Commit Graph

13376 Commits

Author SHA1 Message Date
Pawel Raasz
5ef7c02bdf
Remove unused function from build (#21057)
if Paddle FE is disabled to avoid build failures `-Werror=unused-function`
2023-11-14 11:27:09 +01:00
Pawel Raasz
c974c9a478
Remove limit for Loop inputs in bindings (#21055) 2023-11-14 11:18:40 +01:00
Vladislav Golubev
b43b9f9d50
[CPU] Weights decompression support for hybrid models (#20973) 2023-11-14 13:27:42 +04:00
Zhang Yi
7cb3bf5610
[CPU] Enable bf16 acdb layout for transpose (#21030) 2023-11-14 10:24:54 +04:00
Piotr Krzemiński
bb3ed2d42e
[SPEC] Apply changes from release branch (#20986) 2023-11-14 06:56:06 +01:00
River Li
89494ab412
[CPU] CPU plugin API 2.0 migration for ngraph namespace (#21013)
* [CPU] cleanup misc IE and ngraph

1. InferenceEngine::SizeVector
2. InferenceEngine::parallel_for
3. All ngraph namespace except ngraph::op

* [CPU] clean ngraph opset namespace and header files

* Remove unused header files

1. ngraph/ngraph.hpp
2. ngraph/ops.hpp
3. blob_factory.hpp
3. using namespace ngraph

* Cleanup ie_parallel

* Fix compile error
2023-11-14 00:37:27 +04:00
Alina Kladieva
f0c0bf89e2
Smart CI for docs (#21021)
* Handle Smart CI for docs

* Remove path filters

* Fix quotes

* Fix logic

* Revert unneeded change

* Add md_files_only to components configuration

* Get rid of custom output

* Try to fix condition

* Add manual handling of some docs changes

* Remove helper label
2023-11-14 00:00:51 +04:00
Maksim Kutakov
75acdac5f9
Extend the existing IO binding subgraph tests (#20987) 2023-11-13 15:22:41 +01:00
dependabot[bot]
8b7537a30d
Update networkx requirement from <=3.1 to <=3.2.1 in /tools/pot (#20751)
Updates the requirements on [networkx](https://github.com/networkx/networkx) to permit the latest version.
- [Release notes](https://github.com/networkx/networkx/releases)
- [Commits](https://github.com/networkx/networkx/compare/networkx-0.23...networkx-3.2.1)

---
updated-dependencies:
- dependency-name: networkx
  dependency-type: direct:production
...

Signed-off-by: dependabot[bot] <support@github.com>
Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com>
2023-11-13 17:44:08 +04:00
dependabot[bot]
03a1ba1f81
Bump pytest-html from 3.2.0 to 4.1.1 in /src/bindings/python (#20948)
Bumps [pytest-html](https://github.com/pytest-dev/pytest-html) from 3.2.0 to 4.1.1.
- [Release notes](https://github.com/pytest-dev/pytest-html/releases)
- [Changelog](https://github.com/pytest-dev/pytest-html/blob/master/docs/changelog.rst)
- [Commits](https://github.com/pytest-dev/pytest-html/compare/v3.2.0...4.1.1)

---
updated-dependencies:
- dependency-name: pytest-html
  dependency-type: direct:production
  update-type: version-update:semver-major
...

Signed-off-by: dependabot[bot] <support@github.com>
Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com>
2023-11-13 17:43:45 +04:00
dependabot[bot]
fd403e552a
Bump pytest-html from 3.2.0 to 4.1.1 in /tests (#20949)
Bumps [pytest-html](https://github.com/pytest-dev/pytest-html) from 3.2.0 to 4.1.1.
- [Release notes](https://github.com/pytest-dev/pytest-html/releases)
- [Changelog](https://github.com/pytest-dev/pytest-html/blob/master/docs/changelog.rst)
- [Commits](https://github.com/pytest-dev/pytest-html/compare/v3.2.0...4.1.1)

---
updated-dependencies:
- dependency-name: pytest-html
  dependency-type: direct:production
  update-type: version-update:semver-major
...

