* [PT FE] Fix timm model list according to newest version
* Remove xfail for hf model passed in latest nightly
* Fix code for loading vit_h model
* Restore torchvision
* Update reverse infer to allow changing shape if it already partially defined
* Update tests
* Remove changes in If
---------
Co-authored-by: Roman Kazantsev <roman.kazantsev@intel.com>
* Use system model cache when running torch hub tests locally
* Update tests/model_hub_tests/torch_tests/test_torchvision_models.py
* Update tests/model_hub_tests/torch_tests/test_torchvision_models.py
* Input/output order Keras tests.
* Added precommit mark.
* Added xfail.
* Small correction.
* Check input/outputs by names in FW.
* Moved output order tests to Python API group.
* Corrected comments.
* [TF FE] Fix TF1 SSD PPN model conversion
It contains a case when one Merge node eliminated different conditional flows.
Signed-off-by: Kazantsev, Roman <roman.kazantsev@intel.com>
* Add layer test
Signed-off-by: Kazantsev, Roman <roman.kazantsev@intel.com>
---------
Signed-off-by: Kazantsev, Roman <roman.kazantsev@intel.com>
* Added experimental ScaledDotProductAttention operation in opset12. Supported in PT FE for aten::scaled_dot_product_attention translation. Decomposed in the common optimizations as functional reference.
* Better ScaledDotProductAttention
- Moved decomposition to the decomposing transformation
- Implemented more ctors for the op
- Renamed is_causal to causal
- Shape/type inference native code instead of using decomposition
- Moved the op from opset12 to opset13
- Added Python wrapper for ScaledDotProductAttention
* Fix test that counts ops in the opsets
* Update src/core/src/op/scaled_dot_product_attention.cpp
Co-authored-by: Katarzyna Mitrus <katarzyna.mitrus@intel.com>
* Update src/core/src/op/scaled_dot_product_attention.cpp
Co-authored-by: Katarzyna Mitrus <katarzyna.mitrus@intel.com>
* Move ScaledDotProductAttentionDecomposition from fusions to decompositions.
* Remove not used legacy shape inference in ScaledDotProductAttention
* Better namespace usage
* Register all nodes in ScaledDotProductDecomposition for correct tracking of nodes and running next mather passes on all new nodes.
* Don't use register_new_node_
* ScaledDotProductAttention specification (with an extra scale argument)
* Code style fix
* Scale input implementation for ScaledDotProductAttention
* Handle attention_mask=0 case in the op spec
* Better description of scale input
* N->M in scale description
* Code style fix, remove debug print.
* Apply suggestions from code review
Co-authored-by: Katarzyna Mitrus <katarzyna.mitrus@intel.com>
Co-authored-by: Mateusz Mikolajczyk <mateusz.mikolajczyk@intel.com>
* Fix for case when is_causal is not passed
* Extended description of ScaledDotProduct op
* Better description in py op wrapper
* Basic shape propagation tests for ScaledDotProductAttention
* Added ScaledDotProductAttention to toc.
* Add op impl check
---------
Co-authored-by: Katarzyna Mitrus <katarzyna.mitrus@intel.com>
Co-authored-by: Mateusz Mikolajczyk <mateusz.mikolajczyk@intel.com>
* [TF FE] Fix conversion of TF1 OD models out-of-the-box
Signed-off-by: Kazantsev, Roman <roman.kazantsev@intel.com>
* Add test While with nested If operation
Signed-off-by: Kazantsev, Roman <roman.kazantsev@intel.com>
* Update tests/layer_tests/tensorflow_tests/test_tf_While.py
---------
Signed-off-by: Kazantsev, Roman <roman.kazantsev@intel.com>
* [TF FE] Support complex tensors
Signed-off-by: Kazantsev, Roman <roman.kazantsev@intel.com>
* Align output type for Real and Imag operations
Signed-off-by: Kazantsev, Roman <roman.kazantsev@intel.com>
* Update decoding complex types
* Add support for ComplexAbs, FFT and IFFT operations
Signed-off-by: Kazantsev, Roman <roman.kazantsev@intel.com>
* Correct axes based on a number of inner-most dimensions
* Add layer tests
Signed-off-by: Kazantsev, Roman <roman.kazantsev@intel.com>
* Update supported ops documentation
Signed-off-by: Kazantsev, Roman <roman.kazantsev@intel.com>
* Add a comment for ComplexTypeMark
Signed-off-by: Kazantsev, Roman <roman.kazantsev@intel.com>
---------
Signed-off-by: Kazantsev, Roman <roman.kazantsev@intel.com>
* [TF FE] Switch off TF1 While support totally
This is a total switch off due to GPU limitation
Signed-off-by: Kazantsev, Roman <roman.kazantsev@intel.com>
* Need additional fallback in Enter to avoid shapes problem
* Disable tests with While op
Signed-off-by: Kazantsev, Roman <roman.kazantsev@intel.com>
* Disable layer test for TF1 While
* Remove extra spaces
---------
Signed-off-by: Kazantsev, Roman <roman.kazantsev@intel.com>
Ekaterina Aidova
Maxim Vafin
Roman Kazantsev
Pavel EsirandMaxim Vafin
Luo Cheng
Anastasiia Pnevskaia
Przemyslaw Wysocki
dependabot[bot]
Andrey Kashchikhin
rsato10andRoman Kazantsev