* [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>
* [TF FE] Provide full support of TF1 Control flow and TensorArray ops
Signed-off-by: Kazantsev, Roman <roman.kazantsev@intel.com>
* Add missed header for TensorArrayV3 op
* Temporarily disable GRU cell fusion
* Update src/common/transformations/src/transformations/common_optimizations/moc_transformations.cpp
* Fix a case when element_shape for TensorArrayV3
* Fix translator for TensorArrayCloseV3
* Update summarize graph with TensorArrayCloseV3
* Add layer tests for TensorArrayScatterV3, Close, Size, Array
* Fix output shape for Merge node
* Remove unused variable
* Fix translator for TensorArrayConcatV3
* Fix translator for TensorArrayConcatV3
* Add layer tests for TensorArrayWriteV3, Gather, and Concat
Signed-off-by: Kazantsev, Roman <roman.kazantsev@intel.com>
* Add translator for GatherTree
* Fix TF FE unit-test for GatherTree
* Fix GatherTree translator
* Fix GatherTree translator to handle 1d end_token
* Fix undeclared parameter issue
* Fix GatherTree unit-test
* Add TensorArrayV3Replacer transformation
* Temporarily disable dangling transformation
* Recover RemoveMultiSubGraphOpDanglingParamsResults transformation
* Recover GRUCellFusion transformation
* Simplify check for GRUCellFusion transformation
* Use proper name for unit-tests
* Simplify translator for TensorArrayWriteV3
Signed-off-by: Kazantsev, Roman <roman.kazantsev@intel.com>
* Fix RemoveMultiSubgraphOpDanglingParamsResults transformation
Signed-off-by: Kazantsev, Roman <roman.kazantsev@intel.com>
* Additional fix for remove_multi_subgraph_op_dangling_params
* Make static TI run a dynamic subgraph
* Dedicated SL test
* Change condition to respect stat shapes
* Adjust test to cover the code path properly
* Recover fallback for still failing case GNMT
---------
Signed-off-by: Kazantsev, Roman <roman.kazantsev@intel.com>
Co-authored-by: Maksim Kutakov <maksim.kutakov@intel.com>
* Reference implementation for u4 constant compression from pytorch model based on bitwise ops pattern
* Fixed order of 4-bit halfs in byte
* Switched PyTorch FE to dev mode: in case if model cannot be fully converted, give partially converted model with PTFrameworkNode's with a printed warning (normally would raise an exception in case).
* Moved u4 compression to utils_quantize. Implemented not-interleaved version of u4 compression
* Removed debug output
* Added aten::matmul to the list of exceptions in may_produce_alias as a workaround for gptq models
* Added patching for gptq models applied automatically in convert_model
* WA for an inssue with u4 with earlier convert to fp16
* U4 blocked repacking for gptq patched model layout
* Deleted obsolete u4 re-packing based on aten::cat. Fixed the resulting u4 constant shape. Removed debug output.
* Revert "Switched PyTorch FE to dev mode: in case if model cannot be fully converted, give partially converted model with PTFrameworkNode's with a printed warning (normally would raise an exception in case)."
This reverts commit 0ef1455e70.
* Update src/frontends/pytorch/src/op/cat.cpp
* Check mask and shift values in u4 pattern. deque -> OutputVector for u4_compression_stack
* Convert to a given floating type instead of half in gptq patching. Better structured code.
* Code style fix
* Removed deque include
* Code style fixes
* Trailing space removed
* Fixed patched_forward and ts_decoder after unvalidated commits.
