* Infrastructure for tflite
* Removed submodule flatbuffers
* Added flatbuffers submodule. Fixed version to v22.12.06 aka acf39ff
* Move headers back
* Flatbuffers integration
* Small fixes
* Started parsing the Model
* flatbuffer changes
* decoder_flatbuffer changes
* Lite Input Model -- not needed as of now but looks cool
* Rolled back inherritance from ov::frontend::tensorflow::InputModel
* Results are not treated as outputs, but its ok
* Fix missplaced input vs output
* Refactor
* Load model op-by-op. Frontend API finalized
* Debugging still, there are prints here and there. Decoder is not sane
* Convolution with all attributes is translated and quantization is applied for inputs and constatants. TODO: quantize intermediate tensors, separate decoder specific logic?
* Float ssd and posenet models are showing good accuracy
* Need to refactor but work flawlessly
* Telemetry and lightweight model cutting
* Code style and test changes. Extensions supported
* Quantization and style
* Style refinements
* Move onednn back
* New portion of operations enabled
* TFLite FE doesn't inherrit TF FE
* Moved files to another directory
* Rename header op_table.hpp to common_op_table.hpp for all files in src/frontends/tensorflow_common/src/op/
* Removed visability macroses
* CMake changes
* Unit-test execution in .ci
* Update labeler.yml
* Codeowners
* Style check and fix
* Static Build arrangement
* Addressing the comments
* install common headers to previous place
* New approach with public decoder and graph_iterator
* New approach with public decoder and graph_iterator
* Move GraphIterator back
* Comments addressed
* Comments adressed
* Preliminary TF FE README.md changes
* Added target_compile_definitions OPENVINO_STATIC_LIBRARY for static build
* Fixed conflicts and added TF to common places
* Frontends use only openvino::core::dev API
* Merged common tensorflow changes and made code build and work on selective number of models
* Style
* Rollback unnecessary changes from Tensorflow FE
* Rollback unnecessary changes from Tensorflow Common
* Minor refactor
* cmake minor refactoring
* Mixed commit
* Style and merge fix
* Low hanging fruit operations
* Fix windows build
* Refactor quantization parameters representation
* license compliance. approved by OS PDT
* copyrights in generic file
* dependabot
* labeler
* Unit Test to be triggered in CI
* cmake variables naming. corrected copyright years in copyrights/generic file
* library renamed in .ci/ calls
* Copyright year update
* Set openvino-tf-frontend-maintainers as owner of /src/frontends/tensorflow_lite/
* Fixed flatc corss-compilation
* Cleaned flatbuffers header usage
* Nitpicks solved
* Update cmake/templates/OpenVINOConfig.cmake.in
* Compile with flatbuffers headers
* Fixed "which is prefixed in the source directory"
* Fixed typo in flatbuffers cmake
* Removed flatbuffers submodule
* Added fork submodule
* Fixed static build
* Fixed cross-compilatio
* Fixed -Wshadow warning
* Fixed warning on Windows
* Use only headers from flatbuffers library
* Added LTO and fixed compilation errors on Windows
* Fixed warnings in tensorflow_common
* Move ctors implementation to cpp file
* Added information about new frontends to common FEm part
* Temporaryily disable warnings
* Fixed code style using clang-format
* Fixed Windows
* reverted changes in onnx
* Revert changes in onnx_common
* Removed pragma once frm cpp
Co-authored-by: missjane <estepyreva@gmail.com>
Co-authored-by: Ilya Lavrenov <ilya.lavrenov@intel.com>
* Review propagate interval shapes and labels
* Review eye template shape inference
* Add partial value and label propagation on inputs
columns and rows
* Include array in eye shape inference
* Fix compilation issues
* Remove local label_t alias from eye tests
* [GNA] Fix issue with Parameter followed by Broadcast/Tile layer
* added InsertCopyBeforeLayerToBeEliminated transofrmation: handling issue with
Broadcast and Tile layer in case they are eliminated from network,
* added tests for verifying fix
* [GNA] Fix review comment. Remove unnecessery loop and varialble
* [GPU] Perform memory transfer from usm_host to usm_device only for dGPU
* [GPU] Allocate new memory buffer for biases fusions to avoid original buffer modification since it may be used by other primitives
* New static shape inference iface using ov::Tensors
- Add new shape inference factory
- Add helpers to create inference factory map entries
- Create map for IShapeInferCommon instead of if else switch
- Create new map for IStaticShapeInfer
* Re-factor tile shape inference to use new iface
* ov::default_label_evaluator uses ov::Tensor now
* Improve cmp::lt for mixed types unsigned and float
* Fix cpp lint issue
* Update using tile shape_inference in GPU plugin
* Do tile shape infer before repeats lock deletion
* Fix label type conversion to element type
* Rename shape infer transformation
to type utils and change namespace from ov::sh_infer_tr to ov::util
* Update shape inference utilities
* Add unit test for safe compare of values
* Update shape infer factory to be a template
and use unordered map
* Remove from_label_type as lebel_t can be used
by element:from<>
* Add PushConstantToSubgraph transformation
Transformation detects constfoldable inputs to MultiSubGraphOp,
constantfold them and then pushes them to inner subgraphs.
