Nikita Malinin
064a18eb09
[POT] Change python version to 3.8+ ( #20071 )
...
* Change python version to 3.8+
* Fix tests
2023-09-27 18:01:34 +04:00
Nikita Malinin
a4b0fe51af
[POT] Update for CI ( #19067 )
...
* Update references
2023-09-01 18:12:24 +02:00
Stefania Hergane and Dan
24f8c4105e
[EISW-89824] [master] Rename VPUX to NPU ( #19004 )
...
* Change `VPUX`/`VPU` occurrences to `NPU`
* Switch `HARDWARE_AWARE_IGNORED_PATTERNS` VPU to NPU
* Rename `MYRIAD plugin`
* Rename vpu_patterns to npu_patterns in tools/pot
* Rename vpu.json to npu.json in tools/pot
* Rename restrict_for_vpu to restrict_for_npu in tools/pot
* Change keembayOptimalBatchNum to npuOptimalBatchNum
---------
Co-authored-by: Dan <mircea-aurelian.dan@intel.com >
2023-08-10 00:20:07 +04:00
8e97010595
remove quantization config for vpu ( #17507 )
...
* remove quantization config for vpu
* remove VPU config testcases from test unify scales
---------
Co-authored-by: shokinal <alexander.shokin@intel.com >
Co-authored-by: Alexander Kozlov <alexander.kozlov@intel.com >
2023-06-05 13:14:48 +03:00
Liubov Talamanova
0c0aa5c997
[POT] Fix POT CI ( #16955 )
2023-04-14 17:21:01 +00:00
Liubov Talamanova
5fca707ebd
[POT] Update CPU_SPR transformer quantization ( #15241 )
...
* [POT] Update CPU_SPR transformer quantization
* Add comments
2023-01-24 15:56:22 +04:00
Liubov Talamanova and Alexander Kozlov
ddd4f050c7
[POT] Fix precommit tests ( #14972 )
...
Co-authored-by: Alexander Kozlov <alexander.kozlov@intel.com >
2023-01-06 13:44:54 +00:00
Liubov Talamanova and Alexander Kozlov
39ff705a3e
[POT] Update CI branch ( #14916 )
...
Co-authored-by: Alexander Kozlov <alexander.kozlov@intel.com >
2023-01-03 17:26:36 +00:00
Liubov Talamanova and Alexander Kozlov
6dd86506cd
Remove openpyxl dependency ( #14764 )
...
Co-authored-by: Alexander Kozlov <alexander.kozlov@intel.com >
2022-12-26 14:24:55 +00:00
Roman Kazantsev
0b2f3347f6
[Tools] Support NumPy 1.24 ( #14728 )
...
* [Tools] Avoid use of NumPy deprecated types
Signed-off-by: Kazantsev, Roman <roman.kazantsev@intel.com >
* Revert "[Tools] Avoid use of NumPy deprecated types"
This reverts commit 21ffc167d1 .
* Move to 1.24 Numpy
Signed-off-by: Kazantsev, Roman <roman.kazantsev@intel.com >
2022-12-19 23:51:34 -08:00
Liubov Talamanova
7ceb8bfce0
[POT] Update test references ( #14318 )
...
* Update references
* Update GNA references
* Rebase branch
2022-12-07 14:05:03 +04:00
Liubov Talamanova
8d360ea3e6
[POT] Keep original out names in statistics collection ( #14042 )
2022-11-17 17:36:14 +04:00
Liubov Talamanova
bb00a9e664
[POT] Enable quantization inside subgraphs for CPU ( #12776 )
...
* Enable LSTMCell quantization
* Refactored unify function
* reverse dict
* Fix docs
* Add LSTM and GRU sequences
* Change scales to unified_scales in hw configs
* Fix inplace statistics
* Shift axis for subgraphs
* Changed HW config
* Update HW configs for tests
* Not quantize GRU ops with linear_before_reset: true
* Enable tests
* Support models with scalar input
* Fix tests
* return back submodules
* Fix tests
* Update GPU HW config
* Fix comments
* Fix axis
2022-11-12 07:54:29 +04:00
Nikita Malinin
8e9a6d3457
[POT] BC update for transformers ( #13869 )
...
* Update node_utils
* HBC update
* Updated HBC & added test
* Apply comments
2022-11-11 11:33:11 +04:00
Liubov Talamanova
58b37c9bc2
[POT] Skip unstable test ( #13889 )
2022-11-07 12:44:16 +00:00
Przemyslaw Wysocki and jiwaszki
520b9ff68c
[PyOV] Disallow Python 3.6 usage ( #13240 )
...