* Swap nibbles in u4/i4
* Better exception handling around jit.trace and gptq.patch_model
* Update src/bindings/python/src/openvino/frontend/pytorch/gptq.py
Co-authored-by: Alexander Kozlov <alexander.kozlov@intel.com>
* Update src/bindings/python/src/openvino/frontend/pytorch/gptq.py
Co-authored-by: Alexander Kozlov <alexander.kozlov@intel.com>
* Code style
* Revers int4 byte order
* Fixed core tests
* Fixed unguarded dynamic_cast result
Co-authored-by: Evgenya Nugmanova <eva.my.link@gmail.com>
* Fixed transformation tests
* Update src/bindings/python/src/openvino/frontend/pytorch/gptq.py
Co-authored-by: Maxim Vafin <maxim.vafin@intel.com>
* Prevent patching of non-gptq models
* Removed extra calling of quantized weights decompression patterns
* Better detection of supported AutoGPTQ models + more diagnostics
* Accurate diagnostics in case when aten::stack has multiple axes
---------
Co-authored-by: Alexander Kozlov <alexander.kozlov@intel.com>
Co-authored-by: Ilya Churaev <ilyachur@gmail.com>
Co-authored-by: Evgenya Nugmanova <eva.my.link@gmail.com>
Co-authored-by: Maxim Vafin <maxim.vafin@intel.com>
* Add Multinomial-13 to MO
* Add Multinomial tests for MO IR reader
* Move convert_type check
* Imports clean up
* Update pacgage BOM file
* Avoid files collision in tests
* [TF FE] Support TF 2.14 and add OnesLike translator
Signed-off-by: Kazantsev, Roman <roman.kazantsev@intel.com>
* Update tests constraints
* Update open_model_zoo
* Adopt TF Lite test to 2.14 TF
Signed-off-by: Kazantsev, Roman <roman.kazantsev@intel.com>
* Support TF Lite layer tests for diffrent TF versions
---------
Signed-off-by: Kazantsev, Roman <roman.kazantsev@intel.com>
* [TF FE] Support TF1 While Control flow
Signed-off-by: Kazantsev, Roman <roman.kazantsev@intel.com>
* Apply code-style fix
* Update API for OpPlace to store back edge
* Fix build: no rvalue by reference passing
* Fix build issue: correct type
* Fix TF FE unit-tests
* Apply code-review feedback: remove unused vars
* Fix fusing complicated case of TF1 While
* Remove unused variable
* Update MO unit test
* Fix layer tests for While
* Handle Switch and NextIteration nodes connected directly
Signed-off-by: Kazantsev, Roman <roman.kazantsev@intel.com>
---------
Signed-off-by: Kazantsev, Roman <roman.kazantsev@intel.com>
* Use FindPython3.cmake
* Fixed compilation on macOS 14 with new core development tools
* Try to use Python3_SOABI instead of PYTHON_MODULE_EXTENSION
* Use Development.Module
* Keep specifying only Python3_EXECUTABLE
* Print PYTHON_MODULE_EXTENSION
* Added check for minimal cmake version for python API
* Returned Python3_INCLUDE_DIR for cross-compilation case
* Try to allow cmake older than 3.18
* Use build python interpreter to check cython dependency
* revert changes in .ci/openvino-onnx/Dockerfile
* removed unused code
* Fixed issue with variables scope
* Experiment: remove include dirs
* Corrected docs
* Use pybind11 function to set extension
* Revert "Experiment: remove include dirs"
This reverts commit 6f7f90211c.
* Refactor ConvolutionBackpropDataLayerTest, ConvolutionLayerTest, DeformableConvolutionLayerTest (#19810)
* Refactor ConvolutionBackpropDataLayerTest
* Refactor ConvolutionLayerTest
* Refactor DeformableConvolutionLayerTest
* Apply comments
* Apply comments
* Fix
* Updated minimum cmake version for Windows
* Simplified check
* Removed useless message status
* Use puiblic option
---------
Co-authored-by: Oleg Pipikin <oleg.pipikin@intel.com>
* [workflows/liux] Trying AKS runners
* Remove sudo usages
* Fix repositories path
* Well, adding debug output
* execution bit?
* more debug output
* using bash...
* We should use shell syntax for env variables in 'run' sections
* again, may be we should use bash...
* fix cloning path for openvino repo
* more debug output
* Trying to populate WORKSPACE var in other way
* Trying different WORKSPACE
* export ALL variables for samples tests
* Trying to put openvino build into correct directory
* Replace more occurences of BUILD_DIR...
