This pull request adds support for the TensorFlow "**MatrixInverse**"
operation to OpenVINO's TensorFlow Frontend (TF FE). It implements a new
loader function translate_matrix_inverse_op that translates the
TensorFlow operation into the equivalent OpenVINO Inverse operation
(from opset-14) for both real-valued and complex-valued inputs.
Addresses issue:
#[22957](https://github.com/openvinotoolkit/openvino/issues/22957)
Hi Roman @rkazants, could you please review my work, thank you!
---------
Co-authored-by: Roman Kazantsev <roman.kazantsev@intel.com>
### Details:
- *The PR adds RISCV64 arch for python wheel setup to fix the following
error during build on the target machine:*
```
[100%] Building Python wheel
openvino-2024.2.0-14978-cp310-cp310-manylinux_2_36_riscv64.whl
Processing /home/sipeed/openvino/openvino/src/bindings/python/wheel
Preparing metadata (setup.py) ... error
error: subprocess-exited-with-error
× python setup.py egg_info did not run successfully.
│ exit code: 1
╰─> [6 lines of output]
Traceback (most recent call last):
File "<string>", line 2, in <module>
File "<pip-setuptools-caller>", line 34, in <module>
File
"/home/sipeed/openvino/openvino/src/bindings/python/wheel/setup.py",
line 50, in <module>
OV_RUNTIME_LIBS_DIR = os.getenv("OV_RUNTIME_LIBS_DIR",
f"runtime/{LIBS_DIR}/{ARCH}/{CONFIG}")
NameError: name 'ARCH' is not defined
[end of output]
note: This error originates from a subprocess, and is likely not a
problem with pip.
error: metadata-generation-failed
× Encountered error while generating package metadata.
╰─> See above for output.
note: This is an issue with the package mentioned above, not pip.
hint: See above for details.
make[2]: ***
[src/bindings/python/wheel/CMakeFiles/ie_wheel.dir/build.make:177:
wheels/openvino-2024.2.0-14978-cp310-cp310-manylinux_2_36_riscv64.whl]
Error 1
make[1]: *** [CMakeFiles/Makefile2:2841:
src/bindings/python/wheel/CMakeFiles/ie_wheel.dir/all] Error 2
make: *** [Makefile:156: all] Error 2
```
### Tickets:
- *N/A*
### Details:
- Used actual shape in expected output tensor for
`ExperimentalDetectronDetectionOutput` and
`ExperimentalDetectronGenerateProposalsSingleImage` tests.
### Tickets:
- CVS-137158, CVS-137161
### Details:
- Return false when dynamic shape in check_allocatable() to aviod
asstion by big upper bound
- Add excessive upper bound test case in softmax dynamic shape test
### Tickets:
- 135307
### Details:
- Used actual shapes for Tensors creation.
### Tickets:
- CVS-137147
---------
Co-authored-by: Michal Lukaszewski <michal.lukaszewski@intel.com>
### Details:
- Change acceptable filter x size of convolution_bfyx_gemm_like kernel
to avoid kernel build error and slower performance than ref kernel from
64 to 32
### Tickets:
- 137837
### Details:
- adds specification for ROIAlignRotated
- the main difference between ROIAlign and ROIAlignRotated is that new
op has angle parameters which allows to rotate proposal's box.
### Tickets:
- *CVS-115296*
---------
Co-authored-by: Katarzyna Mitrus <katarzyna.mitrus@intel.com>
Co-authored-by: Mateusz Mikolajczyk <mateusz.mikolajczyk@intel.com>
Co-authored-by: Michal Lukaszewski <michal.lukaszewski@intel.com>
### Details:
- The rule of filling data into shape_info[] is to skip it for static
shape input
- However, in scatter_update kernel, that skipping has not been applied
- If there are static shape inputs among the inputs, the number of
static shape input should be applied to the index calculation of
shape_info[]
### Tickets:
- 135859
### Details:
- Used actual shapes for Tensors creation.
### Tickets:
- CVS-137153
---------
Co-authored-by: Michal Lukaszewski <michal.lukaszewski@intel.com>
After the latest release https://pypi.org/project/h5py/#history stopped
being installed as a Python module on arm - it tries to be built from
sources and there is a missing dependency for this. Trying to fix it
without restricting the module version...
### Details:
- Added tests for Round op for both real and complex tensors
- Added support for handling complex tensors for the Round operation
### Tickets:
- #23237
---------
Co-authored-by: Roman Kazantsev <roman.kazantsev@intel.com>
### Details:
- Used actual shapes for Tensors creation.
- Applied to `Convert` and `ConvertLike`.
### Tickets:
- CVS-137152
---------
Co-authored-by: Michal Lukaszewski <michal.lukaszewski@intel.com>
### Details:
- Create functions for validation in a separate file (_validation.hpp_)
- New overload to _cast_to_tensor_ function
- Test for scenarios when an object passed to `setInputTensor()`
`infer()` `setOutputTensor()` `setTensor()` is not a Tensor.
- Remove `Test setInputTensor() - pass number as a single arg` -
overlaps with `Test setInputTensor throws when passed object is not a
Tensor.`
### Tickets:
- *120315*
### Details:
- *Add NPU in the supported hardware matrix*
- *Add NPU in the list of supported plugins*
- *Add NPU plugin in CONTRIBUTING.md*
### Tickets:
- *EISW-119403*
### Details:
- Recommend to set LD_LIBRARY_PATH to point to conda libraries
### Tickets:
- CVS-134534
---------
Co-authored-by: Yaroslav Tarkan <yaroslav.tarkan@intel.com>
### Details:
- *Moving getDriverVersion to the backend makes more sense, and creating
a new helper, getDriverExtVersion that would be used for plugin batching
feature to decide when to use batching on auto mode or only on compile.*
- *Because of E-117498 we need to decide when Compiler or Auto mode for
batching to be used.*
- *DriverExtVersion should be also updated by the driver team for this
to work as expected.*
### Tickets:
- *E-117498*
Tomasz Jankowski