Signed-off-by: dependabot[bot] <support@github.com>
Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com>
2023-11-13 17:43:35 +04:00
Roman Kazantsev
75c72157dd
[TF Hub] Add yamnet with complex tensors into precommit (#21035)
After fixing ov.Tensor creation for empty numpy array, we are ready to support yamnet

Signed-off-by: Kazantsev, Roman <roman.kazantsev@intel.com>
2023-11-13 17:42:13 +04:00
Xuejun Zhai
4563f71ffc
[Func Test] remove ngraph::helpers::QuantizationGranularity, replaced with ov::test::utils::QuantizationGranularity (#20985)
Signed-off-by: Zhai, Xuejun <xuejun.zhai@intel.com>
Co-authored-by: Chen Peter <peter.chen@intel.com>
2023-11-13 13:29:36 +00:00
River Li
5dd317c733
[CPU] cleanup misc IE and ngraph (#21007)
1. InferenceEngine::SizeVector
2. InferenceEngine::parallel_for
3. All ngraph namespace except ngraph::op
2023-11-13 17:06:59 +04:00
Zlobin Vladimir
f97e7f1c9d
setupvars.sh: ignore cd output (#20657)
* `setupvars.sh`: ignore `cd` output

Having `function cd() { builtin cd "$@" && l; }` defined in bash breaks `setupvars.sh`

* Use `builtin cd` to enable `function cd() { builtin cd "$@" && l; }`, remove wrapping `echo $()` because `pwd` already prints
2023-11-13 16:15:30 +04:00
Zlobin Vladimir
0125c89738
Fix --mean_values and --scale_values prohibition to align with C++ (#20910) 2023-11-13 16:15:02 +04:00
hyunback kim
03e48f3c17
[GPU] Fix LCM notebook failure issue for int8 model. (#20944)
Fix to use partial_shape in dynamic case. Not get_dims().

Signed-off-by: hyunback <hyunback.kim@intel.com>
2023-11-13 20:39:02 +09:00
Maciej Smyk
5a04359200
[DOCS] Updating links for master 2023-11-13 12:23:23 +01:00
Zlobin Vladimir
e79e5122f8
benchmark_app: is_file->is_file() (#21016)
Close https://github.com/openvinotoolkit/openvino/issues/21000

Co-authored-by: Andrei Kochin <andrei.kochin@intel.com>
2023-11-13 11:04:14 +00:00
Tomasz Jankowski
70a2736695
[core] Migrate Log operator to new API (#20917)
* Drop ngraph remains

* Use ov::Tensor

instaed of ngraph::HostTensor

* Remove useless code
2023-11-13 11:00:09 +00:00
Roman Kazantsev
7c595f8773
[TF FE] Refactor ops translators to check complex type and speed-up compilation (#21025)
* [TF FE] Refactor AddN translator

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

* Refactor ArgMin/ArgMax

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

* Add default check for binary operations

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

* Refactor Cast translator

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

* Refactor Const translator

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

* Refactor Einsum, Elu, and Fill operations

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

* Refactor MatMul translator

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

* Refactor Relu6 and Placeholder

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

* Refactor Round, Square, and unary operation translators

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

* Update src/frontends/tensorflow_common/src/op/relu_6.cpp

* Update src/frontends/tensorflow_common/src/op/const.cpp

---------

Signed-off-by: Kazantsev, Roman <roman.kazantsev@intel.com>
2023-11-13 14:29:18 +04:00
Jan Iwaszkiewicz
6650b8750a
[PyOV] Support Tensor creation from empty numpy arrays (#20964) 2023-11-13 11:25:58 +01:00
Maksim Kutakov
fb3751717f
[Inference] Return state ptr by value (#21011)
* Return state ptr by value

* Fix mock class
2023-11-13 14:24:54 +04:00
Jan Iwaszkiewicz
212a9bc852
[PyOV] Support Constant creation from empty numpy arrays (#20967)
* [PyOV] Support Constant creation from empty numpy arrays

* Return 0 when shape is 0

* Add missing file...
2023-11-13 10:11:12 +00:00
Anastasiia Pnevskaia
5fa53aa715
Input and output order Keras tests. (#20902)
* Input/output order Keras tests.

