Commit
This commit does not belong to any branch on this repository, and may belong to a fork outside of the repository.
* [IE][VPU]: Remove protocol checks for updating memType and watchdog flag (#3762) Remove protocol checks for updating memType and watchdog flag. This has been verified by Microsoft on their target platform with 2 ma2085 over PCIE. The target was able to run openVino sample with these changes. * Broken first inference time counter (#3848) * [IE CLDNN] Performance / accuracy fixes (#3729) - Added linear_onnx mode support into resample_opt kernel. - Fixed byxf layout check. - Added Resample + Eltwise fusing support - Update dequantize merge pass to work with eltwise instead of scale - Fixed uninitialized m_maxBatch value for query mode - Fixed missing AddPrimitiveToProfiler for DeformablePSRoiPooling - Fixed 0d gather - Added WA for Resample+Eltwise fusing Co-authored-by: Gleb Kazantaev <[email protected]> * MO dev guide refactoring (#3266) (#3595) * Release mo dev guide refactoring (#3266) * Updated MO extension guide * Minor change and adding svg images * Added additional information about operation extractors. Fixed links and markdown issues * Added missing file with information about Caffe Python layers and image for MO transformations dependencies graph * Added section with common graph transformations attributes and diagram with anchor transformations. Added list of available front phase transformations * Added description of front-phase transformations except the scope-defined and points defined. Removed legacy document and examples for such transformations. * Added sections about node name pattern defined front phase transformations. Copy-pasted the old one for the points defined front transformation * Added description of the rest of front transformations and and all middle and back phase transformations * Refactored Legacy_Mode_for_Caffe_Custom_Layers and updated the Customize_Model_Optimizer with information about extractors order * Added TOC for the MO Dev guide document and updated SVG images with PNG ones * Fixed broken link. Removed redundant image * Fixed broken links * Added information about attributes 'run_not_recursively', 'force_clean_up' and 'force_shape_inference' of the transformation * Code review comments * Added a section about `Port`s * Extended Ports description with examples * Added information about Connections * Updated MO README.md and removed a lot of redundant and misleading information * Updates to the Customize_Model_Optimizer.md * More updates to the Customize_Model_Optimizer.md * Final updates for the Customize_Model_Optimizer.md * Fixed some broken links * More fixed links * Refactored Custom Layers Guide: removed legacy and incorrect text, added up-to-date. * Draft implementation of the Custom layer guide example for the MO part * Fixed broken links using #. Change layer->operation in extensibility documents * Updated Custom operation guide with IE part * Fixed broken links and minor updates to the Custom Operations Guide * Updating links * Layer->Operation * Moved FFTOp implementation to the template extension * Update the CMake for template_extension to build the FFT op conditionally * Fixed template extension compilation * Fixed CMake for template extension * Fixed broken snippet * Added mri_demo script and updated documentation * One more compilation error fix * Added missing header for a demo file * Added reference to OpenCV * Fixed unit test for the template extension * Fixed typos in the template extension * Fixed compilation of template extension for case when ONNX importer is disabled Co-authored-by: Alexander Zhogov <[email protected]> * [BF16] Simulation mode was added to documentation (#3649) * [BF16] Simulation mode was added to documentation * Update Bfloat16Inference.md Co-authored-by: Anastasiya Ageeva <[email protected]> * Inconsistent inference results for hello_classification sample between Windows and Linux (44369) (#3849) * Fix image load issue * remove extra line * Attributes have different values in MO and NGraph IRs (#3793) * regionyolo do_softmax attribute * add serialization single layer tests for normalizel2 and reshape * add prelu sslt, change letter size in op name