Commit Graph

742 Commits

Author SHA1 Message Date
Ekaterina Aidova
82ff7e17c9 use input parameter for building example_inputs (#17207)
* use input parameter for building example_inputs

* Update tools/mo/openvino/tools/mo/moc_frontend/pytorch_frontend_utils.py
2023-04-26 17:58:06 +04:00
Zlobin Vladimir
de30d8523d State single value is uese (#15458)
Ticket EISW-60868
2023-04-26 14:50:03 +04:00
Maciej Smyk
72533a7da1 DOCS shift to rst - Quantizing Models with Accuracy Control, Documentation, Get Started & Learn OpenVINO (#16997)
* Update AccuracyAwareQuantizationUsage.md

* Update AccuracyAwareQuantizationUsage.md

* Update AccuracyAwareQuantizationUsage.md

* Update AccuracyAwareQuantizationUsage.md

* Update AccuracyAwareQuantizationUsage.md

* Update AccuracyAwareQuantizationUsage.md

* Update AccuracyAwareQuantizationUsage.md

* Update AccuracyAwareQuantizationUsage.md

* Update AccuracyAwareQuantizationUsage.md

* Update AccuracyAwareQuantizationUsage.md

* Update AccuracyAwareQuantizationUsage.md

* rst

* fixes
2023-04-25 16:06:34 +02:00
Anastasiia Pnevskaia
acd424bb5e Show message with suggestion to try legacy FE in case of conversion error (#17088)
* Moved exception checks to _convert(), added suggestion to try legacy TF in case of conversion fail.

* Added test.

* Added send_conversion_result() method.

* Small correction.

* Update tools/mo/openvino/tools/mo/convert_impl.py

Co-authored-by: Roman Kazantsev <roman.kazantsev@intel.com>

* Moved test_suggest_legacy_fe() test to check_info_messages_test.py.

* Removed not needed import.

* Small correction.

---------

Co-authored-by: Roman Kazantsev <roman.kazantsev@intel.com>
2023-04-25 13:57:01 +00:00
Przemyslaw Wysocki
923b6f297c [PyOV] Move environment markers to requirements.txt files (#17113)
* WIP

* WIP

* Debug

* WIP

* Expand function to other setup.pies

* Revert mxnet

* Update docstring'

* restore defusedxml

* Update tools/mo/requirements.txt

Co-authored-by: Roman Kazantsev <roman.kazantsev@intel.com>

* Code review

---------

Co-authored-by: Roman Kazantsev <roman.kazantsev@intel.com>
2023-04-25 13:25:21 +00:00
Maxim Vafin
d423491bcb Fix Scatter value infer for fully dynamic value (#17165)
* Fix issue with dynamic Scatter in MO IR Reader

* Only normalize for 1D tensors

* Add test
2023-04-25 16:38:49 +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
Nikita Malinin
e37288fbcc [POT] Added inference shape for in-place statistics (#17114)
* Added inference shape for inplace statistics

* Update graph_builder
2023-04-25 11:14:34 +04:00
Anastasiia Pnevskaia
00847cba7d Fix of tf.GenericFunction conversion in convert_model() (#17125)
* Added GenericFunction support, fixed tf.Function test.

* Added test, added TF version checks.

* Small correction

* Removed Trackable type support.

* Small correction.
2023-04-24 22:57:56 +00:00
Roman Kazantsev
3830125e3b [TF FE] Report the full list of unsupported operations (#17143) 2023-04-24 21:33:07 +00:00
Ilya Lavrenov
a34ef680f2 Made plugins.hpp generation to be CONFIG dependent (#17139) 2023-04-24 14:48:45 +04:00
dependabot[bot]
eac265722f Update networkx requirement from <=2.8.8 to <=3.1 in /tools/pot (#16745)
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-3.1)

---
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>
2023-04-24 13:37:35 +04:00
Maxim Vafin
01065338ef Fix MO IR Reader extender for StridedSlice to support empty begin and end masks (#17019) 2023-04-24 13:08:28 +04:00
Daniil Lyakhov
7997354359 POT is depricated (#16758) 2023-04-24 09:37:57 +04:00
Anastasiia Pnevskaia
50a6c88ea3 Fix of crashes of convert_model() when executed for different frameworks (#16968)
* Fix of class conflicts in different frameworks.

* Remove commented code.

* Moved FakeQuantWithMinMaxVars to common part.

* Fixed BOM package test.

* Removed not needed code.

