Commit Graph

13376 Commits

Author SHA1 Message Date
Sebastian Golebiewski
a530a53eee
Fixing links in notebooks (#21208) 2023-11-21 12:09:19 +01:00
Tingqian Li
61c5a80fa6
[CPU] General pattern & matcher & RoPE (with EliminateStridedSlice fixed) (#21196) 2023-11-21 10:56:56 +00:00
Vladimir Paramuzov
a6e4d8fc30
[GPU] Cleanup buffer optimization code (#21012) 2023-11-21 14:43:14 +04:00
Oleg Pipikin
6607e5b8c2
Refactor ngraph builders 7 (#21181)
* Refactor make_reduce builder

* Refactor make_comparison builder

* Refactor make_logical builder

* Refactor make_fully_connected

* Refactor make_lstm builder

* Refactor make_gru builder

* Refactor make_rnn builder

* refactor make_augru builder

* Refactor make_gather_nd builders

* Refactor make_dft builder

* Refactor make_rdft builder

* Fix code style

* Fix

---------

Co-authored-by: Ilya Lavrenov <ilya.lavrenov@intel.com>
2023-11-21 13:36:51 +04:00
Oleg Pipikin
165f574d8f
Refactor ngraph builders 2 (#21043)
* Deprecate makeBatchToSpace

* Deprecate makeSpaceToBatch

* Remove makeStridedSlice

* Remove and deprecate makeSlice

* Remove and deprecate makeMVN

* Fix
2023-11-21 13:03:39 +04:00
River Li
aaa08d013a
[Core]Remove macro CONFIG from core_impl (#21142)
* Remove macro CONFIG from core_impl

* Fix errors

* Solve AutoBatching_Test_DetectionOutput failure issue
2023-11-21 12:51:30 +04:00
Oleg Pipikin
a7edeb53d1
Refactor negative ProposalBehTest (#21190)
Co-authored-by: Ilya Lavrenov <ilya.lavrenov@intel.com>
2023-11-21 11:28:49 +04:00
Pawel Raasz
5d6d6a2cfe
[core]Optimize OV assert macors to reduce CPU plugin binary size (#21180)
* Optimize OV assertions to reduce bin-size of libs

* Migrate assertion leftovers in CPU plugin

* Add NotImplemented::create to support use with macro
OPENVINO_ASSERT_HELPER

* Remove CheckLocInfo struct

---------

Co-authored-by: Ilya Lavrenov <ilya.lavrenov@intel.com>
2023-11-21 07:16:30 +01:00
Wilson Seok
d2dcdf86ba
[GPU] Fix issues in dynamic loops newly created by TF FE support (#21060)
* implementation of loop for new tf fe

* fix loop dynamic shape func test case failure

* backedge memory validation for static shape

* update checking user of backedge_to_prim

* avoid opt out of loop body network reorder result

* fix for batch 2 case

* fix batch2 case for loop

* fix build error

* fix missing condition
2023-11-20 16:15:02 -08:00
Kelvin Choi
adbfc53374
[GPU] Add an unittest to check reorder with trucation mode after reshape node not to split (#20783) 2023-11-21 09:00:12 +09:00
Meet Patel
20af42cfd9
Add python bindings for PILLOW interpolation modes (#21188) 2023-11-20 22:39:05 +00:00
Maxim Vafin
570817998d
Update reverse infer to allow changing shape if it already partially defined (#21073)
* Update reverse infer to allow changing shape if it already partially defined

* Update tests

* Remove changes in If

---------

Co-authored-by: Roman Kazantsev <roman.kazantsev@intel.com>
2023-11-20 21:57:43 +00:00
Ilya Lavrenov
0f33a77a27
Fixed compilation after merging 2 conflicting PRs (#21192) 2023-11-20 21:21:54 +04:00
Ilya Lavrenov
21a90f4e78
Smart CI: specializations for preprocessing and LPT (#21186)
* Smart CI: specializations for preprocessing and LPT

* Added PROXY component
2023-11-20 19:08:45 +04:00
Anastasia Kuporosova
56301d8878
[PyOV] add param-result to offline transformation (#21140) 2023-11-20 15:59:02 +01:00
Jan Iwaszkiewicz
0c041d7ebc
[PyOV] Adjust opset13 Constant to utilize runtime.op.Constant functionalities (#21046) 2023-11-20 15:29:46 +01:00
Alina Kladieva
23462aea6b
[GHA] Fix validation of dependent components in Smart CI config (#21187)
Use new syntax
2023-11-20 15:08:24 +01:00
Vitaliy Urusovskij
b700040e29
Remove legacy API from ov_cpu_unit_tests (#21184)
* Remove `InferenceEngine` usage

