Commit Graph
594 Commits
Author SHA1 Message Date
FisherandXiuchuan Zhai 99a7fa1287 【PaddlePaddle Hackathon 4】Add paddle op mapper silu (#15874)
* Add paddle op mapper silu

* Add more test cases

* Add dynamic shape test for op silu

---------

Co-authored-by: Xiuchuan Zhai <xiuchuan.zhai@intel.com>
2023-05-12 13:11:31 +08:00
NetPunkandXiuchuan Zhai 306df51001 【PaddlePaddle Hackathon 4】add paddle grid_sampler op (#15869)
* update op linspace

* rewrite function name

* add paddle grid_sample op mapping

* add op_fuzzy

* adjust op logic

* adjust op name

* format code

* add tests

* adjust test

* adjust test

* adjust test

* adjust test

* format code

---------

Co-authored-by: Xiuchuan Zhai <xiuchuan.zhai@intel.com>
2023-05-12 13:11:04 +08:00
Mateusz Bencer 5eab00a116 Fixed default value of score threshold (#17448) 2023-05-10 13:49:35 +02:00
Ekaterina AidovaandMaxim Vafin 66e1af18b5 [Pt FE]: aten::embedding_bag (#17098)
* [Pt FE]: aten::embedding_bag

* Update src/frontends/pytorch/src/op_table.cpp

Co-authored-by: Maxim Vafin <maxim.vafin@intel.com>

---------

Co-authored-by: Maxim Vafin <maxim.vafin@intel.com>
2023-05-10 09:44:08 +02:00
Katarzyna Mitrus 43936bd18a [ONNX FE] ONNX Resize (1-10) import use scale input and fix (#16789) 2023-05-09 12:05:29 +01:00
Roman Kazantsev eb178a753b [TF FE] Handle incorrect models (empty, fake) by TF FE (#17408)
* [TF FE] Handle incorrect models (empty, fake) by TF FE

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

* Apply suggestions from code review

---------

Signed-off-by: Kazantsev, Roman <roman.kazantsev@intel.com>
2023-05-09 00:00:12 -07:00
Evgenya Stepyreva af3d1d69dd Segment Sum renamed in common lib (#17378) 2023-05-08 11:00:58 +04:00
Maxim Vafin 48604e9092 Support sizes input as list to upsample ops (#17350) 2023-05-07 19:23:51 +02:00
Roman Kazantsev fb38fcef2b [TF FE] Refer Frontend Extension page in case unsupported operations (#17387)
Signed-off-by: Kazantsev, Roman <roman.kazantsev@intel.com>
2023-05-06 06:20:13 +01:00
Roman Kazantsev b6098fed90 [TF FE] Provide single tensor names for inputs and outputs in SavedModel (#17370)
* [TF FE] Provide single tensor names for inputs and outputs in SavedModel

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

* Fix build issue

* Xfail some cases due to internal problems in TF

* Xfail other layer test

* Extend documentation for function to adjust tensor names

* Use old path of tf2 layer testing for legacy frontend

---------

Signed-off-by: Kazantsev, Roman <roman.kazantsev@intel.com>
2023-05-06 05:37:47 +01:00
Mateusz Tabaka 48281376a0 [TF frontend] use InterpolateMode::LINEAR_ONNX if input rank is 4 (#17381)
This change mimicks LinearToLinearONNXReplacer transformation in
legacy frontend, where linear interpolate mode is replaced with
linear_onnx due to performance reasons.

Ticket: CVS-108343
2023-05-05 17:12:18 +02:00
PuQingandBo Liu bc6402fb27 【PaddlePaddle Hackathon 4】add paddle softshrink op (#15845)
* add softshrink

* Modify the implementation

* fix input unsigned

* fix name typo

* fix unsigned

* fix selct

* add input dtype check

---------

Co-authored-by: Bo Liu <bo4.liu@intel.com>
2023-05-04 16:18:44 +08:00
Maxim Vafin c1933fcaf0 [PT FE] Support default strides for avg and max pooling (#17337)
* Support default strides for avg and max pooling

* Fix code style

* Remove changes from other ticket
2023-05-04 09:27:10 +02:00
Piotr KrzemińskiandAndrei Kochin 1c286e4636 [PT FE] Add aten::all implementation (#16901)
* [PT FE] aten::all implementation with tests

* [PT FE] Add non-dynamic type check

* [PT FE] Update tests, temporarily turn off uint8 tests

* [PT FE] Fix dtype for uint8

* [PT FE] Apply suggested optimizations

---------

Co-authored-by: Andrei Kochin <andrei.kochin@intel.com>
2023-05-02 21:12:12 +02:00
Maxim Vafin 89d3eaa67f Fix issue with Pow when both inputs are scalars (#17305)
* Fix issue with Pow when both inputs are scalars

