Jan Iwaszkiewicz
660c6a3e84
[DOCS] Python Exclusives overview ( #10946 )
...
* Add python docs
* Small fix
* Apply comments
* Fix style
2022-03-15 14:26:12 +03:00
Tomasz Dołbniak
29144d3a6b
ONNX Expand extended support ( #10833 )
2022-03-15 12:21:30 +01:00
Bartek Szmelczynski
840e622da5
add snippets for automatic batching ( #10910 )
...
* add snippets for automatic batching
* Update docs/snippets/ov_auto_batching.py
Co-authored-by: Alexey Lebedev <alexey.lebedev@intel.com>
* add missing bracket
Co-authored-by: Alexey Lebedev <alexey.lebedev@intel.com>
2022-03-15 14:17:20 +03:00
Sergey Lyubimtsev
5f27c74d96
Add description for zsh: no matches found : openvino-dev[...] issue. ( #10950 )
...
* Add description for `zsh: no matches found : openvino-dev[...]` issue.
* spell check
2022-03-15 13:37:39 +03:00
Ilya Znamenskiy
fc5356cd3b
[GPU] Spelling fixes ( #10952 )
2022-03-15 12:25:55 +03:00
Yuan Xu
e341cdf541
Add Python version for Docker installation ( #10840 )
...
* update support matrix with Python version
* fix formatting
* update formatting
* fix formatting
* fix formatting
2022-03-15 12:06:48 +03:00
Yuan Xu
e71a05d94d
Minor updates to Linux/macOS/Windows installation guide ( #10955 )
...
* Add Overview page
* Revert "Add Overview page"
* CVS-71745
* fix links & errors
* fix formatting
* update bullet points
2022-03-15 12:06:30 +03:00
Mateusz Tabaka
c58ef365b5
Fuse FQ->Mul also if first FQ input can be constantfolded ( #10712 )
...
The change fixes FQ fusions for subgraphs like 'Const weights'->FQ->Transpose->Multiply.
After PullTransposeThroughFQUp transformation, we end up with following:
'Const weights'->Transpose->FQ->Multiply. Because of the Transpose on first
FakeQuantize inputs, Multiply could not be fused since FakeQuantizeMulFusion
expected that weights is a Constant node.
Ticket: 77785
2022-03-15 09:54:41 +01:00
Nikita Semaev
758d12b9cb
The correct namespace LayerTestsDefinitions ( #10821 )
...
Co-authored-by: Ilya Lavrenov <ilya.lavrenov@intel.com>
2022-03-15 11:34:33 +03:00
Vladimir Zinoviev
4a2d0f39dd
[LPT] Turn back checks in reshape transformation when subtract is absent ( #10939 )
2022-03-15 11:34:12 +03:00
Mikhail Nosov
ef5ad90dd7
[Read time improvement] Avoid calling of 'are_all_data_elements_bitwise_identical()' during Constant creation ( #10858 )
...
* Performance improvement for constant creation
The issue is that 'are_all_data_elements_bitwise_identical()' is called every time in Constant constructor, and it potentially checks all buffer which is O(N) complexity.
While it is needed only if client uses 'get_all_data_elements_bitwise_identical'
Solution:
- Defer calculation until first call of 'get_all_data_elements_bitwise_identical'
- Store calculated value in mutable class member to reuse it on next calls of 'get_all_data_elements_bitwise_identical'
Test verifies both cases:
a) that constant creation with shared memory data (now O(1)) is significantly faster than creation+bitwiseCheck O(N)
b) Than once calculated, value is taken from cache, which is significantly faster than re-calculation
* fix clang-format
Co-authored-by: Ilya Churaev <ilya.churaev@intel.com>
2022-03-15 10:03:47 +03:00
Mingyu Kim
0a8f97f429
[GPU] Friendly exception msg for alloc failure ( #10953 )
2022-03-15 15:48:31 +09:00
Steve Yoo
a9ff10b365
Add SLT to Template Plugin: ROIAling-3 ( #10625 )
2022-03-15 07:31:27 +03:00
Mingyu Kim
0b556fd7a9
[GPU] More friendly exception message ( #10721 )
...