* Remove use of `ie_ngraph_utils.hpp`

* Rename `ng_transormations` to `transformations`

* Remove `ngraph` usage

* Misprint
2023-11-20 17:49:56 +04:00
Liu
d9e04c3b9e
[ONNX] Extend ONNX Frontend with Function LessOrEqual (#21102)
* Implement less_or_equal in set_1 and set_16

* Create tests for ONNX frontend less_or_equal operator
2023-11-20 17:16:03 +04:00
Ilya Lavrenov
a5e33f10ff
Revert "[CPU] Add general pattern serialization & matcher & RoPE (#20729)" (#21182)
This reverts commit a61a9be495.
2023-11-20 16:37:15 +04:00
Ilya Lavrenov
2ee8b29f64
Smart CI: CPU triggers tests for PT and TF FEs (#21183) 2023-11-20 15:35:40 +04:00
Tomasz Jankowski
ffa6e8458d
[core] Migrate ShapeOf operator to new API (#21143)
* Drop legacy stuff

* Drop HostTensor

* Remove unused element types support

* Revert "Remove unused element types support"

This reverts commit 2ca8280c56.

* Improve style
2023-11-20 15:06:30 +04:00
Pawel Raasz
af27b6f16a
Add checking compatible types for Gathers GroupedGatherElimination (#20979)
* Check Gathers 2nd input type to avoid Concat exception
in GroupedGatherElimination transformation

* Add indices conversion if possible
2023-11-20 14:59:37 +04:00
Evgeny Kotov
ecd1972c24
don't fold ShapeOf in TransposeSinking (#20742)
* add to DisableShapeOfConstantFolding flag; set it in ts_gather; add unit test

* fix ts_general; use check_shape flag in EnableShapeOfConstantFolding

* set EnableShapeOfConstantFolding constructor explicit

---------

Co-authored-by: Ivan Tikhonov <ivan.tikhonov@intel.com>
2023-11-20 14:57:19 +04:00
Alina Kladieva
7931938ea4
[GHA] Alternative way to handle required pipeline checks (#21164) 2023-11-20 11:14:58 +01:00
Roman Kazantsev
bb773137f1
[TF Hub] Move all nightly scope to Kaggle links (#21169)
7 models are skipped since they are not moved there. Now they are not available.

Signed-off-by: Kazantsev, Roman <roman.kazantsev@intel.com>
2023-11-20 13:33:21 +04:00
Przemyslaw Wysocki
dddc85f68f
Add lower bound to sympy (#21127) 2023-11-20 10:17:47 +01:00
Przemyslaw Wysocki
bd5bd56d29
Remove failing mxnet test (#21151) 2023-11-20 10:17:22 +01:00
Zlobin Vladimir
e965bea8fe
benchmark_app: allow dla_benchmark for FPGA to override show_available_devices() for --help (#20945)
It's possible now to have in main.py:
parser = parse_args()
import argparse, openvino
core = openvino.Core()
class print_help(argparse.Action):
    def __call__(self, parser, namespace, values, option_string):
        parser.print_help()
        print("\nAvailable target devices:  ", ("  ".join(core.available_devices)))
        sys.exit()
parser.add_argument('-h', '--help', action=print_help, nargs='?', default=argparse.SUPPRESS, help='Show this help message and exit.')
args = parser.parse_args()

The details are in https://github.com/openvinotoolkit/openvino/pull/20098
2023-11-20 13:00:37 +04:00
Roman Kazantsev
ab3452ce59
[TF FE] Speed up compilation - part 2 (#21170)
Avoid use of heavy header

Signed-off-by: Kazantsev, Roman <roman.kazantsev@intel.com>
2023-11-20 12:51:35 +04:00
Alina Kladieva
f7f8636fe4
[GHA] Workaround for some non-repo components in Smart CI (#21134)
* Workaround for some non-repo components in Smart CI

* Add possibility to add all components as dependent

* Remove extra check

* Add test case for "all" key
2023-11-20 12:44:50 +04:00
Pawel Raasz
43bb86d384
[core]Migrate Power operator to new API (#21150)
* Migrate Power operator to new API

* Refactor ref implementation to reduce bin size
2023-11-20 08:48:38 +01:00
Maksim Kutakov
5203d3483b
[CPU] Dynamic shapes support for memory states with zero copy (#20368) 2023-11-20 09:58:38 +04:00
Tingqian Li
a61a9be495
[CPU] Add general pattern serialization & matcher & RoPE (#20729) 2023-11-20 09:50:50 +04:00
Min, Byungil
081f5aad8a
[GPU] Fix perf regression from dynamic tensor iterator (#21065)
+ Not to use reference::split. It is very slow.