* Fix code style
2023-05-02 16:49:42 +02:00
Roman Kazantsev b253342ea6 [TF FE] Use original input types for SavedModel (#17295)
Also, refactor TF FE unit-tests

Signed-off-by: Kazantsev, Roman <roman.kazantsev@intel.com>
2023-05-01 15:46:29 +04:00
Piotr KrzemińskiandMaxim Vafin b7311d8907 [PT FE] Fix aten::chunk for dynamic shapes (#16902)
* [PT FE] Add replacer for chunk+getitem

* [PT FE] Fix missing replaced nodes, fix incorrent chunk size calculation

* [PT FE] Fix incorrect item shape, reduce tests count

* [PT FE] Convert back with frontend

---------

Co-authored-by: Maxim Vafin <maxim.vafin@intel.com>
2023-05-01 09:32:10 +00:00
Ilya Lavrenov 7743e175b7 Warn if OpenVINO symbols require new CXX ABI (#16080)
* Warn if OpenVINO symbols require new CXX ABI

* Fixed warnings / errors on Windows
2023-04-29 01:17:52 +01:00
Georgy Krivoruchko 835f51a5d2 [TF FE] Added additional pruned inputs for MetaGraph support (#17237)
* Added handling of additional pruned inputs
Added possible topology of RestoreV2 -> AssignVariableOp
Added additional checks

* Extended tests coverage
2023-04-28 13:03:33 +04:00
Mateusz Bencer 2b8a6ba99a condition to print warnings (#17195) 2023-04-27 13:43:32 +00:00
Ekaterina AidovaandMaxim Vafin 6389f423bf [PT FE]: implement scaled dot product attention (#17178)
* [PT FE]: implement scaled dot product attention

* Apply suggestions from code review

Co-authored-by: Maxim Vafin <maxim.vafin@intel.com>

* Update src/frontends/pytorch/src/op/scaled_dot_product_attention.cpp

Co-authored-by: Maxim Vafin <maxim.vafin@intel.com>

---------

Co-authored-by: Maxim Vafin <maxim.vafin@intel.com>
2023-04-26 12:51:02 +04:00
Roman Kazantsev 7cf9d109e8 [TF FE] Implement optimal conversion of body graphs (#17211)
* [TF FE] Implement optimal conversion of body graphs

Preliminary setting input shapes and types for body graph InputModel
provides more optimal conversion of body-graphs.

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

* Fix build issue

---------

Signed-off-by: Kazantsev, Roman <roman.kazantsev@intel.com>
2023-04-26 12:12:54 +04:00
Ilya Lavrenov 2e3deb8d8f Windows arm64 support for CPU plugin (#17075)
* ARM32 support

* ARM32 support

* Fixed packaging

* Windows arm64 support

* Updated submodule

* 32 bits support in Intel CPU plugin

* Fixed FIndAcl.cmake

* Enable proper conditional  compilation for Windows ARM64

* Enable proper conditional  compilation for Windows ARM64

* Updated submodule

* Updated submodule

* Updated submodule

* Updated submodule

* Updated submodule

* Added template_extension to CPU func tests dependencies

* Updated submodule

* Enabled runtime model tests

* Updated submodule

* Submodule update
2023-04-25 16:41:28 +04:00
Evgenya StepyrevaandTatiana Savina ee4ccec190 TensorFlow Lite FrontEnd: documentation changes (#17187)
* First glance doc changes

* Apply suggestions from code review

Co-authored-by: Tatiana Savina <tatiana.savina@intel.com>

* Update docs/MO_DG/prepare_model/convert_model/Convert_Model_From_TensorFlow_Lite.md

Co-authored-by: Tatiana Savina <tatiana.savina@intel.com>

---------

Co-authored-by: Tatiana Savina <tatiana.savina@intel.com>
2023-04-25 16:18:24 +04:00
Georgy Krivoruchko 3f07c8b48b [TF FE] Added MetaGraph file format (#16524)
* Separeted SavedModelVariablesIndex class from Saved Model

* Renamed SavedModelVariablesIndex class

* Enabled Tensorflow MetaGraph

* Enabled Tensorflow MetaGraph

* Covered VariableV2 and Assign nodes

* Applied review comments

* Added tests

* Added names to input/output ports too

* Fixed naming for using with MO

* Applied part of review comments

* Renamed meta.cpp and saved_model.cpp

* Applied shared_ptr for memory management of PtrNode

* Fixing CI

* Prevent cycles while passing thru graph

* Released requirement for Checkpointable Object Graph

* Changed naming approach to align port order

* Changed renaming order (before reordering)