Ticket: 98155
* cast to int
* comments, split to functions
* remove op::util
* Excluded EXACT mode from the test
* Update src/plugins/intel_gna/tests/functional/shared_tests_instances/behavior/ov_infer_request/inference_chaining.cpp
* Remove None at outputs of the model, improve types handling in frontend
* Fix py code style
* Add torch dependency in pybind tests
* Fix tests if fe is disabled and add backward type cpnversion
* Move decoder tests to layer tests
* Fix codestyle
* Add comment
* Move tests to separate folder
* Update .ci/azure/linux.yml
* [MO][TF FE] Switch MO to TF FE in default mode
Signed-off-by: Kazantsev, Roman <roman.kazantsev@intel.com>
* Fix code-style
* Extend operations for the fallback
* Fix MO unit-tests
* Check only legacy FE for read-from-memory functionality
* Fix failures in IR comparator tests
* Fallback to the legacy FE in case tensorflow_custom_operations_config_update
* Revert copyright and update
* Fix unit-test since it is oriented for the legacy FE
* Fallback to the legacy FE in case deprecated config options
* Fix value propagation from deprecated config option
* Fix the Result node name in case cutting by input port for outputs
* Set Result node name aligned with the Legacy Frontend
* Reformat a list of operations to fallback
Signed-off-by: Kazantsev, Roman <roman.kazantsev@intel.com>
* Safe loading of default plugins
1. In case of default plugins.xml all plugins is registered by
absolute paths
2. In case of user API user is able to specify abs or rel path
or plugin name to be found in ENV
3. Update `ov::util::get_absolute_file_path()` in order to prevent
checking file exists or can be accessed
4. Add tests + delete duplicated tests
* Add `OV_CORE_CALL_STATEMENT` to `Core()` ctor
to convert InferenceEngine::Exception to
ov::Exception
* Add `ie_plugins.hpp` dependency to `ov_infer_unit_tests`
* Update C and Py docstrings
* Comment fix
* Update LD_LIB_PATH in openvino-onnx/Dockerfile
* Skip `test_register_plugin*` for Debian job
* Review TopK for:
- label and dimension propagation
- partial value and label propagation
- preserve partial value and labels
- add evaluate upper, lower and label
* TopK v1 use shape infer instead fallback
- update static shape inference tests
* TopK shape_infer return output shapes
* Add new way to get tensor data as shape
with custom data processing
- Update tail op to use new function
- Update topk op to use this function
- Add test for negative k
* Add missing include
* Fix compilation issues
* Add support for i4 and u4 element types in
get_raw_data_as
* Fix signed and unsigned and compile warnings
* Remove constexpr from InTypeRange::operator()
* Use forward reference for functor
- minor corrections in InTypeRange class
* Use shape)infer in evaluate
- fix TopK v3 ctor for input data validation
* Fix transformation tests to use correct type for k
* Fix f16 handling in get_raw_data_as
* Correct topk bounds evaluators
* Topk detect overlap for same size dimensions
As op specification not guarantee correct order of
several elements same value
* Remove evaluate bounds
required investigation if required then will be provided
* Remove bound evaluation leftovers
* Update get const data in slice ops