to align with MO * add shufflechanels sslt, add workaround to serialize the op with proper opset number * add broadcast sslt, change attribute string representations to lowercase * add pad sslt, change attribute string representations to lowercase * Unify sslt name prefixes * add prelu name translation for serialization * change expected type of regionyolo do_softmax attribute to bool * transform autobcast type attr to lowercase, add unit test, add special opset mapping in serialization * style fix * fix indentation * fix indentation 2 * Possibility of different opset assignment for different op versions * Update header dates in modified files * Match special opset to type_info_t instead of a string * Adjust the comment to match the code * Fix sanitizer build (#3869) * [ONNX Importer] Reduce amount of ONNX Importer public includes. (#3837) * Initial moving * ONNX Importer is private now - CMakeLists.txt * ONNX Importer is private now - Includes * Make some files visible * Style apply * Review fix * Public headers have a prefix now * Style * hide more headers * [IE][VPU]: Added MYRIAD_THROUGHPUT_STREAMS in default config (#3861) * [IE][VPU]: Fixed the calculation of timeout for x32 system (#3842) * [Python API] Small fixes in tests and change of format string to f-string (#3865) * Added -Wall for IE Core libraries (#3852) * doc files copyright (#3843) * doc files copyright * fix indentation * Enhancing Object Detection Sample SSD C Sample docs to cover the use of ie_network_reshape() for setting the batch size (#3875) * Allow FakeQuantize with output_low scalar to be transformed (#3812) * Allow FakeQuantize with output_low scalar to be transformed * add test case with scalar * Enable CNN2D tests for GNa Lib 2.1.0.1048 (#3529) Enable tests including rectangular kernel and multiple kernels Pad filters to 16B Fix style space after if before ( needed Fix PRETTY_FUNCTION double def Fix canMatchWith1AsyncThread Fix ifdefs for gna 2.0 Add and fix mock Simplify and fix condition for Rotate features Refine commnets in GNA CONV tests file Apply review, Refactor ConvolutionPrimitive Refine CNN enforce legacy Add debug print Move debug dump definitions Add new metric for GNA library version Add coments on FP32 * Add Clamp fusion transformation (#3756) * Add Clamp fusion transformation It fuses Maximum->Minimum subgraph to Clamp operator. Ticket: 44783 * address review comments * update year in headers * Adding docs for maacOS samples building (#3862) * Develop Bucketize Reference Implementation (#3693) * Bucketize: Revise op class and add type_prop unit tests * Bucketize: Develop reference implementation * Bucketize: Add unit tests * Bucketize: Add single layer test and cpu instantiation * Bucketize: Add unit test with empty buckets for INTERPRETER * Bucketize: Typo in buckets element type check * Bucketize: Add custom generated inputs in single layer test class * Bucketize: Use random_device to generate seed for data blob * Bucketize: Remove unsupported f64 precision * Bucketize: Add function description * Bucketize: Remove randomness of inputs generation by using static seed * Bucketize: Support different precisions for data and bucket inputs * Bucketize: Refactor type_prop tests and improve backend unit test coverage * Fixed warnings generation for ngraph API (#3864) * ONNX model editor - replacing input shapes (#3844) * Azure CI: Prepare for updating IB ver (#3085) * Add install_ib_console.bat * [ONNX Importer] move null_node to private scope (#3877) * Replaced size_t with int64_t (#3744) * Offline transformation API (#3408) * Added offline transformations library * Added python API for calling MOCTransformations * Added CF flag for MOC Transformations * Divided offline api to separate independent module * Update MOC pipeline to execute only fusions * Disable CF for PriorBox ops * Clean-up * Added python test * Removed transformation pipeline as it is not ready yet * Remove not related to this PR changes * Fixed build for dev package case; renamed to offline_transformations_api * Removed unrelated changes * Removed excess exports from cmake * Removed useless custom command from cmake * Remove deprecated methods usage from transformation library (#3881) * Remove