* Added a Placeholder translator which checks updated shape

* WA missing Identity name

* Fix CI and restored lost translators after rebase

* WA for output names

* Removing unused params after cutting a model

* Prevents crash in case VariableV2 appears in freezed model

* Fixed saved model in case no variables.index found, but
variables exists

* Changed approach for handling native formats support

* Aligned behavior with freezing .meta files

* Fixed behavior for cutting a model by input tensor

* Applied review comments
2023-04-25 13:46:06 +04:00
Ekaterina Aidova 39ed9a624f [PT FE]: extend batch norm to support training mode (#17040) 2023-04-25 11:27:00 +02:00
Roman Kazantsev 3830125e3b [TF FE] Report the full list of unsupported operations (#17143) 2023-04-24 21:33:07 +00:00
Piotr KrzemińskiandMichal Lukaszewski 22a81e0e58 [PT FE] Enable stable tests for sort & argsort (#16415)
* [PT FE] Enable stable tests for sort & argsort

* Update test_argsort.py

* [PT FE] Update to opset11

* [PT FE] Remove redundant argument from argsort test

---------

Co-authored-by: Michal Lukaszewski <michal.lukaszewski@intel.com>
2023-04-25 01:21:16 +04:00
Tomasz DołbniakandMichal Lukaszewski 6ea9cc7149 ONNX FE - model loading fix (#17091)
* Path retrieval fix

* More detailed messages in the failing test

* Exe path with model name

---------

Co-authored-by: Michal Lukaszewski <michal.lukaszewski@intel.com>
2023-04-21 15:25:26 +04:00
Mateusz Bencer 77a5d1aa03 [ONNX FE] Fixed handling duplicates during graph extraction (#17071) 2023-04-20 11:10:09 +00:00
Evgenya Stepyreva 497a19edf6 CVS-102308 Read tflite model to vector (#17048) 2023-04-19 13:27:41 +00:00
Ilya Churaev 566ef01a3f Remove constructors for ov Exceptions (#16938)
* Remove constructors for ov Exceptions

* Fixed linux build

* Fixed ONNX Frontend

* Fixed paddle

* Fixed exceptions in tests

* Deprecate constructors for ov::Exception

* Suppress some warnings

* Merge several exceptions

* Some small changes

* Suppress more warnings

* More warnings

* mode warnings

* Suppress more warnings

* More warnings
2023-04-18 21:02:26 +04:00
Katarzyna Mitrus 2a5c69abc6 [ONNX FE] Fix ONNX DequantizeLinear-13 import dynamic shape (#16966) 2023-04-18 13:03:55 +02:00
Przemyslaw WysockiandIlya Lavrenov d72d833a96 [PyOV] Enable Python 3.11 (#15144)
* Bump ONNX version

* Bump protobuf

* Add xfails and skips

* Add tickets

* Skip ONNX Serialization tests

* Compile ONNX with C++17

* Force cpp17 - 2

* Use MSVC check

* Relax python reqs, enable 311 in azure

* Fix setupvars error

* Ignore watchdog error

* Update tensorflow

* Minor change

* Bump onnx to 1.13.1

* Bump protobuf to 3.20.3

* Debug test tf

* Xfail tests in comp

* Update comp tests

* Update tf reqs

* Remove deprecated ONNX function

* Align PDPD FE protobuf req with 2.4.1

* Satisfy dependency review

* Attempt to fix dependency review

* Revert pdpd protobuf

* Skip pdpd tests

* Fix MO-TF-PB test

* Skip TF test case

* Enable py311 on rest of jobs

* Try disabling pdpd req

* Exclude pdpd form cmake

* Update .ci/azure/linux.yml

Fixed unmerged merge-conflict

* CR

* Fix reqs

* Skip pdpd tests

* Disable pdpd tests building in cmake

* Skip another pdpd cmake

* Add file

* Add paddle constraint to tests

* Disable paddle reqs

* Debug prints

* Skip TF test if Python ver is 3.11

* Apply Mish cr comments

* Debug

* Debug

* Constrain tensorflow_addons

* Fix pdpd skipping

* Add debug prints

* Update skips

* Remove prints

* Minor change

* Update OMZ commit

* Fix some tests

* Minor change

* Disable pdpd at all

* Disable pdpd at all

---------

Co-authored-by: Ilya Lavrenov <ilya.lavrenov@intel.com>
2023-04-17 13:30:17 +04:00
Maxim Vafin 25015f9790 [PT FE] Support prim::DictConstruct on the output (#16894)
* Support dict on the output