* Added precommit mark.

* Added xfail.

* Small correction.

* Check input/outputs by names in FW.

* Moved output order tests to Python API group.

* Corrected comments.
2023-11-13 14:01:35 +04:00
Vitaliy Urusovskij
1a5b0b70f9
Remove castOps2Nodes and convert2OutputVector (#21015) 2023-11-13 13:29:53 +04:00
Pawel Raasz
c451a94572
Fix compile warning regarding ABI changes (#20990)
and using std::true_type/false_type
2023-11-13 07:44:54 +01:00
River Li
fef0df6ee1
[CPU] Add deprecation message to extension API (#20970) 2023-11-13 10:37:35 +04:00
Sergey Shlyapnikov
306137f86b
[GPU] Make ShapePredictor instance unique for each InferRequest instead of the cldnn::network (#21019) 2023-11-13 08:52:07 +04:00
Paul Youngsoo Ahn
51da30b48d
Support LSTMSequence with -1 sequence length (#20935)
* [GPU] Support LSTMSequence w/ -1 seq_length

Co-authored-by:Taylor Yeonbok Lee <taylor.lee@intel.com>
Co-authored-by:Andrew Park <andrew.park@intel.com>

* Fix GetInputInfo to retrieve input pid from LSTMCell

* LSTMCell use ov::PartialShape instead of cldnn::tensor
* implement lstm_elt_inst::calc_output_layouts
* implement lstm_elt_impl::static_canonicalize_shapes

* Add functional tests

* Fix unit test failure

---------

Co-authored-by: Andrew Park <andrew.park@intel.com>
2023-11-11 00:06:08 -08:00
Maxim Vafin
c08e01d6d7
[PT FE] Optimize reverseprop in pytorch frontend (#20989)
* [PT FE] Optimize reverseprop in pytorch frontend

* Add transformation

* Improve readability

---------

Co-authored-by: Alina Kladieva <alina.kladieva@intel.com>
2023-11-10 18:00:04 +01:00
Tatiana Savina
e446dac727
[DOCS] Add content to about ov page (#21010)
* add about ov info

* fix format

* fill ov page
2023-11-10 16:28:09 +01:00
Roman Kazantsev
b64d6be8ba
[TF FE] Fix TF1 OD SSD PPN model conversion (#20994)
* [TF FE] Fix TF1 SSD PPN model conversion

It contains a case when one Merge node eliminated different conditional flows.

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

* Add layer test

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

---------

Signed-off-by: Kazantsev, Roman <roman.kazantsev@intel.com>
2023-11-10 11:44:28 +00:00
Alina Kladieva
e8d28f7f6d
Make conformance wait for Smart CI step (#21014) 2023-11-10 12:10:36 +01:00
Pawel Raasz
641d3ab351
Migrate Constant operator to new API (#20760)
* Migrate Constant operator to new API
- refactor to reduce binary size

* Fix code style

* Fix build issues

* Apply corrections after review:
- Restore mem_size calculation for bit widths >= 8
- Remove element type helpers functions

* Use float cast for floating types except f64
2023-11-10 12:49:08 +04:00
Irina Efode
ebf1874eee
[GHA] Check OpImplCheck conformance for template plugin (to make sure that all functions are checked by conformance) (#20712)
* [CONFROMANCE] Fix Template OpImplCheck on Win