* [GPU] More friendly exception message
* Apply Ilya's comment
Co-authored-by: Ilya Znamenskiy <ilya.znamenskiy@intel.com>
Co-authored-by: Ilya Znamenskiy <ilya.znamenskiy@intel.com>
2022-03-15 09:57:22 +09:00
Karol Blaszczak
3b2b055bfd
repair 2 png files ( #10949 )
2022-03-14 22:03:09 +03:00
Ilya Churaev
ad1c4a24c3
Deprecate version inside DiscreteTypeInfo ( #10781 )
...
* Deprecate version inside DiscreteTypeInfo
* Fixed code style
* Fixed openvino for macOS
* Fixed build for macOS
* Fixed errors for Windows build
2022-03-14 21:18:00 +03:00
Ryan Loney
575b2fad73
Update Binder URL on the tutorials landing page ( #10877 )
...
* Update Binder URL on the tutorials landing page
Binder URL was linking to a file. It should go to an actual Binder tutorial.
(Replaces https://github.com/openvinotoolkit/openvino/pull/10747 )
* binder logo
* fixes
Co-authored-by: CCR\ntyukaev <nikolay.tyukaev@intel.com>
2022-03-14 21:11:01 +03:00
Ilya Churaev
0d404633a9
Add OpenVINO as required component and remove clang-format from example ( #10944 )
2022-03-14 20:05:24 +03:00
Mateusz Tabaka
23eaa80325
Don't memset Constant's buffer if it's about to be filled with data ( #10861 )
...
* Don't memset Constant's buffer if it's about to be filled with data
* dont memset buffer in visit_attributes
2022-03-14 19:36:40 +03:00
Irina Efode
3aa525c003
SubgraphDumper: clone only not constant graph ( #10867 )
...
* SubgraphDumper: clone only not constant graph
* Apply comments
2022-03-14 18:49:11 +03:00
Maxim Vafin
4e27d936b5
Update Convert_YOLACT.md ( #10942 )
2022-03-14 15:21:43 +00:00
Mikhail Nosov
72fe6082ea
[Preprocess] InputTensorInfo::set_from implementation ( #10839 )
...
* InputTensorInfo::from implementation
If user's application already has `ov::runtime::Tensor` object created,
it will be possible to reuse basic characteristics for input (shape, precision) from tensor using InputTensorInfo::from method
* Rename 'from' to 'set_from' as in Python 'from' keyword is used for import modules
Python bindings: from ov.Tensor and from numpy array
* Style fix (quotes)
* Apply suggestions from code review
Co-authored-by: Ilya Churaev <ilyachur@gmail.com>
* Fix code style
* Use set_from in hello_classification CPP sample
Co-authored-by: Ilya Churaev <ilyachur@gmail.com>
2022-03-14 18:02:51 +03:00
Vladimir Paramuzov
4c4581940a
[GPU] Use int64_t type for axis in concat ( #9790 )
2022-03-14 18:02:21 +03:00
Anastasia Kuporosova
d0b4cae2f8
[Python API] move util under utils ( #10923 )
...
* [Python API] move util under utils
* fix importing
Co-authored-by: Ilya Lavrenov <ilya.lavrenov@intel.com>
2022-03-14 14:40:28 +03:00
Mikhail Nosov
96f954c704
[Preprocessing] Crop preprocessing support ( #10805 )
...
* Crop preprocessing support
Note: instead of 'ov::Coordinate' simple std::vector<int> is used because Coordinate don't support negative dimensions
Added unit tests, template reference tests, cpu and gpu tests
* Added python bindings
Fix review comments
* Fixed python code style
* Fix thresholds
* Fix python style
Co-authored-by: Ilya Lavrenov <ilya.lavrenov@intel.com>
2022-03-14 13:32:27 +03:00
Roman Kazantsev
6ec8e53183
Update Model Optimizer User Guide ( #10759 )
...