* Preserve output order
2023-04-13 16:42:17 +00:00
Mateusz Tabaka 5d80bca16e [TF frontend] Add test for Split->Conv->Concat scenario (#16816) 2023-04-13 10:42:17 +02:00
Mateusz Bencer e737e18b02 [ONNX FE] Fix Squeeze v1 (#16865) 2023-04-12 14:33:49 +02:00
Przemyslaw Wysocki 69d6ef33fc [PyOV] Align and bump numpy, further tidy up requirements (#16652)
* Align numpy

* Simplify the rest

* Minor change

* Minor change

* Restart CI

* Update paddle reqs
2023-04-12 13:14:38 +04:00
Bo Liu 4bb9222c6e fix Paddle unit tests unexpected exceptions and seg fault issue (#16808)
* fix Paddle unit tests unexpected exceptions and seg fault issue

* parse confine from reqfile to keep algin with other requirements

* Apply suggestions from code review

* Apply suggestions from code review
2023-04-12 11:13:25 +04:00
Ivan Tikhonov 920900fbda Delete the redundant check in convert method of TF FrontEnd class (#16846)
* remove a check in convert method

* delete unused variables and comment

* leave only one pass::Manager in normalize method
2023-04-12 01:05:16 +04:00
Roman Kazantsev 9e89b6c5f6 [TF FE] Support NonMaxSuppression with named outputs (#16835)
* [TF FE] Support NonMaxSuppression with named outputs

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

* Simplify the test for NMS named outputs

* Share a script for test model generation

---------

Signed-off-by: Kazantsev, Roman <roman.kazantsev@intel.com>
2023-04-11 19:14:59 +02:00
Ekaterina Aidova ca2265395d [PT FE]: fix aten::mean behaviour for provided dtype (#16790) 2023-04-11 14:29:29 +04:00
Ekaterina Aidova d41663694c [PT FE]: aten::gather (#16784)
* [PT FE]: aten::gather

* add detach and sign
2023-04-11 14:28:05 +04:00
Ekaterina Aidova d407bc1b3b [PT FE] fix invalid reshape shape after aten::index (#16821)
* [PT FE] fix invalid reshape shape after aten::index

* support aten::index_select
2023-04-11 12:41:59 +03:00
Roman Kazantsev f991f92f8c [TF FE] Test ResourceGather operation and fix debug caps (#16819)
* [TF FE] Test ResourceGather operation and fix debug caps

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

* Fix test generation script

---------

Signed-off-by: Kazantsev, Roman <roman.kazantsev@intel.com>
2023-04-11 11:33:32 +04:00
Ivan Tikhonov 72952bdc45 Disable ConstantFolding for ShapeOf subgraph in TS transformation (#16765)
* Disable ConstantFolding for ShapeOf expressions in TS transformation

* update ModelWithEmptyTensorListAndPushBack: add ShapeOf subgraph
2023-04-07 14:50:59 +04:00
Maxim VafinandSergey Lyalin 8b7e6878e8 [TF FE] Better support for named ports in tensorflow frontend (#16697)
* Fix in create_same_type_const_scalar; accurate updating type for parameter when inlining function call body

* Added Unique to the list of operations with named output ports (another MUSE fix)

* Draft: working version of extension with named ports in TF

* Merge fixes

* Refactor and productize POC

* Clean up

* Fix build

* Fix code style

* Fix lib so extension test

* Fix namespaces

* Remove usage of Any from CreatorFunction

* Fix build

* Fix arm build

* Apply review feedback

* Fix build after merge

* Apply suggestions from code review

---------

Co-authored-by: Sergey Lyalin <sergey.lyalin@intel.com>
2023-04-07 14:16:23 +04:00
Oleg Pipikin 1c564226f3 Deprecate util functions in public api (#16716)
* Deprecate util functions in public api

* Add deprecation suppression for usage inside openvino

* Fix clang-format

* Fix1
2023-04-06 06:32:04 +04:00
Vitaliy Urusovskij 7442a17240 Add Core property to switch from mmap to read in IR Frontend (#16600)
* Add Core property to switch from `mmap` to `read`
in IR FrontEnd

* Add tests on `ov::enable_mmap` property

* Add `enable_mmap` in C & Py APIs

* ClangFormat
2023-04-05 18:22:11 +04:00
Ekaterina Aidova 837f5a7d53 [PT FE]: fix aten::index inconsistent reshape (#16741)
* [PT FE]:  fix aten::index inconsistent reshape

* add index name, return false

* Update src/frontends/pytorch/src/transforms/aten_index_replacer.cpp
2023-04-05 10:44:25 +02:00