* Use shell expansion instead of Actions syntax in run steps
* Skip unit test failures
* Oops, there's no pytest for MO unit tests
* Oops, typo
* Fix LAYER_TESTS_INSTALL_DIR variable expansion
* Fix LAYER_TESTS_INSTALL_DIR for new stages
* Replace all the varibles
* Comment out CCACHE_DIR
I want to test worst-case scenario
* Comment setup ccache step
* Revert "Comment out CCACHE_DIR"
This reverts commit 046663a9f1.
* Just checking something
* Update with new stages from master
* One more stage to fix
* Fix INSTALL_DIR again (new stages were merged to master?)
* Remove concurrency limit (for test purposes)
* Trigger one more pipeline
* Disable concurrency settings
* Trigger another build
* Disable ccache (for testing purposes)
* trigger another build to measure duration without ccache
* And one more test commit
* Return back ccache
* Testing new image
* Enable concurrency back
* Using new image
* And another image
* Trying build on the clean image
* Install git
Upstream ubuntu image doesn't have git
* Oops, forgot apt-get update
* Upstream Ubuntu image, but using ACR cache
* Remove debug output
* Use Ubuntu image from ACR cache for the rest of the stages
* Display version of ccache
* Swith to ubuntu 20 temporarily (I hope)
* Set CCACHE_TEMP_DIR outside of shared space
* Revert "Swith to ubuntu 20 temporarily (I hope)"
This reverts commit 2e53109d83.
* trying ccche nohardlink option
* Trying to disable ccache file cloning
* fix CCACHE_TEMPDIR
* Install git to Python unit tests stage
* Install libsnappy-dev as tests require it
* Install python to test stage
* Fix env vars syntax in few places
* Update docker image name
* Increase timeout for CPU tests
* Debug output - trying to find out what's wrong with test reports
* Change file name in debug-output 'find' command
* let's try shell syntax for upload artifact action...
It most likely won't work but I see strange output in the logs:
Error: No files were found with the provided path: /__w/openvino/openvino/install/tests/TEST*.xml
/runner/_work/openvino/openvino/install/tests/logs/failed/*.log
/runner/_work/openvino/openvino/install/tests/logs/crashed/*.log
/runner/_work/openvino/openvino/install/tests/logs/hanged/*.log
/runner/_work/openvino/openvino/install/tests/logs/interapted/*.log
/runner/_work/openvino/openvino/install/tests/logs/disabled_tests.log. No
artifacts will be uploaded.
So the first path is translated to the path inside the container
correctly and the rest are not O_o
* Revert "let's try shell syntax for upload artifact action..."
This reverts commit eb19b4f319.
* Leave just disabled_tests.log (as it is the only one present)
* Use my own directory instead of github.workspace
Inside-container path translation doesn't work for upload-artifact
actions (it works only for the first path, but not for the rest)
* Revert "Leave just disabled_tests.log (as it is the only one present)"
This reverts commit 4321827880.
* Okay, let's try hardcoded workspace path...
* Okay, path should be inside "official" workspace. Hardcode it
* Missed some variables, replace github.workspace to hard-coded value
* Remove debug output 'find' command
* Remove old-style cache setup
* Clean ccache stats after cmake
* Change docker image to the one with non-root user
* Oops, switch to Ubuntu 20
* Playing with concurrency group name
* Oops, forgot sudo for ninja installation
* Revert "Oops, forgot sudo for ninja installation"
This reverts commit a7e1730279.
* Revert "Oops, switch to Ubuntu 20"
This reverts commit 19fe75f4af.
* Revert "Change docker image to the one with non-root user"
This reverts commit 553116492d.
* Use Ubuntu 20 DockerHub image
* Trying to force apt-get packages not to wait for user input
* Make DEBIAN_FRONTED for all stages
* Update reason of skipped MO unit test
* Add DEBIAN_FRONTED to all jobs
* Fix environment variables expansion in newly-added stages
* Update .github/workflows/linux.yml
Co-authored-by: Ilya Lavrenov <ilya.lavrenov@intel.com>
* Update .github/workflows/linux.yml
Co-authored-by: Ilya Lavrenov <ilya.lavrenov@intel.com>
* Fix review comments
* More review comment fixes
* Remove DEBIAN_FRONTEND from Python Models job
* "Get tools versions" step is absent on master
---------
Co-authored-by: Ilya Lavrenov <ilya.lavrenov@intel.com>
* trying with pytest
* update as per suggested
* pytest testing on compress_quantized_weights_test
* resolved warning of assert on tuple
---------
Co-authored-by: Roman Kazantsev <roman.kazantsev@intel.com>
* [TF FE] Use regular Convolution in case dynamic input channels
This solution is aligned with the legacy frontend but it has limitation.