* Remove install prerequisites steps, order FWs, and move pre-processing details
Signed-off-by: Roman Kazantsev <roman.kazantsev@intel.com>
* Update Introduction: examples of MO CLIs, references to parameters description pages
Signed-off-by: Roman Kazantsev <roman.kazantsev@intel.com>
* Update Setting Input Shape section
Signed-off-by: Roman Kazantsev <roman.kazantsev@intel.com>
* Update Optimizing Preprocessing Computation page
Signed-off-by: Roman Kazantsev <roman.kazantsev@intel.com>
* Revert location of Additional_Optimizations.md
Signed-off-by: Roman Kazantsev <roman.kazantsev@intel.com>
* Describe layout and FP16 support in MO
* Fix docs issue
* Apply feedback
* Apply review feedback
* Clean-up Resources
Signed-off-by: Roman Kazantsev <roman.kazantsev@intel.com>
* Mention FP16 compression in MO Introduction
Signed-off-by: Roman Kazantsev <roman.kazantsev@intel.com>
* Apply the first portion of feedback
Signed-off-by: Roman Kazantsev <roman.kazantsev@intel.com>
* Apply the second portion of feedback
Signed-off-by: Roman Kazantsev <roman.kazantsev@intel.com>
* Apply review feedback
* Apply review feedback
* Apply the third portion of feedback
Signed-off-by: Roman Kazantsev <roman.kazantsev@intel.com>
* Apply suggestions from code review
Co-authored-by: Tatiana Savina <tatiana.savina@intel.com>
* Apply feedback for FP16 compression documentation
* Apply review for FP16 page
* Apply suggestions from code review
Co-authored-by: Tatiana Savina <tatiana.savina@intel.com>
* Update docs/MO_DG/prepare_model/Additional_Optimizations.md
Co-authored-by: Tatiana Savina <tatiana.savina@intel.com>
* Apply feedback
Signed-off-by: Roman Kazantsev <roman.kazantsev@intel.com>
* Apply feedback
Signed-off-by: Roman Kazantsev <roman.kazantsev@intel.com>
* Apply feedback
Signed-off-by: Roman Kazantsev <roman.kazantsev@intel.com>
* Address feedback about tutorials, input_shape option
Signed-off-by: Roman Kazantsev <roman.kazantsev@intel.com>
* Rework Setting Input Shapes section
Signed-off-by: Roman Kazantsev <roman.kazantsev@intel.com>
* Update "See also" list
Signed-off-by: Roman Kazantsev <roman.kazantsev@intel.com>
* Correct conversion documents for each FW
Signed-off-by: Roman Kazantsev <roman.kazantsev@intel.com>
* Refactor TensorFlow converting document and expand Embedding Preprocessing document
Signed-off-by: Roman Kazantsev <roman.kazantsev@intel.com>
* Fix a link to POT
Signed-off-by: Roman Kazantsev <roman.kazantsev@intel.com>
* Apply suggestions from code review
Co-authored-by: Tatiana Savina <tatiana.savina@intel.com>
Co-authored-by: Maxim Vafin <maxim.vafin@intel.com>
Co-authored-by: Tatiana Savina <tatiana.savina@intel.com>
Co-authored-by: Sergey Lyalin <sergey.lyalin@intel.com>
2022-03-14 13:08:58 +03:00
Mikhail Nosov
43cb3920fb
Docs: preprocessing use case with saving model to IR ( #10698 )
...
* Docs: added preprocessing use case with saving resulting model to IR
* Enable Model Caching to 'application code' section
* Fix review comments
2022-03-14 12:12:20 +03:00
Alexey Suhov
ef00057c8e
Change product version to 2022.2.0 ( #10911 )
...
* Change product version to 2022.2.0
* change OPENVINO_VERSION_MINOR
2022-03-14 11:42:03 +03:00
yanlan song
a6583965a5
try avoid timeout in batch plugin during transition in auto plugin ( #10753 )
...
* initial debug
Signed-off-by: fishbell <bell.song@intel.com>
* refine
Signed-off-by: fishbell <bell.song@intel.com>
* remove debug msg
Signed-off-by: fishbell <bell.song@intel.com>
2022-03-14 11:05:26 +03:00
Ilya Churaev
0bc6196d96
Migrate to new RTTI for all transformations and graph structures ( #10703 )
...
* Migrate to new RTTI for all transformations and graph structures
* Fixed code style
2022-03-14 06:57:21 +03:00
Maxim Gordeev
4be227f5a1
[IE Samples] Fixed rights for file with image ( #10924 )
2022-03-12 01:51:34 +03:00
Alexander Zhogov
45d34e7885
CODEOWNERS: Fix 3d party dependencies
2022-03-11 21:43:09 +03:00
Dawid Kożykowski
3b5f3d1957
Snippets for preprocessing migration page ( #10899 )
...
