* Draft version of new approach for Proposal sub-graph conversion for TF OD API models
* Added clip_after_nms = True for Proposal sub-graph being replaced with DetectionOutput
* Refactored code to insert DetectionOutput instead of Proposal operation
* Code cleanup
* Added separate function to insert DetectionOutput instead of Proposal operation
* Updated transformation configuration files for the TF OD API models with Proposal transformation
* Code refactoring
* Code refactoring
* Fix for the condition
* Fixed transformation
* Fixed transformation. One more time
* Updated document about conversion of the TF OD API models
* Update code comments
* Allow to read and serialize IRs with -1 in dimensions (partially defined shape)
* Added unit test for reading/writing IR with partially defined shapes
* Added missing xml file with test IR
* Remove copy-paste issue
* Output message fix
* Restored statification of the output shapes during IR serialization
* Try to make dynamic shapes static with upper bound
* Code style changes
* Improve model cutting
* If part of model is cut, conversion rules must not run on it
* Add incorrect cut test
* Fix code style
* Fix test
* Fix codestyle
* Do not change op places graph on convert
* Assert output has producer
* Fix code style
* init version, need revise: opset7
* add convert testcase
* multiclass_nms support spec
* init version
* matrixnms support spec
* init support for matrix_nms
* impl matirx_nms
* implemented multiclass_nms reference.
TODO: more test cases.
* support dynamic shape in test
* update to spec 0611
* update to spec 0611
* fixes.
* fix: now sort by class_id and score work.
* fix clang check error
* more test cases verified.
* fixes in ref impl.
* attribute nms_eta works
* test cross_batch and output_type i32.
* enable multiclass-nms cpu plugin fallback ngraph
* keep topk typo
* enable matrix-nms cpu plugin fallback ngraph
* support sort_result_across_batch
* Add matrix_nms unit test
* Add cross batch test cases
* fix typo
* move multiclass to opset8
* move matrixnms to opset8
* Reference implementations for MulticlassNms and MatrixNms ops
* fix name conflict
* remove unused var
sort_result_across_batch default set to false
* avoid float overflow
* fix clang check error
* info for mac fail
* change testcase due to unstable sort
* nms add 'normalized' attribute
* multiclass cpu test support 'normalized'
* nms add 'normalized' attribute
* fixes: 1. normalized support. 2. sort by score before keep_top_k inside a batch.
* fixes: 1. normalized support. 2. sort by score before keep_top_k inside a batch.
* fix sort order in matrix_nms
* fix review comments
* add matrix_nms MKLDNN extension layer
* parallel in matirx nms
* separate filtered_box
* separate class_nms result
* parallel in class
* parallel in batch
* partial new nms
* partial remove useless function
* debug & fix
* debug in indexing
* fix test cases
* remove logging
* fix code-style
* fix typo
* add matrix_nms extension
* nms python api
* remove unused testcases
* refactor transformation
* transform dynamic shape to static shape
* Update inference-engine/src/transformations/include/ngraph_ops/nms_static_shape_ie.hpp
Co-authored-by: Ilya Churaev <ilyachur@gmail.com>
* remove register_pass call
* [MKLDNN]migrate matrix_nms to MKLDNNNode
* bug fix in matrix_nms
* padding on matrix_nms
* remove logging
* test case refine
* merged transform_matrix_nms branch
* refine matrixnms testcase
* multiclass nms cpu plugin implement for static shape, rebased on Reference implementations PR
* rebase to new multi-classs transform provided by lc
* Name style algin with matrix-nms
* static shape padding style to batch inside,new unit test method, real classnum shape
* fix format
* fix ci error
* multi-class NMS modification based on PR reviewer opinion: code format, copyright, delete unused include and funciton way
* explicit template instantiation due to mac ci fail
* Yi3/fix review (#16)
* fix coding style
* use parallel_for2d
* fix ci fail
* unify 'copyright 2021'
* mkldnn_multiclass_nms node update based on PR review (#17)
* [MKLDNN] apply suggestion for matrix_nms (#18)
* fix bug
* apply review comments
* apply review comments
* apply review comments
* apply review comments
* skip only Nms test, not MatrixNms MulticlassNms test