deprecated methods usage from transformation library * graph_rewrite_callback -> matcher_pass_callback * Clean-up legacy library from deprecated methods usage * Update func tests * [IE][VPU]: changing condition in HW tiling (#3695) * Update MO extensions enabling/disabling mechanism (#3873) * Add id for NormalizeToNarmalizeL2 transformation * Update copyright year * Update extensions enabling/disabling mechanism * Remove copyright change * Copyright year * Update documentation * Revert missed year in copyright * Add MVN-6 related transformations (#3710) * Add MVN decomposition transformation * Add MVN-1 to MVN-6 transformation * Apply review feedback * Apply review feedback * Fix build * Fix if statement and add 5D tests * Apply review feedback * Apply review feedback * Apply feedback * Revert "Apply feedback" This reverts commit 039fefbff9590a718b1450ebac4417c2064e4103. * Apply review feedback * Apply review feedback * Fix build issue * Apply review feedback * Apply review feedback * Apply feedback * Proper cpplint target for object libraries (#3883) * Enable calculation of reference data without prior run of infer request (#3856) * Implement ExperimentalDetectronDetectionOutput and ExperimentalDetectronPriorGridGenerator operations as nGraph ops (#3374) * Commit. * Started to write nGraph operation ExperimentalDetectronDetectionOutput. Written draft of the header file. * Written draft of the cpp-file for nGraph operation ExperimentalDetectronDetectionOutput. * Small fix. * Added reading of ExperimentalDetectronDetectionOutput as nGraph operation. * Some fix. * Unregistered old shape infer function of the operation ExperimentalDetectronDetectionOutput. * Written the header file for the operation ExperimentalDetectronPriorGridGenerator. * Small refactoring. * Small fix. * Added set_output_size(3) into op::ExperimentalDetectronDetectionOutput::validate_and_infer_types(). * Added check for number of inputs of ExperimentalDetectronDetectionOutput. * Reverted some changes. * Changed IR for ExperimentalDetectronDetectionOutput serialization test. * Written cpp-file of nGraph operation ExperimentalDetectronPriorGridGenerator. * Small fix. * Some fixes. * Fixes in type and shape infer functions of the MO operation ExperimentalDetectronDetectionOutput. * Now ExperimentalDetectronPriorGridGenerator is readed as nGraph operation. * Fixed the infer function of the nGraph operation ExperimentalDetectronPriorGridGenerator. * Started to write tests for the shape infer function of the nGraph operation ExperimentalDetectronDetectionOutput. * Written the draft of the test for the shape infer function of the nGraph operation ExperimentalDetectronDetectionOutput. * Small fix. * Fixed ngraph/test/CMakeLists.txt. * Started to write tests for the shape infer function of the nGraph operation ExperimentalDetectronPriorGridGenerator. * Now the shape infer function of the nGraph operation ExperimentalDetectronPriorGridGenerator performs correctly case dynamic input shapes with static ranks. * Continued to write test for the nGraph operation ExperimentalDetectronPriorGridGenerator. * Small fixes. * Written tests for the shape infer function of the nGraph operation ExperimentalDetectronPriorGridGenerator (case when input shapes are partially dynamic). * Added test for reading ExperimentalDetectronDetectionOutput as an operation from opset6. * Some fixes. * Added some debug outputs. * Deleted inserted debug output. * Small fixes. * Small fix. * Small fix. * Small change. * Added comments to attributes of ExperimentalDetectronDetectionOutput. * Reverted changes. * Deleted shape infer for output port 3. * Small fixes. * Deleted redundant keyword 'virtual'. * Deleted redundant usings in header files of nGraph operations ExperimentalDetectronDetectionOutput and ExperimentalDetectronPriorGridGenerator. * Some fixes. * Small change. * Now GridGenerator::validate takes three args (input partial shapes). * Small fix. * Deleted some usings. * Small code style fix. * Reverted changes in validate_and_infer_types() and validate() of op::v6::ExperimentalDetectronPriorGridGenerator. * Added description of the class ExperimentalDetectronDetectionOutput. * Added some comments into the