* add placeholder for python version of first snippet
* fix problem with placeholder
* fix wrong file name
* fix fragment name
* update python snippets
* move imports to the top of the code fragments
2022-03-11 21:19:07 +03:00
Przemyslaw Wysocki
de3088adce
[Docs] Add Python snippets for configure devices ( #10913 )
...
* Add Python docs for configure devices
* Bugfixes
* Minor changes
* Minor changes
* Format changes
* Minor changes
2022-03-11 21:17:22 +03:00
Anastasia Kuporosova
23604ca28c
[Python API] Update doc style ( #10708 )
...
* [Python API] Update doc style
* apply comments
Co-authored-by: Ilya Lavrenov <ilya.lavrenov@intel.com>
2022-03-11 19:18:20 +03:00
Irina Efode
7790f2036f
[IE TESTS][CONFORMANCE] Fix for IRs with dynamic shapes ( #10880 )
2022-03-11 19:17:53 +03:00
Vladimir Zinoviev
eebe8c70f9
[LPT] Fix out of bounds access in reshape ( #10791 )
2022-03-11 18:04:14 +03:00
Mikhail Nosov
86322c916b
Fix loading time issues for POT models (with lots of results) ( #10898 )
...
* Fix loading time issues for POT models (with lots of results)
* Same for 'optimized_strided_slice'
2022-03-11 17:44:36 +03:00
Andrey Noskov
6fdd983750
[GNA] Added multi crop test ( #10459 )
2022-03-11 15:05:14 +03:00
Andrey Noskov
caaacb2db4
[GNA] Moved single Lstm-cell test from deprecated tests ( #10472 )
...
* [GNA] Single lstm-cell test added
* Added additional config for test
* one more input and hidden shape
* Added cell with ReLU
Deleted deprecated test
* test added as lstm_cell_basic
* Enabled gna_compact_mode
Co-authored-by: Mikhail Ryzhov <mikhail.ryzhov@intel.com>
* enabled compact_mode in all tests
Co-authored-by: Mikhail Ryzhov <mikhail.ryzhov@intel.com>
2022-03-11 15:03:16 +03:00
Ilya Churaev
d93ce1e246
Added intro to transformation guide ( #10894 )
2022-03-11 14:27:11 +03:00
Vladimir Dudnik
f48b233629
update omz intel models, fix docs ( #10843 )
2022-03-11 12:34:55 +03:00
Vladislav Volkov
9d74f5cd76
Export/import fixed for param->result and const->result models ( #10838 )
...
Co-authored-by: Ilya Lavrenov <ilya.lavrenov@intel.com>
2022-03-11 11:10:56 +03:00
Nikolay Tyukaev
2940db0fb1
benchmark legal, snippet margin bottom ( #10886 )
2022-03-11 11:10:11 +03:00
Sergey Lyubimtsev
dd076264eb
add pre-release description for wheels packages (2) ( #10813 )
...
* add pre-release description for wheels packages
* refactoring
* lines
* Revert "lines"
This reverts commit 01a74dc168
2022-03-11 11:09:17 +03:00
Sergey Lyubimtsev
0dc2ab182b
Update APT instructions according to repository configuration ( #10869 )
2022-03-11 10:45:31 +03:00
Alexey Lebedev
97efdb5020
[docs] python snippet for dynamic shapes ( #10762 )
...
* Create snipp
* link python snipp with doc
* fix docs
* Apply suggestions from code review
Co-authored-by: Jan Iwaszkiewicz <jan.iwaszkiewicz@intel.com>
* Fix cpp comments
Co-authored-by: Jan Iwaszkiewicz <jan.iwaszkiewicz@intel.com>
2022-03-11 08:42:33 +03:00
Elizaveta Lobanova
4e0a740eb3
[GNA] Support of overload correction for MatMul with 2 non-constant layers ( #10447 )
2022-03-10 15:16:17 +03:00
Vladimir Paramuzov
09246e2db8
[GPU] GPU plugin docs ( #10734 )
2022-03-10 15:01:52 +03:00
Anton Pankratov
a8a2640fb7
Added callback and wait migration guide ( #10775 )
...
* Added callback and wait migration guide
* Added start async
* Simplified wait
* Added selector for sync async
* fixed doc
* fixed build
* fixed doc
* fixed doc
2022-03-10 14:00:42 +03:00