* Removed not needed code.
2023-04-21 19:29:38 +04:00
Maxim Vafin
552143c9cd [MO] Fix Interpolate-11 in MO (#17002)
* Fix Interpolate-11 in MO

* Add forgotten file

* Fix output type of TopK-11

* Do not force precision on port 1 for mode scales

* Update tools/mo/openvino/tools/mo/ops/interpolate.py

---------

Co-authored-by: Ilya Lavrenov <ilya.lavrenov@intel.com>
Co-authored-by: Andrei Kochin <andrei.kochin@intel.com>
Co-authored-by: Roman Kazantsev <roman.kazantsev@intel.com>
2023-04-20 09:51:38 +02:00
Anastasiia Pnevskaia
5026aa044a Removed naming of inputs in MO Python API PyTorch tests. (#17070)
* Removed naming of inputs in MO Python API PyTorch tests.

* Fixed coping of data.

* Small correction.

* Small correction.

* Small fix.
2023-04-20 11:49:45 +04:00
Anastasia Kuporosova
9f250edc7f [PyOV] use generator is multi config (#17004)
* [PyOV]- use generator is multi config

* use ov

---------

Co-authored-by: Ilya Lavrenov <ilya.lavrenov@intel.com>
2023-04-18 22:04:22 +00:00
Anastasiia Pnevskaia
078f28911b Fixed parsing of 'layout' param (#16999)
* Fixed layout parsing.

* Small correction.

* Removed wrong change.
2023-04-18 22:43:38 +04:00
Karol Blaszczak
1471a6e8de [DOCS] benchmarks new page (#16620) 2023-04-17 16:43:57 +02:00
Anastasiia Pnevskaia
dc2fa65224 Support of unnamed saved_model_dir in MO Python API (#16542)
* Added support of unnamed saved_model_dir.

* Switch TF2 layer tests for unnamed saved_model_dir.

* Added test.

* Correction of comment.

* Removed unnecessary pytest mark.

* Code correction, added comment.
2023-04-17 17:20:27 +04:00
Przemyslaw Wysocki
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
Roman Kazantsev
18da874c57 [MO] Remove use of mapping file and its generation (#16944)
* [MO] Remove use of mapping file and its generation

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

* Fix pylinter findings

* Remove usage of mapping file in the layer tests

* Fixing layer tests for legacy frontend

---------

Signed-off-by: Kazantsev, Roman <roman.kazantsev@intel.com>
2023-04-15 10:38:33 +00:00
Roman Kazantsev
4ba0ac5476 [MO][TF FE] Support delayed batch setting (#16937)
* [TF FE] Support delayed batch setting

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

* Cover BOM list

* Add unit-tests for batch setting with layout

* Apply code-review: check batch size

* Apply code-review: default index for any dimension

---------

Signed-off-by: Kazantsev, Roman <roman.kazantsev@intel.com>
2023-04-14 22:35:43 +00:00
Liubov Talamanova
0c0aa5c997 [POT] Fix POT CI (#16955) 2023-04-14 17:21:01 +00:00
Anastasiia Pnevskaia
24c9d95779 Support of unnamed input for MO Python API. (#16373)
* Support of unnamed input for MO Python API.

* Code correction, tests fix.

* Small fix.

* Added tests for unnamed input, code fixes.

* Small code correction.

* Removed code comment.

* Added tests, fixed bugs.

* Minor corrections, added comments.

* Code refactoring.

* Added defaults for InputCutInfo.

* Fixed error.

* Small fixes.

* Removed wrong change.

* Fixed error.

* Corrected input description.
2023-04-14 19:37:46 +04:00
Pavel Esir
68f46ff9a1 [MO] compress_to_fp16=False by default (#16854)
* compress_to_fp16=False by default

* Apply suggestions from code review

Co-authored-by: Karol Blaszczak <karol.blaszczak@intel.com>

* note abound RAM consumption for FP16 compressed models

* detailed notion about RAM usage

* update 'get_compression_message()'

* corrected get_compression_message: remove infor about RAM

* fix pytorch convert layer tests

---------

Co-authored-by: Karol Blaszczak <karol.blaszczak@intel.com>
2023-04-14 01:16:41 +00:00
Shen, Wanglei
3461064507 update benchmark_app to remove setting UNDEFINED with -hint none (#16695)
* Remove setting ov::hint::PerformanceMode::UNDEFINED from benchmark_app

* update benchmark_app

* update python code and description

* update python code

* fix code style issue

* update python code

* update c++ app
2023-04-13 14:29:13 +00:00
Maxim Vafin
c592ecd44e [MO] Fix legacy If (#16613)
* Fix legacy If

* Add test for If op

* Small fix
2023-04-13 18:10:40 +04:00
Anastasiia Pnevskaia
4921d1ad28 Fix for slowdown of convert_model() after multiple runs (#16751)
* Used singleton class for version check.

* Moved VersionChecker to utitl/version.py, added tests.

* Minor corrections.

* Sort imports.

* Small correction.