This is a temporal solution until the core obtains ShapeOf evaluator.
Signed-off-by: Kazantsev, Roman <roman.kazantsev@intel.com>
* Remove unused variable from the test
Signed-off-by: Kazantsev, Roman <roman.kazantsev@intel.com>
* Fix unit-test
* Update mo unit-test
---------
Signed-off-by: Kazantsev, Roman <roman.kazantsev@intel.com>
* Added check that nncf was imported.
* Added check that nncf was imported in MO.
* Added check that nncf was imported in MO.
* Apply suggestions from code review
Co-authored-by: Sergey Lyalin <sergey.lyalin@intel.com>
* Removed not needed import.
* Pylint fix.
---------
Co-authored-by: Sergey Lyalin <sergey.lyalin@intel.com>
* Fixed output_model logic.
* Removed InputCutInfo, disabled input cut in ovc.
* Disabled output cut, added tests for setting shapes or types for not all inputs.
* Returned support of numpy type.
* Separated MO and OVC python API tests.
* Small corrections.
* Added output dir test, exceptions test.
* Tests fixed.
* Corrected extension param description.
* Corrected input description, minor code corrections.
* [PT FE] Use weight share switch in frontend
* Return static for function
* Update src/bindings/python/src/openvino/frontend/pytorch/ts_decoder.py
* Fix issue with quantized constants
* Add tests for shared
* Remove inits, update main one
* Fix stacklevel
* Testing wrong solution
* Testing test test
* Fix test test test test
* mo modules mo problems
* Xfail test that check stdout/err?
* not so correct solution to circular imports
* Fix or not to fix
* CMake magic, co-authors: my best team
* Fix package imports
* Fix tools inits
* Fix ovc tf
* Fix Q000
* Fix F401
* Fix linters
* Add save_model
* Remove LayoutMap
* Move test_utils to 'internal modules'
* First testing
* Missing Type
* Expand main namespace
* Change some more tests
* Add OVAny to namespace
* Add Constant and Parameter to namespace
* More tests changes
* Fix inits
* Add layout_helpers to main namespace
* Revert CMake and linux.yml with ovc
* Update main inits
* Remove MO from tools inits
* changes to init files
* Fix tests
---------
Co-authored-by: Sergey Lyalin <sergey.lyalin@intel.com>
* [MO] compress_to_fp16=True by default (2dn attempt)
* fix unit-tests
* second round of fixin unit-tests
* set compress_to_fp16 default to True in ovc/cli_parser.py
* use save_model in mo_python_api_tests
* enforce compress_to_fp16=False in test_zero_copy
* selectively compress depending on the path user has chosen to generate IR
* corrected doc
* allow compress_to_fp16=False/True for ovc
* doc and unit-tests failing fix
* user save_model in ovc cli tool
* revert back serialize and compress_model but into main instead of moc_emit_ir
* cover more argument combinations for cli tool and convert_model
* Added Torchscript Backend
* First commit for backend with Torch FX Decoder
* Merging changes from Torch FX branch
* Torch FX initial fixes (Temporary)
* Fixed type/shape issues in Torch FX decoder
* Added translation for built-in getitem
* MaxPool update & Output shape fix (Torch FX)
* Torch FX graph outputs fix
* Torch FX support for sigmoid and slu_
* Torch FX graph module caching
* Torch Fx partitioner cache removed
* Torch FX initial getitem replacer added
* Index check for torch fx getitem replacer
* Debug print removed from partitioner
* Added environment variables for pytorch tracing mode and openvino device
* FX translation fix for getitem & getitem replacer removed
* Added checks for PyTorch tracing mode environment variable
* Adding compile mode for fallback
* Added more ops for resnet18
* Added a check for environment variable
* Generalized addmm to work with torchscript and torchfx
* Added the missing batch_norm.default translation
* fx_backend: include get_attr ops to the partitions