header file of the nGraph operation ExperimentalDetectronPriorGridGenerator. * Some fixes. * Added some comments to the class of the nGraph operation ExperimentalDetectronPriorGridGenerator. * Now the MO operation ExperimentalDetectronDetectionOutput has the attribute 'version' as 'opset6'. * Now the MO operation ExperimentalDetectronPriorGridGenerator has the attribute 'version' as 'opset6'. * Some fixes in the MO class ExperimentalDetectronDetectionOutput. * Fixes in the shape infer function of the nGraph operation ExperimentalDetectronPriorGridGenerator. * Renamed test XML model for ExperimentalDetectronDetectionOutput serialization tests. * Added validation of input shapes for the nGraph operation ExperimentalDetectronDetectionOutput. * Small fixes in the XML models for serialization testing of ExperimentalDetectronDetectionOutput. * Added tests of shape infer function of the nGraph operation ExperimentalDetectronDetectionOutput for the case when input shapes are partially dynamic. * Added tests of shape infer function of the nGraph operation ExperimentalDetectronDetectionOutput for the case when some input shapes have dynamic ranks. * Small fixes. * Small fix in the MO operation ExperimentalDetectronDetectionOutput shape infer function. * Fixes in op::v6::ExperimentalDetectronDetectionOutput::validate_and_infer_types(). * Code style fix. * Small refactoring. * Added NGRAPH_OP_SCOPE into ExperimentalDetectronDetectionOutput nGraph class. * Added NGRAPH_OP_SCOPE to the nGraph class ExperimentalDetectronPriorGridGenerator. * Small fixes. * Some refactoring. * Small fix. * Small fixes. * Reverted some changes in ExperimentalDetectronDetectionOutput::validate_and_infer_type(). * Now VPU reads the attribute class_agnostic_box_regression of ExperimentalDetectronDetectionOutput as Bool. * Now MO generates attribute 'class_agnostic_box_regression' of ExperimentalDetectronDetectionOutput only with values false or true. * Small fix. * Tabs were replaced by spaces in some XMLs. * Fixed copyrights. * Refactoring in op::v6::ExperimentalDetectronDetectionOutput::validate_and_infer_types(). * Refactoring in op::v6::ExperimentalDetectronPriorGridGenerator::validate_and_infer_types(). * Small fixes. * Started to write ExperimentalDetectronPriorGridGenerator shape infer tests for the case when dynamic input dimensions are intervals. * Deleted redundant 'return'. * Written tests for interval values of input shapes of op::v6::ExperimentalDetectronPriorGridGenerator. * Code style fix. * Code style fix. * Add support for ONNX Operator ReduceSum v13 and revise other Reduce operators (#3605) * Fixed -Wall warnings on ARM build (#3885) * ONNX tests mismatch error (#3836) * Deprecated IVariableState interface (#3884) * Improvements for subnormal floats zeroing in CPU plugin (#3797) * Added CC macro to transformations (#3795) * Added CC macro to transformations * Fixed typo * Added MATCHER_SCOPE * Fixed review comments * Try to remove MATCHER_CALLBACK_SCOPE * Fixed matcher name * Fixed MATCHER_SCOPE * Added documentation * Fixed typo * Fixed CC for linux * Fixed names * Fixed docs * Fixed typo * FIxed comments * Add more CC macros * [CPU] Runtime precision for execution graph (#3886) * [IE][VPU][DTS]: shrink mask support for StridedSlice and test (#3835) * [IE TESTS][CPU] Fusing tests added to the CPU specific single layer tests. (#3015) * Fix signed/unsigned comparison warnings (#3900) They are treated as error, which leads to build failure. Tested on Ubuntu 20.04, gcc 9.3.0. * [IE CLDNN] Changed weights layout used in the plugin (#3858) Before this patch constant with weights could be not detected if it wasn't directly connected to Conv/Deconv layer. Now weights always uses common data format (bfzyx) in the plugin which is converted into weights format later (goiyx, oiyx, etc), so weights sub-graph can now contain anything * Fix nGraph doxygen for master (#3899) * Changed style of some headers * Fixed shared buffer * Remove chrome_trace * Fixed comment * [IE CLDNN] Added missing pointer type case for blocked read (#3866) * [IE CLDNN] Change memory reset rules (#2909) * [IE CLDNN] Eltwise b_fs_yx_fsv16 mixed presicion support (#3734) * Visitor api ti serialization (#3777) * Add