* Initial version of ReduceL1, ReduceL2 and ReduceLp enabling in the MO
* Added operations ReduceL1 and ReduceL2 to nGraph
* Removed ReduceLp. Added ReduceL1 and ReduceL2
* Separated specification of ReduceLp into ReduceL1 and ReduceL2
* Updated ReduceL1 and ReduceL2 specification
* Fixed ReduceL1 and ReduceL2 type prop tests
* Implemented nGraph transformation to decompose ReduceL1 and ReduceL2. Disabled them for CPU and GPU plugins
* Updated supported framework layers
* Added unit tests for ReduceL1 and ReduceL2 reference implementation
* Fixed ReduceXXX operations reference implementation by adding support for a new parameter 'keep_dims'
* Fixed constant folding for v0::Any
* Added ReduceL1 and ReduceL2 to Python API
* Implemented ReduceL1 and ReduceL2 decomposition tests and fixed ReduceL2 decomposition
* Added specific creator for ReduceXXX operations instead of NodeBuilders
* Fixed conversion ReduceXXX to CNNLayer
* Fixed parser for ReduceLogicalXXX operations
renamed logits -> bbox_deltas
updated ngraph unittests for Proposal
removed validate_and_infer_types Proposal-4
removed validate_and_infer_types Proposal-4
changed validate_and_infer_types in parent class of Proposal
removed get_output_size
successfully inferred Proposal on SSH and Faster-RCNN
added unittests for Proposal-4
added unittests for Proposal-4
added unittests for Proposal-4
returned back default namespace for Proposal
reduced number of outputs in v0::Proposal
correct conversion of Proposal-4 -> propodal_ie with 2 outputs
removed creator for proposal v0
removed converter for proposal v0
added Proposal-4 to MO
removed `for_deformable` attribute
added Proposal-4 to MO and nGraph Python API
removed typo in Proposal-4 specification
style corrections
style corrections and removed some redundant code
rename proposal Python api test
removed 'attrs' context from visitor
returned back AttrVisitor to check if passes OpenVINO ONNX pipeline
Should pass OpenVINO ONNX pipeline (returned back AttrVisitor just to check)
python api for Proposal-4 works ok
(style correction) python api for Proposal-4 works ok
parametrized proposal_ie some other corrections
removed 'attrs.' context from nGraph Python API tests for Proposal
minor corrections in replacer proposal->proposal_ie
corrected Python API OpenVINO-ONNX tests should pass
Improved workaround for AttributeVisitor for Proposal
Add additional check of im_info tensor shape to Proposal node in MKLDNNPlugin
😠 removed 4 extra spaces from test_dyn_attributes.py to match The Style
added new nGraph RTTI declarations, removed throwing exception in transformation
added new nGraph RTTI declarations, removed throwing exception in transformation, corrected exception in MKLDNNplugin
corrected im_info size checking in Proposal node of MKLDNNPlugin
* Separate MO configuration for TensorFlow 2 model conversion
Also, it updates documentation including steps to convert
TF2 model with a custom layer in Keras H5 format into SavedModel
* Do fixes based on the first-round code review
* Specify, review and approve operation Proposal-4
* added types section and some other corrections
* Added example of Proposal-4 without reductions
* Corrected information about input tensors
* removed 'logits' from specification, added information about shapes
* removed `for_deformable` attribute
* changed `batch_size` to 7
* updated output dimension
* Removed legacy library includes from plugin api headers
* Removed IInferencePluginAPI interface; merged with IInferencePlugin
* Removed pluginAPIInterface usage in Core implementation
This PR introduces next changes:
1. Transformations *_tbl.hpp files were replaced with direct registration in cpp files.
2. Plugins use pass::Manager to call conversion passes.
3. Transformations callback was moved to PassBase class as there is no more need to keep it in separate class
4. All pattern based transformations must be inherited from MatcherPass class. GraphRewrite class will be used only for matchers registration and execution on function.
MatcherPass class adds new features to pattern-based transformations approach:
* Allows to run matcher pass on a single node.
* Operations that were created inside transformation callback can be added to execution list to be available for pattern matching within single GraphRewrite.
5. GraphRewrite MatchClosure was replaced with MatcherPass. So all matchers will be registered as a MatcherPass.
6. Added pass::Manager::clear_state() method to avoid dependency with nodes that no longer belongs to function after replacement.
7. Some representative transformations were updated to use MatcherPass as an example.
8. Mul->Add sequence fusion transformation was replaced with LinOpSequenceFusion.
9. Pattern and callback registration code was moved to class c-tors (will be finished for remaining passes in other PR) .
10. Updated pass::Manager to get pass names only when NGRAPH_PROFILE_PASS_ENABLE enabled.
11. Moving towards removing PassProperty.
12. Added ngraph::pattern::wrap_type<T>(inputs, pred) to simplify pattern creation.
13. GraphRewrite was updated to execute MatcherPass more efficient.
* Network serializer for v7 is removed
* Fixed compilation
* Fixed Windows build
* WA for GPU
* Create function 2 times
* Fixed compilation
* Added return
* Specify operation CTCLoss-4
Signed-off-by: Roman Kazantsev <roman.kazantsev@intel.com>
* Correct documentation for CTCLoss after #1 review
Signed-off-by: Roman Kazantsev <roman.kazantsev@intel.com>
* Correct documentation for CTCLoss after #2 review
Signed-off-by: Roman Kazantsev <roman.kazantsev@intel.com>
* Correct documentation for CTCLoss after #3 review
* Correct documentation for CTCLoss after #4 review
Signed-off-by: Roman Kazantsev <roman.kazantsev@intel.com>
* Correct layout for logits and add more description for unique attribute
Signed-off-by: Roman Kazantsev <roman.kazantsev@intel.com>
* Correct types for length and indices tensors
Signed-off-by: Roman Kazantsev <roman.kazantsev@intel.com>
* Correct formulas and punctuation
Signed-off-by: Roman Kazantsev <roman.kazantsev@intel.com>
* Added mish layer doc opset
* Refactoring mish spec
* Update mish spec
* Change output description of Mish layer
* Fix Mish according to review
* Refactoring Mish and GELU spec according to code review
* Update formula for ops in spec
* Refactoring spec text
* Update Mish opset
* Change Mish version from 1 to 4
* Sort opset4
Co-authored-by: Your Name <you@example.com>
* Added documentation for Interpolate-3.
* Some fixes.
* Fixed some typos.
* Now Interpolate-3 is Interpolate-4.
* Fixed typo.
* DEleted unused 'mode' 'area'.
* Fixed some typos.
* Now 'axes' attribute is an input of Interpolate.
* Added description of variants of nearest_mode.
* Added descriptions of coordinate transformation modes.
* Now 'axes' is an optional input.
* Fixed typo.
SparseToDense used in Wide and Deep model is expressed through ScatterND operation.
ScatterND is more functional than SparseToDense. Hence, it was decided to replace SparseToDense
with ScatterND. ScatterND is more useful for other models.
Remove SparseToDense from the previous opset
Signed-off-by: Roman Kazantsev <roman.kazantsev@intel.com>