* Remove py3.6 constraints
* Cleanup out of date python versions
* Bump pybind11 to v2.10.1 release tag
* [PyOV] Fix wheel requirements for new package versions
Co-authored-by: jiwaszki <jan.iwaszkiewicz@intel.com >
2022-11-06 10:45:42 +04:00
Liubov Talamanova
03dbd8c4e7
[POT] Update node names in ONNX models ( #13872 )
2022-11-05 21:00:19 +01:00
Liubov Talamanova
02d30c8aaa
[POT] Unify MatMul scales ( #13717 )
...
* Support FQ scales unification for MatMul
* Add test
* Update test_scales.py
2022-11-05 09:33:54 +04:00
Liubov Talamanova
8789fcda04
[POT] Propagate FQ through Gather ( #13583 )
...
* Add Gather to QUANTIZE_AGNOSTIC_OPERATIONS
* Add test
* Update HW configs path in tests
* Fix tests
* Update CI references
2022-11-04 12:21:20 +04:00
Liubov Talamanova
ee93ddc453
Update references ( #13637 )
2022-10-27 10:55:54 +00:00
Liubov Talamanova
968bd6c96b
Fix bug with unknown node type ( #13406 )
2022-10-11 19:05:54 +04:00
Liubov Talamanova
fcfc5c963b
[POT] Fixed non-zero zero point value in symmetric quantized weights ( #13013 )
...
* Fixed non-zero zero point val in symmquantized weights
* Update references
* Add tests
2022-10-04 12:00:16 +04:00
Liubov Talamanova
9f2564670f
[POT] Support SoftSign quantization for GNA ( #13140 )
...
* Add SoftSign to GNA HW config
* Add test
* Update gna3 HW config
2022-10-02 10:43:51 +00:00
Liubov Talamanova
f68b6e27b0
Update references ( #13245 )
2022-09-30 18:10:01 +04:00
Liubov Talamanova
4df8ed881a
[POT] Unroll GRUCell for GNA ( #12930 )
...
* [POT] Unroll GRUCell for GNA
* Add test
2022-09-23 21:57:10 +03:00
Bonhun Koo
572d00eaa2
[POT][GNA] add mixed-precision support for Accuracy Aware Quantization ( #12470 )
...
* [POT] add GNA3 mode
* [POT][GNA3] add mixed-precision support for Accuracy Aware Quantization
* [POT] add GNA AAQ sanity test with synthetic data
* [POT][GNA3] add GNA3.5 mode and minimize AAQ option
* [POT] fix pot/ci fails on config test
2022-09-20 08:47:33 +09:00
Daniil Lyakhov
d0d88fa1ec
[POT] Skip per channel quantizers allining before concats ( #12483 )
...
* Skip per channel quantizers allining before concats
* Test coverage
2022-08-29 13:55:37 +04:00
Nikita Malinin
f2d6248dec
Disable LWT tests ( #12740 ) ( #12763 )
...
(cherry picked from commit 3980672082 )
2022-08-26 12:38:44 +04:00
Daniil Lyakhov
1ea12a0bab
[POT] Finetuned model reference update ( #12610 )
...
* Finetuned model reference update
* Comment with AVX512 reference value
2022-08-17 19:54:39 +00:00
Daniil Lyakhov
edaa7f8e7e
[POT] Precommit reference update ( #12304 )
...
* WIP graph tests fixing
* Fix collectiors graph tests
* remove debug code
* Fix rebase
* eps update for scales tests
* Outputs for some reference models was changed
* Sanity reference metrics update for VNNI CI hosts
* Unused hyperopt dependency which broke python3.6 support is commented
* Minor comments fixes
2022-08-05 17:50:45 +04:00
Bonhun Koo
b371e74735
[hotfix] pytest error of act_act example ( #12093 )
...
* [hotfix] pytest error of act_act example
* remove needless import
2022-07-11 12:56:32 +09:00
Bonhun Koo
d5e8d1d968
Nm/outputs quantization scheme ( #12035 )
...
* [POT] outputs quantization scheme
* [POT] remove needless blank line
* add a range_estimator config for outputs
* Add fq_config_priority
2022-07-07 16:08:55 +09:00
Wonju Lee
62d5f9a006
[POT] Rename ranger to range_supervision ( #11998 )
...
* fix: rename ranger by range_supervision
* ci: dummy commit
2022-06-29 15:27:57 +09:00
Nikita Malinin
5e3e8d6084
[POT] Update POT with the ResultRenaming flag ( #10989 )
...