* Update windows.yml

* check win

* Update windows.yml

* remove extra changes
2023-11-10 12:39:58 +04:00
Ilya Lavrenov
d4dd169ca3
Added more smart CI conditions (#20999) 2023-11-09 23:40:26 +04:00
Alina Kladieva
51a17ba642
Workaround failing MO unit when Python API unit are skipped (#20997) 2023-11-09 18:07:57 +01:00
Tatiana Savina
8034d1795f
change structure (#20988) 2023-11-09 15:03:01 +01:00
Sungeun Kim
b1705e8bd3
[GPU] clean up for extend pad/stride/dilation (#20828)
* clean up for extend pad/stride/dilation
2023-11-09 20:48:34 +09:00
Sungeun Kim
9cc4c25e48
[GPU] print datashape of input for benchmark_app (#20943)
* print datashape of input for benchmark_app
2023-11-09 20:46:50 +09:00
Zhang Yi
09a45bceae
[CPU][MLAS]Apply lower bound protection for K stride (#20873) 2023-11-09 15:14:27 +04:00
Aleksandr Voron
3c88a9cf58
[CPU] [ARM] Enable MatMul SLT tests on ARM (#20923) 2023-11-09 15:12:22 +04:00
Alina Kladieva
fa22836cfb
Fix no match files change case (#20981) 2023-11-09 12:07:47 +01:00
Ilya Lavrenov
c851d643b3
Fixed smart CI (#20980) 2023-11-09 11:28:32 +01:00
Pawel Raasz
d6852598ce
Fix Ubuntu20 build error on relu operator (#20965) 2023-11-09 07:42:06 +00:00
Alina Kladieva
000966660c
Smart CI POC (#19825)
* Try using a custom action directly from repo

* Run smart CI under ubuntu-latest

* Set output + add a sample step

* Update linux.yml

* Add components.yml

* Add some conditions

* Just to check if reference to "needs" work in job context

* Update linux.yml

* More example cases

* Dummy change to CPU

* Fix typo

* Fix SAMPLES_AFFECTED variable

* Use more correct dependents key

* Fighting with messy GHA conditions

* No brackets and no double quotes in conditions

* Revert "Dummy change to CPU"

This reverts commit 4eae09e5b5.

* Use refactored action

* Move action implementation to openvino repo

* Extend components.yml config

* Update labeler.yml

* Dummy change to TF FE

* Fix indentation

* Add missing needs

* Add missing records

* Allow missing records for components in validation

* install_openvino_dependencies as a separate step for Python_Unit_Tests

* Improve config validation

* Revert "Dummy change to TF FE"

This reverts commit 01190864d1.

* Dummy change to model hub tests

* Update CPU component config

* Dummy change to Python API

* Dummy change to Python API

* Revert "Dummy change to Python API"

This reverts commit 3fce0bb3fb.

* Dummy change to Python API

* Simplify conditions. Cover "no components changed" case

* Update components.yml

* Update .gitignore

* Revert "Dummy change to Python API"

This reverts commit e57ea9852c.

* Fix dependencies scopes

* Add simple unit tests for smart ci functionality

* Revert "Dummy change to model hub tests"

This reverts commit c3d6837e22.

* Use ghapi module with permissive license

* Cover install_build_dependencies.sh script by labeler

* More labels

* Use ghapi. Apply review comments

* Enable dot files to be matched by labeler

* Warning instead of error in artifacts upload where smart ci is enabled

* Fix master merge

* Fix condition for TF FE common tests

* Fix condition for Pytorch FE tests

* Remove condition for pytorch model tests

* Allow any label as a component

* Refactor tests log handling

* Allow any defined label as a component

* Rearrange config structure. Fill the config with actual data

* Run full scope on changes to non-matching files

* Add missing conditions

---------

Co-authored-by: Ilya Lavrenov <ilya.lavrenov@intel.com>
2023-11-09 11:38:58 +04:00
Tomasz Jankowski
6e073b1165
[core] Migrate SoftSign operator to new API (#20958)
* Align code style

* Use Evaluate in place of switch case

* Use std::transform in place of for loop
2023-11-09 11:10:37 +04:00
Oleg Pipikin
4bde741de4
Refactor StaticShapeLoopLayerTest (#20963) 2023-11-09 11:08:18 +04:00
Vitaliy Urusovskij
bcb38796ce
Ngraph helpers/builders cleaning (#20819)
* Delete `getNodeSharedPtr()`

* Remove `makeRoll` ng::builder

* Delete `makeSelect` ng::builder

* Delete `makeDepthToSpace` ng::builder

* Remove `CompareFunctions` and `getConstData` from ng::helpers

* Return `makeSelect` for compatibility with NPU

* Port `QuantizationGranularity`, `MemoryTransformation`

* Restore ng::helpers::QuantGranularity for BWD CMP
2023-11-09 10:51:00 +04:00