on_adapter(Function) for serialization. * Add port_map and back_edges serialization. * Add 2 unit tests for TI serialization. * Convert lambda expression into function pointer. * Add single layer test for tensor iterator. * Add limitation for file name length during serialization. * Add file name length limitation for Serialize(). * Add WA for LSTMCell v0 in serialize class, new test class for TI serialization with dynamic weights, add bin path to SerializationParams, replace call to ngfunction_2_irv10 with visitor.on_attribute(). * Remove hacks for TI from ngfunction_2_irv10(), validate buffers in port_map. * Changed year in new added test files. * Add check for version of LSTMv0 WA, add assert for model read from file. * Remove append_copy for xml Function, changed comparison for LSTMvo WA. * Update second WA for LSTMCell v0 with version check. * Remove find_child when searching for port_map and back_edges. * Fixed cmake 'message' for multiple arguments (#3901) * [nGraph][ONNX] Extend ONNX Importer for operation "GatherElements-6" (#3822) * [IE TESTS][CPU] I8 and U8 precisions was enabled in the reverse sequence single layer test. (#3722) * Change `json.loads` to `json.load` for `--db_metadata` (#3871) * Fixed import module name (#3906) * Set output blobs precision for IE tests (#3905) * Calling SetPrecission on cnn network outputs * added tests * get_output_name refactor * add missing test file * run tests on all backends (or disable if backend is not available) * fixed tests * fixed TestEngine * [CPU] ROIAlign: fixed misprint in input width value (#3853) * [IE][VPU]: Fix buffer size calculation bug (#3825) * [IE][VPU][Tests]: Support DTS for GatherElements (#3688) * Support DTS for GatherElements * Extract GatherBase to a common part * Introduce tests on inference * Introduce tests on function comparing * Disable failing tests * Added PythonAPI For LowLatency Transformation (#3910) * [IE][VPU][Tests]: Fix ROIPooling test (#3705) * fix initialization bug of spatial_scale in tests (affected input generating) * fix input generating for bilinear ROI Pooling * correct parameters for myriad tests: * myriad plugin does not support batch for this layer; * decrease threshold since myriad uses fp16 calculations * Azure CI: Add install (#3876) * Azure CI: Add install * Fix virtual inheritance for class PadLayerTest (#3912) * Implement ExperimentalDetectronROIFeatureExtractor operation as nGraph op (#3739) * Commit. * Written the header file of the nGraph operation ExperimentalDetectronROIFeatureExtractor. * Started to write cpp-file for the nGraph operation ExperimentalDetectronROIFeatureExtractor. * Deleted in_ports_count attribute for the MO operation ExperimentalDetectronROIFeatureExtractor. * Written validate_and_infer_type() method of ngraph::op::v6::ExperimentalDetectronROIFeatureExtractor. * Code style fixes. * Code style fixes. * Small fixes. * Code style fixes. * Now operation ExperimentalDetectronROIFeatureExtractor is read as nGraph operation ExperimentalDetectronROIFeatureExtractor. * Implemented op::v6::ExperimentalDetectronROIFeatureExtractor::clone_with_new_inputs(). * Added macro NGRAPH_OP_SCOPE to the cpp-file of the nGraph operation ExperimentalDetectronROIFeatureExtractor. * Fixes in some tests. * Code style fix. * Fixed yet another test for ExperimentalDetectronROIFeatureExtractor. * Added tests for reading ExperimentalDetectronROIFeatureExtractor as operation from opset6. * Added more test for reading ExperimentalDetectronROIFeatureExtractor as operation from opset6. * Started to write shape infer tests for the nGraph operation ExperimentalDetectronROIFeatureExtractor. * Corrected ngraph/test/CMakeLists.txt. * Small changes. * Code style fix. * Small fixes. * Added ctor of ExperimentalDetectronROIFeatureExtractor with NodeVector as argument. * Added setting the attribute in_ports_count when the MO operation ExperimentalDetectronROIFeatureExtractor is creating in the MO transformation ONNXMaskRCNNTransformation. * Added shape infer for the second output of the nGraph operation ExperimentalDetectronROIFeatureExtractor. * Written shape infer tests for nGraph operation ExperimentalDetectronROIFeatureExtractor (case when input shapes