Signed-off-by: Min, Byungil <byungil.min@intel.com>
2023-11-20 10:03:39 +09:00
Min, Byungil
8181f30a67
[GPU] Fix accuracy issue of blocked format batching on iGPU (#20890)
* [GPU] Fix accuracy issue for blocked format batching on iGPU

+ Bugfix GET_INDEX for batching of b_fs_zyx_fsv16 of target model
+ Updated fetch_data.cl
+ Minor fix of error message

Signed-off-by: Min, Byungil <byungil.min@intel.com>
2023-11-20 09:46:37 +09:00
Maxim Vafin
276153d1ce
[PT FE] Support aten::_weight_norm and aten::full with scalar size (#21160)
* Support aten::_weight_norm and aten::full with scalar size

* Add op_table changes

* Add comments
2023-11-17 19:13:15 +00:00
Sebastian Golebiewski
44d56b9dc7
[DOCS] New page design for notebooks (#20996)
New design and new directive for notebooks
2023-11-17 16:34:34 +01:00
Oleg Pipikin
a9dffa8d70
Refactor ngraph builders (#20998)
* Remove makeInputLayer builders

* Refactor makeBroadcast builder

* Deprecated makeCTC builders

* Fix for broadcast builder

* Remove and deprecate makeSplit builder

* fix

* Fix
2023-11-17 16:10:19 +01:00
Maxim Vafin
b2e14f9fad
[PT FE] Fix pad value dtype for pooling (#21139)
* [PT FE] Fix pad value dtype for pooling

* Apply suggestions from code review

* Apply suggestions from code review
2023-11-17 16:09:56 +01:00
Oleg Pipikin
71af0eef38
Refactor ngraph builders 4 (#21100)
* Remove and deprecate some ngraph builders
2023-11-17 14:51:56 +00:00
Andrzej Kopytko
d29207e201
[DOCS] update benchmark files 2023-11-17 14:02:43 +01:00
Karol Blaszczak
fa0a6ab9d1
[DOCS] fix npu mention (#21147) 2023-11-17 13:50:05 +01:00
Tatiana Savina
c01fdc9276
[DOCS] Port release docs to master (#21154)
* update links (#21118)

* change install (#21117)

* deprecate deployment manager (#21089)
2023-11-17 13:47:00 +01:00
Georgy Krivoruchko
c71ee333f8
[TFLite] Extended verification of supported files (#21006)
* [TFLite] Fix for crash in case of zero-length file

* Extended verification using FourCC check in the header

* Fix for Linux build

* Fixes for Linux

* Some platforms may miss SizePrefixed... method

* Fixed path preparation
2023-11-17 15:03:31 +04:00
Roman Kazantsev
b380eb06ee
[TF FE] Speed up compilation - part 1 (#21144)
Signed-off-by: Kazantsev, Roman <roman.kazantsev@intel.com>
2023-11-17 10:26:28 +00:00
Luo Cheng
e4311aae46
[CPU] Fix ScaledDotProductAttention build failure on ubuntu18 (#21123) 2023-11-17 10:14:01 +00:00
Maxim Vafin
6bdc1597ed
[PT FE] Align types for aten::clamp_max and aten::clamp_min (#21137)
* Align types for aten::clamp_max and aten::clamp_min

* Add tests
2023-11-17 10:26:44 +01:00
Paul Youngsoo Ahn
8b5b7a627b
[GPU] Fix loop issues (#21091)
* [GPU] Fix loop issues
* if loop does not run inner body, return zero dimension layout for dynamic dimension layout

* Support dynamic sliced input in inner body in creaet concate mapping

* Modify update_shape to call reset_shape_changed() when inputs of loop are not changed
* Add unit test

* Follow-up codereview
2023-11-17 00:16:58 -08:00
Aleksandr Voron
60730f61a4
[CPU][ARM] Call to_string() method of ov::element::Type in ACL Convert executor (#21136) 2023-11-17 07:02:13 +00:00