* AddeTODO note t to improvget_attr algorithm
* created function for adding get_attr nodes
* fx_backend: added aten.mul.Tensor, re-enabled aten.empty.memory_format
* fx_backend: Additional op support/improvement for Inception V3
* Added comment for fix 64-bit to 32-bit max int conversion
* fx_backend: Update for avg_poolnd to support 3 inputs
* Fixed erorr in decoder.py
* TorchFX caching fix
* Torch backend, op support for Stable Diff. & BERT
* Arranged ops in order and added torch tensor mapping
* Added support for more ops for super glue
* TorchFX: Initial permanent fallback
* TorchFX: New ops for improved TorchVision support
* TorchFX backend optimizations for partitioning and tmp fallback
* working operator updates for superglue
* Updates to operators for superglue
* Removed max.dim and stack
* Cleanup
* Cleanup
* Fixed a couple of syntax issues
* Fixed a couple of syntax issues
* Added missing method to TorchFX Decoder
* Added missing method to TorchFX Decoder
* Removed redundant code for transpose
* TorchFX: Initial StableDiffusion support
* PyTorch decoder ovtype to ctype fix for int64
* Added ops for distilbert
* Fixed few unnecessary include statements
* Seperated TorchFX and TorchScript decoders
* Modified import statements to reflect two decoders
* f64 fix for TorchFX
* Import fix for PyTorch backend modules
* TorchFX serialize graph for debugging (Temporary)
* Serialize and load back feature enabled for TorchFX
* Temporary optimization to remove Broadcast
* Temporary SoftmaxRehapeElimination pass is added
* TorchFX custom model cache directory
* PyTorch bitwise translation, conversion checks enabled
* Naming fix in make_list_construct
* TorchFX: Added comments to Softmax and Slice translations
* translate_chunk temporarily removed for TS backend
* Fixed linter issues
* Addressed clang formatting issues
* Fixed few more clang and linter issues
* Fixed tests to use ts_decoder
* Fixed naming convention issues
* Added missing import
* Added inlined_inputs to TorchScriptDecoder
* Added tests for torch fx backend
* Removed magic numbers in PyTorch decoder utils
* TorchFX decoder data type fix
* Added cast from size_t to int
* TorchFX output handling code cleanup
* TorchFX: Use detached input tensor
* Added missing cast from size_t to int
* Added static cast in group_norm
* Fixed casting issue in split
---------
Co-authored-by: ynimmaga <yamini.nimmagadda@intel.com>
Co-authored-by: Cavus Mustafa <mustafa.cavus@intel.com>
* WIP: parameters cleanup
* Removed debug output, fixed CLI
* Fixed python objects conversion
* Finally renamed mmap to share_weights
* Fixed TF conversion from a file or a directory
* Fixed obvious errors in unit tests
* Deleted layouts from OVC. Fixed most of the fails in ovc unit tests (there are still failures)
* Clenaup other references to layouts and fixed --version
* Fixed case when two model files are passed in TF case
* Fixed multiple model parts passing in ovc command line
* Tests fixed, support of unnamed input in cli parser.
* Remove convert_model from runtime.
* Changed silent to verbose.
* Removed transform param.
* Removed example_input, share_weights from ovc cli tool.
* Remove wrong change.
* Test fix.
* Code corrections.
* Returned comment.
* WA to fix process hanging after extension loading.
* Removed not needed code.
* Added comment.
---------
Co-authored-by: Sergey Lyalin <sergey.lyalin@intel.com>
* [PT FE]: support nested inputs in example_inputs and arg dicts with different argtypes
* accept hande lists as inputs
* Update tools/ovc/openvino/tools/ovc/moc_frontend/pytorch_frontend_utils.py
* update tests and add comments in code
* fix for custom types in annotations and duplicate in mo
* Update tools/mo/openvino/tools/mo/moc_frontend/pytorch_frontend_utils.py
Roman Kazantsev