are partially dynamic). * Small fixes. * Code style fix. * Deleted redundant &expected_channels. * Code style fix. * Small refactoring. * Small fixes. * Small changes. * Small fixes. * Deleted attribute distribute_rois_between_levels of ExperimentalDetectronROIFeatureExtractoe. * Deleted attribute preserve_rois_order of ExperimentalDetectronROIFeatureExtractoe. * Deleted attribute image_id of ExperimentalDetectronROIFeatureExtractoe. * Now MO generates attribute 'aligned' of ExperimentalDetectronROIFeatureExtractor only with values 'true' or 'false'. * Small fix. * Fix in the conversion of the attribute 'aligned' of MO operation ExperimentalDetectronROIFeatureExtractor to string. * Tabs were replaced by spaces in some XMLs. * Tabs were replaced by spaces in ngraph_reshape_tests.cpp. * Fixed copyrights. * Applied small patch to IREngine from PR https://github.com/openvinotoolkit/openvino/pull/3814. * Tabs were replaced by spaces in cnn_ngraph_impl_tests.cpp. * op::v6::ExperimentalDetectronROIFeatureExtractor::validate_and_infer_types() was rewritten using operator & for channels. * Added tests for input shapes of op::v6::ExperimentalDetectronROIFeatureExtractor in the case when inputs shapes consist of intervals. * Fixes in test type_prop.detectron_roi_feature_extractor_intervals. * [IE CLDNN] Convolution b_fs_zyx_fsv16_imad tuning improvements (#3011) * Add ReluFakeQuantize transformation (#3811) * Add ReluFakeQuantize transformation * address review comments * replace constant with any_input * use MATCHER_SCOPE macro * Extend and fix input/output precisions support in functional tests (#3933) * Use actual blobs type to get nGraph element type, when generating inputs and calculating reference results. It will allow to run tests with `undefined` preset and use real type, returned from the device to generate and process input. It also fixes the case with several inputs with different type. * Extend `convertOutputPrecision` function to fully support conversions from/to fp16/bf16 types. The device might return blobs in that formats, so they need to be supported by the testing framework. * [LPT] StridedSlice Transformation (#3817) * [nGraph] evaluate_strided_slice: replace read_vec to host_tensor_2_vec * [LPT] StridedSliceTransformation * Develop ConvertLike Reference Implementation (#3857) * ConvertLike: Develop reference implementation * ConvertLike: Enable single layer tests for GPU plugin * ConvertLike: Enable bf16 precision for evaluate method * ConvertLike: Add unit tests * ConvertLike: Add dynamic shape test case * ConvertLike: Remove unnecessary ngraph namespace and using declaration for v1::ConvertLike * ConvertLike: Simplified reference::convert by using std::enable_if * [IE CLDNN] Kernel Selector improvements (#2998) * [IE TESTS] Fix passrate in report (#3904) * [IE TESTS] Fix passrate in report * add skip * update manifest (#3939) * [IE CLDNN] Convolution fsv16 improvements several fixes after code review (#3637) * Added SubGraphOp support in compare_function (#3943) * Add PadFusion transformation (#3785) * Add PadFusion transformation Ticket: 46482 * set pad explicit * fuse ifs * address review comments * fix signed to unsigned comparison warning * add MATCHER_SCOPE * Remove deprecated classes/methods usage from Legacy/Tests/VPUPlugin (#3907) * Fix legacy converter for Mul/Add/Sub ops * Updated VPU plugin to use pass_config;Updated tests to avoid legacy classes/methods * Updated VPU pipeline * rename time test config (#3923) * Update OV telemetry message for 2021.3 (#3926) * Update OV telemetry message for 2021.3 * Fixed missprint * [BUG]Add extra op clone to have default inputs/outputs set. (#3855) * Add extra op clone to have default inputs/outputs set. * Call `validate_and_infer_types` after clone for TensorIterator and Loop * Add gtest to check if default values works with dynamic shapes * Apply suggestions from PR. Co-authored-by: Patryk Elszkowski <[email protected]> * Don't add a new Result operation if output port is already connected to Result (#3934) * Fixed issue with run stateful network with several infer requests on MKLDNNPlugin (#3711) * Refactored VPU tests not to use old interfaces (#3888) * Refactored VPU tests not to use old