* Small correction.
2023-04-13 11:59:11 +04:00
Wang, Yang
86d7c97fa9 Update the logic of benchmark app property setting (#16427)
* 1. refine the logic to ov::device::properties setting.
2. the config overrides will be performed if same config setting is came from CMD line.-a

Signed-off-by: Wang, Yang <yang4.wang@intel.com>

* Update configuration sample file within README.md.

* Update.

* Update.

* 1. Update configuration example file within REAMDME.md for Python version.
2. implement the config DEVICE_PROPERTIES value convertation between the string type and dictionary of Python type.
3. Update the configuration file loading and dumping logic.

Signed-off-by: Wang, Yang <yang4.wang@intel.com>

* Update.

* Update.

* Update.

* Update.

* Update.

* 1. Enable configs to be interchangeable between C++ and Python.
2. Update perf_count showing logic.

Signed-off-by: Wang, Yang <yang4.wang@intel.com>

* Revert the logic of showing show performance counters.

* Update help msg for loading config option.

---------

Signed-off-by: Wang, Yang <yang4.wang@intel.com>
2023-04-12 15:32:54 +00:00
Mateusz Tabaka
bdd79fe931 CompressQuantizeWeights - use f32 precision when computing scale and zero point (#16794)
Ticket: 101825
2023-04-12 12:42:39 +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
Maxim Vafin
23c90aecea Add support for opset10 and opset11 in MO IR Reader (#16742)
* Add support for opset10 and opset11 in MO IR Reader

* Fix unique

* Refactor tests

* Fix Unique shape infer

* Update tests

* Apply suggestions from code review

Co-authored-by: Roman Kazantsev <roman.kazantsev@intel.com>

* Apply review feedback

* Fix BOM tests

* Update tools/mo/unit_tests/mo/utils/ir_reader/ops_test.py

* Improve error log

* Fix test fails when using pytest

* Add changes forgotten in last commit

* Fix error message

---------

Co-authored-by: Roman Kazantsev <roman.kazantsev@intel.com>
2023-04-12 11:35:52 +04:00
Przemyslaw Wysocki
ea213f687a Fix regex (#16850) 2023-04-12 01:06:54 +04:00
Wang, Yang
3740ba9226 [IE Sample] incorrect nstreams retrieved from plugin (#16849)
* Retrieve the ov::num_streams through compiledModel rather than through plugin.

* Update python version.
2023-04-12 01:06:20 +04:00
Ilya Lavrenov
feb08c408f Return benchmark_tool to openvino-dev wheel (#16834) 2023-04-10 16:34:51 +04:00
Anastasia Kuporosova
dbe051aa79 [POT] use serialize methid (#16768) 2023-04-06 15:02:24 +04:00
Anastasiia Pnevskaia
4098434233 Parameter list and descriptions for mo.convert_model() method in docstring (#16459)
* Added convert_model() params docs.

* Added auto-generating of most cli params.

* Added auto-generating of cli params.

* Small correction.

* Removed wrong change.

* Corrected default values.

* Fixed errors, added tests.

* Small correction.

* Corrected params descriptions, moved cli specific params to separate file.

* Moved params specifics to utils/help.py.
2023-04-05 14:48:13 +04:00
Maciej Smyk
8691ec2779 Update README.md (#16700) 2023-04-04 13:15:31 +02:00
Przemyslaw Wysocki
6237868437 Dependabot-ignore line (#16679) 2023-04-03 15:49:27 +04:00
Sebastian Golebiewski
b2e4857a64 DOCS shift to rst - AccuracyAwareQuantization Parameters (#16663) 2023-04-03 08:29:40 +02:00
Sebastian Golebiewski
02b35d7984 DOCS shift to rst - POT CLI Example (#16649) 2023-04-03 08:29:10 +02:00
Sebastian Golebiewski
3a5b819685 DOCS shift to rst - POT API examples (#16627) 2023-04-03 08:28:47 +02:00
Sebastian Golebiewski
2f5be5e81c DOCS shift to rst - Post-Training Optimization (#16621) 2023-04-03 08:28:24 +02:00
Sebastian Golebiewski
848c9e3b76 DOCS shift to rst (#16616) 2023-04-03 08:27:02 +02:00
Sebastian Golebiewski
f9ff518d16 DOCS shift to rst - Model Optimization Guide articles (#16598) 2023-03-31 11:26:04 +02:00
Pavel Esir
6d064d26cb remove deprecated MO args (#16626)
Co-authored-by: Andrei Kochin <andrei.kochin@intel.com>
Co-authored-by: Roman Kazantsev <roman.kazantsev@intel.com>
2023-03-31 12:28:04 +04:00
Sebastian Golebiewski
8fad140a02 DOCS shift to rst - Quantization articles (#16596) 2023-03-31 09:06:52 +02:00
Artyom Anokhov
2a01695370 Deployment Manager: updated configs with 2023.0.0 layout and versions (#16633) 2023-03-29 19:34:26 +02:00