* Update POT with the ResultRenaming flag
* Update flag
* Update gold
2022-03-25 13:22:20 +03:00
Liubov Talamanova
99f0093615
[POT] Fixed bug with out port for nodes with multiple outputs ( #10932 )
...
* Fixed bug with out port
* Add test
* Fix test
* Change test model
2022-03-23 11:17:06 +03:00
Indira Salyahova
3a8fd7135e
[POT] Method сhange to get bias shape in bc and fbc algoritms ( #10463 )
...
* refactoring: get bias shape in bc and fbc algoritms
* use scipy to take most frequent shape
* pylint
* update reference
* pylint
* Update test_sanity.py
* update test_sanity.py
* Update test_sanity.py
2022-03-17 16:46:28 +03:00
Nikita Malinin
e103af056e
[POT] References & golds update ( #10937 )
...
* Update references
* Update golds & add stats dumping
* Statistics_data upd
* Enable densenet in nightly
* Pylint fixes
* Update try-except WA
* Update simplified gold
2022-03-15 16:55:48 +03:00
Nikita Malinin
4746d0881b
[POT] Update BC with the Parameter nodes connection ( #10848 )
...
* Update BC with the Parameter nodes connection
* Update test_sanity with octave
2022-03-10 10:28:47 +03:00
Nikita Malinin
41818a377f
[POT] Update IEEngine with the Dynamic model support ( #10717 )
...
* Update IEEngine with the Dynamic models support
* Update with the batch
* Method naming fix
* Update image_loader & tests with dynamic models
* Update test_sanity.py
* Replace custom_mo_config from the model
2022-03-05 15:49:21 +03:00
Liubov Talamanova
37923a9183
[POT] Remove DataFreeEngine ( #10600 )
2022-02-22 18:38:08 +03:00
Liubov Talamanova
be6a3c34f1
[POT] Throw exception for IRv10 ( #10345 )
...
* [POT] Throw exception for IRv10
* Update reference models
* Updated AC framework name from dldt to openvino
2022-02-17 10:54:08 +03:00
Nikita Malinin
c8ce93290e
[POT] Sync mode only for gna_sample ( #10355 )
...
* Sync mode only for gna_sample
* Disable test
2022-02-16 11:00:13 +03:00
Indira Salyahova
f1557c06de
[POT] Fix inference sample in fbc when get list prediction ( #10159 )
...
* fix: inference sample in fbc when get list prediction
* update reference metrics
2022-02-15 14:42:40 +03:00
Nikita Malinin
0c855ee8b2
[POT] Renaming NXModel ( #10168 )
...
* NXModel -> CompressedModel renaming
* Update references & remove Dicts
* Pylint fixes
2022-02-08 14:07:12 +03:00
Indira Salyahova
da02951d67
[POT] Fix get layout from model ( #10018 )
...
* fix: layout pot
* layout
* fix: layout
* pylint
* add logger
* Update image_loader.py
* pylint
* repeat layout in data free
* resolve conflicts
* sample
* resolve comments
2022-02-04 11:46:54 +03:00
Liubov Talamanova
b4206fe0a1
Supported Simplified mode without provided config ( #10049 )
...
* Support Simplified mode without provided config
* Change data-source default location
2022-02-03 10:56:25 +03:00
Liubov Talamanova
ca09ddd123
[POT] Implement DataFreeEngine ( #9484 )
...
* [POT] Implement DataFreeEngine
* Add CLI
* Updated CLI
* Moved logic to SynteticImageLoader
* Fix bug with draw modes
* Fix bug in DataFreeEngine
* Fix multiprocessing
* Fix pylint
* Add DataFreeEngine test
* Download models
* Fill background
* Fix test
* Fix args
* Support config option for DataFree mode
* Minor fixes
* Add data_free config
* Add more test cases
* Enable RCNN models quantization
2022-02-01 15:15:20 +03:00
Pavel Finashov
ab3207a81b
POT: Fixed command line to convert models for Windows platform. ( #10024 )
...
* For testing purpose
* Fixed command line for windows: removed re-writing PYTHOPATH
* Changed command line for re-writing PYTHONPATH
2022-02-01 10:31:16 +03:00
Indira Salyahova
6145cb736e
[POT] Update patterns with transpose ( #9555 )
...
* fix: update pot patterns with transpose
* add tests
* delete tests
* updatereference metrics tf model
* Update test_sanity.py
2022-01-31 14:30:28 +03:00
Milana Shhanukova
aa518282b0
updat gna configs ( #9920 )
2022-01-27 08:50:15 +03:00