Co-authored-by: Zhang Yi3 <yi3.zhang@intel.com>
Co-authored-by: jialipen <cecilia.peng@intel.com>
Co-authored-by: mangguo <mang.guo@intel.com>
Co-authored-by: Ilya Churaev <ilyachur@gmail.com>
Co-authored-by: liubo-intel <bo4.liu@intel.com>
* Implement transformation for TensorFlow 2 Map Function primitive
Signed-off-by: Roman Kazantsev <roman.kazantsev@intel.com>
* Add a description for get_external_node_by_internal_id function
Signed-off-by: Roman Kazantsev <roman.kazantsev@intel.com>
* Correct a name for get_external_nodes_by_internal_id function
Signed-off-by: Roman Kazantsev <roman.kazantsev@intel.com>
* Fix a description for get_external_nodes_by_internal_id function
Signed-off-by: Roman Kazantsev <roman.kazantsev@intel.com>
* Add logging and fix indentation
Signed-off-by: Roman Kazantsev <roman.kazantsev@intel.com>
* Use skip_nodes_by_condition to by-pass StopGradient nodes for tf.map_fn
Signed-off-by: Roman Kazantsev <roman.kazantsev@intel.com>
* Change logic for using multiple models in cc tests
* removed extra key
* moved multiple infer to main function
* moved multiple infer to main function
* change test_config.yml and work with this file
* change test_config.yml and work with this file
* removed extra key
* changed separator symbol
* removed extra param from output
* Rollback comments in test_config.yml
* removed extra key in yml config file, change logic to save .npz for all model seperate instead of common npz file, change logic in parser arg
* removed extra key in yml config file, change logic to save .npz for all model seperate instead of common npz file, change logic in parser arg
* changed save path for infer result, deleted extra param
* updated test_config.yml
* rollback old way to get bin_path
* changed work with save path for inference result
* add empty line in the end for config file
* rollback line order
* removed extra param allow_pickle=True in loading .npz file
* removed mkdir in run_infer
* uncomment resnet model
* added empty line
* changed save folder for cc result
* Add minor speedup changes.
* inline clip
* reduce clip calls
* more Interval::size - move to header
* terminate instead of throwing exception
* back to throw exception when element type was not found
* rename variable
* Release GIL in load_network
* release gil in infer, wait and get_idle_request_id
* release gil in read_network and IECore.__cinit__
* release GIL in properties
* Release GIL in infer_async
* Add test
* Fix test
* Fix test
* [MO] Add support to moc_frontend of ":" as delimiter for --input
Additions:
Changed default logic for 'Place::get_in(out)put_port' to return nullptr
Changed default logic for 'InputModel::get_place_by_tensor(operation)_name' to return nullptr
* Corrected comments in code
* Missing empty line
* Clang format fixes
* Fix review comments
* Updated test to verify review comments fixes
* Update unit tests after rebase
* Apply review comments
* Rename "pdpd" frontend to "paddle"
Also renamed mo_pdpd.py+main_pdpd.py to mo_paddle.py+main_paddle.py
Class names were not renamed
* Update package_BOM.txt
Win+Lin: add "clean build dir" step to ensure generated test models are taken from install
Windows fix: execute "pip show" on same drive where python is installed
Windows: execute tests with FE_TEST_MODELS env variable
* Revise spec
* Comparison backend test POC
* Split Comparison ops tests into separate files
* remove comparison.cpp, remove unused imports, replace for_each with range based for
* remove unnecessary ngraph:: prefixes
* Fix links in spec
* Add Less to trusted ops list
* Add missing ','
* Use builder in backend tests
* Remove old backend tests for less, equal
* Added Windows OS support to MemCheckTests
* Move system headers to cpp file
* Moved includes for windows to cpp file. Was rewrited function to get memory info
* Was rewrite functions for getting information about memory
* Moved implementation run_in_process to cpp file
* Fixed implementation of run_in_process
Use default linker for sanitizer builds
Compiler out of memory tracking variables in GPU tests.
This trigger recompilation without tracking. Disabling
tracking globally as not required option.
UBSan build is failing on maybe uninitialized variable.
Temporarily disable the check.
