:00
Anton Voronov d90e23fc30 [CPU] Sparse weights decompression feature: changed comp_tile_len data type from int16_t to int (#20707) 2023-10-31 09:34:27 +04:00
Wanglei Shen 78f11965d8 [CPU] Fix user setting num_streams=0 (#20469) 2023-10-31 09:23:58 +04:00
Roman Lyamin 50b6c5f0d7 [GPU] Fix for SoftmaxKernel_bf in dynamic case (#20769) 2023-10-31 09:02:03 +04:00
Roman Kazantsev fc4fe07a0e [TF FE] Fix CTCLoss translator (#20775) 
* Fix CTCLoss translator

Signed-off-by: Kazantsev, Roman <roman.kazantsev@intel.com>

* Expend layer tests for CTCLoss

---------

Signed-off-by: Kazantsev, Roman <roman.kazantsev@intel.com>
 2023-10-31 08:51:18 +04:00
Xiuchuan Zhai 0076f7fc00 [PD FE] loading weight from ov::tensor (#20044) 
* fix paddle load model from memory

* fix coding style

* ignore the deprecated api

* fix a istream bug; add test case

* simplify func variant_to_stream_ptr

* restore the previous impl for less memory affect

* fix memory leak
 2023-10-31 11:17:38 +08:00
Pawel RaaszandMichal Lukaszewski 246410b0dd [core]Migrate NotEqual operator to new API (#20648) 
* Migrate NotEqual operator to new API

* Remove `visit_attributes` is same as base

---------

Co-authored-by: Michal Lukaszewski <michal.lukaszewski@intel.com>
 2023-10-31 00:01:27 +00:00
Mateusz MikolajczykandKatarzyna Mitrus ce8ac6f478 [Opset13][TF FE] Enable tensorflow bitwise operators (#20340) 
* Add opset-13 bitwise ops

* Fix issue in BinaryOps test

---------

Co-authored-by: Katarzyna Mitrus <katarzyna.mitrus@intel.com>
 2023-10-30 23:18:28 +00:00
Pawel Raasz ac176beb33 [core]Migrate Clamp operator to new API (#20676) 
* Migrate Clamp operator to new API

* Remove not used function add comment
 2023-10-30 22:58:35 +00:00
Przemyslaw Wysocki 31f6a95122 [PyOV] Set inference precision explicitly to fp32 for torchvision tests (#20713) 
* Set fp32

* Fix flake

* use properties api
 2023-10-30 20:06:55 +01:00
Anastasia Kuporosova 5b583276b2 [PyOV] Add get_byte_size to const node (#20759) 2023-10-30 19:46:07 +01:00
Ekaterina Aidova c21fd2ea61 [PT FE]: fix object has no attribute 'dtype' (#20755) 
* [PT FE]: fix  object has no attribute 'dtype'

* add model in tests

* update test
 2023-10-30 18:36:08 +00:00
Roman Lyamin 7eb53586f5 [GPU] Added WA for MarkDequantizationSubgraph to work correctly in the plugin (#20767) 2023-10-30 17:58:34 +00:00
Wilson Seok df3e51f818 add comments about origin of reference implementation (#20763) 2023-10-30 21:54:19 +04:00
Katarzyna Mitrus fdec7fb7ee [Opset13][ONNX] NMSRotated-13 test and sort update (#20670) 
* Set sort_result_descending attr false for nms

* Add onnx test

* Tmp exclude for CPU

* Update test values

* Update test vals to avoid cast warning

* Fix typo
 2023-10-30 17:14:37 +01:00
Roman Kazantsev a4c47bf6ab [TF FE] Fix body graph injection, CumSum and SparseFillEmptyRows (#20680) 
* [TF FE] Fix body graph injection, CumSum and SparseFillEmptyRows

Signed-off-by: Kazantsev, Roman <roman.kazantsev@intel.com>

* Do not handle non-parameters in body

* Update layer test to cover default parameter and attribute values

* Fix layer tests

---------

Signed-off-by: Kazantsev, Roman <roman.kazantsev@intel.com>
 2023-10-30 18:40:09 +04:00
Sofya Balandina 061d6b5b62 [apiConformance] Move sw plugin to run with Template only (#20084) 
* [apiConformance] Move sw plugin to run over TEMPLATE

* Fix set_property

* update

* add configs for sw plugins
 2023-10-30 17:45:46 +04:00