### Details:
- *Complete the remaining work after the
[PR](https://github.com/openvinotoolkit/openvino/pull/24297) is merged.*
- *Add test case.*
### Tickets:
- *141542*
---------
Signed-off-by: xipingya <xiping.yan@intel.com>
Co-authored-by: Zlobin Vladimir <vladimir.zlobin@intel.com>
**Details:** Previously, we were able to convert models requiring
openvino-tokenizers extensions (like with string operations, ragged
tensors) only in Python by `convert_model`. Now we add option to convert
using `ovc` tool. The tool internally imports extensions if they are
installed.
**Ticket:** TBD
---------
Signed-off-by: Kazantsev, Roman <roman.kazantsev@intel.com>
**Details:** Remove test-generator dependency. It is removed since this
module seems to be no longer developed and maintained. So it is better
to remove this dependency. `pytest` can substitute `test-generator`.
**Ticket:** TBD
---------
Signed-off-by: Kazantsev, Roman <roman.kazantsev@intel.com>
**Details:** Fix h5py issue in GHA test jobs: `error: libhdf5.so: cannot
open shared object file: No such file or directory`
**Ticket:** TBD
---------
Signed-off-by: Kazantsev, Roman <roman.kazantsev@intel.com>
### Details:
- Send Telemetry info during importing of openvino, required for correct
user count statistic.
Following line will trigger event sending:
import openvino
For Linux event send time:
~0.08016 ms
For Win event send time:
~0.31248 ms
### Tickets:
- 133670
Depends on: https://github.com/huggingface/optimum-intel/pull/648
---------
Co-authored-by: Ekaterina Aidova <ekaterina.aidova@intel.com>
### Details:
Numpy started preparation to release 2.0 version.
It brings many breaking changes listed below.
Align with these changes it's a plan for further development
(CVS-138766), for today we want to secure users against unintentional
installation of 2.x version of numpy with OV.
This PR has to be ported for 2024/1 branch
- Preparing to restrict OV to not use release of Numpy 2.0 which may
introduce many breaking changes including:
- required bump of `pybind` to 2.12+
- API and namespaces clean-ups and deprecations
- behavior changes of keywords such as `copy`
- changes to existing and introduction of new dtypes (such as
`StringDType` and possibility of adding custom ones)
- more can be found here:
https://numpy.org/devdocs/release/2.0.0-notes.html
- and here:
https://numpy.org/devdocs/numpy_2_0_migration_guide.html#numpy-2-migration-guide
### Tickets:
- CVS-138838
---------
Co-authored-by: Michal Lukaszewski <michal.lukaszewski@intel.com>
### Details:
- Removed internal conversion of all typed passed to `convert_model()`
to `np.dtype`, as some types do not have `numpy` analogs, which causes
errors. Also this step is redundant as we can use `ov.Type` instead.
### Tickets:
- 138755
New PR due to merge
conflicts(https://github.com/openvinotoolkit/openvino/pull/22917)
Updated the copyright year from 2018-2023 to 2018-2024 in all openvino
files
Ref. to script: CVS-101144
Command used:
```bash
git grep -lz '2018-2023 Intel Corporation' | xargs -0 sed -i '' -e 's/2018-2023 Intel Corporation/2018-2024 Intel Corporation/g'
```
- Updated paths in an entire documentation,
- updated scripts used in docs building process,
- updated docs cmake to handle new scripts,
- fixed links,
- fixed other errors found in docs.
---------
Co-authored-by: Maciej Smyk <maciejx.smyk@intel.com>
Co-authored-by: Sebastian Golebiewski <sebastianx.golebiewski@intel.com>
Co-authored-by: Karol Blaszczak <karol.blaszczak@intel.com>
Co-authored-by: Andrzej Kopytko <andrzejx.kopytko@intel.com>
Co-authored-by: Tatiana Savina <tatiana.savina@intel.com>
Co-authored-by: Vishniakov Nikolai <nikolai.vishniakov@intel.com>
### Details:
- Extended `Core` class to interact with Remote API via `compile_model`,
`create_context` and `get_default_context`.
- Added `RemoteContext` and `RemoteTensor` classes to Python API.
- Added `ClContext` and `ClImage2DTensor` classes placeholders.
- Added `VADisplayWrapper`, `VAContext` and `VASurfaceTensor` classes.
- Added utility function to raise `NotImplemented` errors.
**TODO list (with cc's):**
- [x] Decide which `VADisplayWrapper` constructors stay.
`VADisplayWrapper(VADisplay device)` (which translates to `void*`) is
quite necessary to pass memory pointers from/to external libraries.
`VADisplayWrapper(std::string& device)` is not necessary as it
introduces additional build dependency on libva itself. However, there
are no standard libva bindings that expose such functionalities.
- [ ] Proposal: change of `create_tensor` to `create_device_tensor ->
RemoteTensor` to make difference clear while API expose
`create_host_tensor -> Tensor`. (cc @ilya-lavrenov @slyalin)
- [x] Question: move CL and libva related classes to specific submodules
`openvino.intel_gpu` or keep it as-is in flat namespace? (cc
@ilya-lavrenov @slyalin @akuporos)
- [x] Decide on how memory management should work. My draft proposal:
expose in future PR as "read-only" via custom bindings to `cl_mem` in
case of accessing `ClImage2DTensor`.
- [x] Add test cases.
### Tickets:
- *129468 and 129469*
---------
Co-authored-by: Michal Lukaszewski <michal.lukaszewski@intel.com>
### Details:
moc_front_end.add_extension(extension) has checks of filepath existence
and creation of absolute path from relative path logic.
It is not needed to have this logic in convert_model().
### Tickets:
- 132251
### Details:
- "To disable all extensions including those that are placed at the
default location, pass an empty string." - this line applies only to
legacy MO.
### Tickets:
- 132289
* [PT FE] torch.export support
* Apply code style
* Fix build
* Support torch <2.2
* Support more operations
* Update tests/model_hub_tests/torch_tests/torch_utils.py
* Support for model operations
* Support is_causal as kwarg for SDPA
* Update src/frontends/pytorch/src/op/addcmul.cpp
* Update tests/model_hub_tests/torch_tests/test_timm.py
* Support only decoder passed to convert_model
* Fix tests
* Update src/bindings/python/src/openvino/frontend/pytorch/fx_decoder.py
* Update src/bindings/python/src/openvino/frontend/pytorch/fx_decoder.py
Co-authored-by: Ekaterina Aidova <ekaterina.aidova@intel.com>
* Apply suggestions from code review
* Apply suggestions from code review
* Improve testing with caching model
* Apply suggestions from code review
---------
Co-authored-by: Ekaterina Aidova <ekaterina.aidova@intel.com>
* [TF FE] Support TensorFlow 2.15
Signed-off-by: Kazantsev, Roman <roman.kazantsev@intel.com>
* Use lower version of pylint
Signed-off-by: Kazantsev, Roman <roman.kazantsev@intel.com>
* Update tools/constraints.txt
* Update tools/constraints.txt
---------
Signed-off-by: Kazantsev, Roman <roman.kazantsev@intel.com>
* Get rid of distutils
* get rid of LooseVersion
* try to get rid of clean and copy_file
* fix mo tests
* fix warning in mo
* Update src/bindings/python/wheel/setup.py
Co-authored-by: Jan Iwaszkiewicz <jan.iwaszkiewicz@intel.com>
* add packaging to requirements
---------
Co-authored-by: Jan Iwaszkiewicz <jan.iwaszkiewicz@intel.com>
* link update
* link update
* link update
* Update dev_api_references.rst
* Update dev_api_references.rst
* Update apidoc.py
* notebooks links
* notebook link update
* filename update
* link update
* link update api
* [MO][TF FE] Switch off fallback to legacy FE
Signed-off-by: Kazantsev, Roman <roman.kazantsev@intel.com>
* Support complex condition for TF While
Signed-off-by: Kazantsev, Roman <roman.kazantsev@intel.com>
* Support TensorArrayV3 of a dynamic size
Signed-off-by: Kazantsev, Roman <roman.kazantsev@intel.com>
* Test TensorArrayV3 of dynamic size
Signed-off-by: Kazantsev, Roman <roman.kazantsev@intel.com>
---------
Signed-off-by: Kazantsev, Roman <roman.kazantsev@intel.com>
* [MO][TF FE] Remove informative messages about API1.0 and TF FE limitations
Signed-off-by: Kazantsev, Roman <roman.kazantsev@intel.com>
* Update unit-tests
Signed-off-by: Kazantsev, Roman <roman.kazantsev@intel.com>
---------
Signed-off-by: Kazantsev, Roman <roman.kazantsev@intel.com>
Xiping Yan