interfaces * Added except of exceptions * Commented failing part of HDDL tests * [MO] Implement TensorFlow 2 While and Keras RNN support in MO (#3573) * [MO] Implement TensorFlow 2 While support in MO Signed-off-by: Roman Kazantsev <[email protected]> * Add extractors for both While and StatelessWhile and do minor changes Signed-off-by: Roman Kazantsev <[email protected]> * Improve update_body_graph function and manage graph names properly Signed-off-by: Roman Kazantsev <[email protected]> * Fix a map for original name of parameters from body and cond Signed-off-by: Roman Kazantsev <[email protected]> * Implement draft version of support of TF2 Keras RNN Signed-off-by: Roman Kazantsev <[email protected]> * Implement Keras LSTM and GRU support in MO Signed-off-by: Roman Kazantsev <[email protected]> * Improve code for Keras RNN support Signed-off-by: Roman Kazantsev <[email protected]> * Finalize implementation of TF2 Keras RNN support in MO Signed-off-by: Roman Kazantsev <[email protected]> * Apply the first part of the comments after review #1 Signed-off-by: Roman Kazantsev <[email protected]> * Avoid use of explicit values of port indices in the transformation Signed-off-by: Roman Kazantsev <[email protected]> * Finalize code after the first-round review Signed-off-by: Roman Kazantsev <[email protected]> * Apply comments after the second-round review Signed-off-by: Roman Kazantsev <[email protected]> * Implement ExperimentalDetectronTopKROIs and ExperimentalDetectronGenerateProposalsSingleImage operations as nGraph operations (#3680) * Commit. * Written the header file for the nGraph operation ExperimentalDetectronTopKROIs. * Written an implementation file of the nGraph operation ExperimentalDetectronTopKROIs. * Small fix. * Added the nGraph operation ExperimentalDetectronTopKROIs into the table of ops of opset6. * Written the header file for the nGraph operation ExperimentalDetectronGenerateProposalsSingleImage. * Code style fix. * Written cpp-file of the nGraph operation ExperimentalDetectronGenerateProposalsSingleImage. * Now the operation ExperimentalDetectronGenerateProposalsSingleImage is read as nGraph operation. * Code style fix. * Fix in ngraph/ops.hpp * Added NGRAPH_OP_SCOPE to the nGraph class ExperimentalDetectronGenerateProposalsSingleImage. * Added NGRAPH_OP_SCOPE to the nGraph class ExperimentalDetectronTopKROIs. * Code style fix. * Small fix. * Added NGraphReshapeTests of ExperimentalDetectronGenerateProposalsSingleImage when ExperimentalDetectronGenerateProposalsSingleImage is considered as opset6 operation. * Changed copyright year to 2021. * Deleted the method ExperimentalDetectronTopKROIs::set_max_rois. * Deleted redundant virtual. * Now ExperimentalDetectronTopKROIs::validate_and_infer_types() handles all cases when input 0 and input 1 have static/dynamic rank independently. * Code style fix. * Small fix. * Started to write shape infer tests for the nGraph operation ExperimentalDetectronTopKROIs. * Written shape infer tests for the nGraph operation ExperimentalDetectronTopKROIs. * Code style fix. * Added checks of input shapes into ExperimentalDetectronGenerateProposalsSingleImage::validate_and_infer_types(). Started to write tests for ExperimentalDetectronGenerateProposalsSingleImage::validate_and_infer_types(). * Small fix. * Fixes in ExperimentalDetectronGenerateProposalsSingleImage::validate_and_infer_types(). Written draft tests for ExperimentalDetectronGenerateProposalsSingleImage::validate_and_infer_types(). * Code style fix. * Fixes in reshape tests for ExperimentalDetectronGenerateProposalsSingleImage. * Added Doxygen documentation to the nGraph operation class ExperimentalDetectronGenerateProposalsSingleImage. * Deleted methods validate_scores_shape and validate_deltas_shape of op::v6::ExperimentalDetectronGenerateProposalsSingleImage. * Deleted methods validate_input_rois_shape and validate_rois_probs_shape of op::v6::ExperimentalDetectronTopKROIs. * Added class descriftion for nGraph operations ExperimentalDetectronTopKROIs and ExperimentalDetectronGenerateProposalsSingleImage. * Revise abs (#3931) * remove type_prop test file for abs operator * add abs operator to unary_ops * remove abs type_prop from CMakeList * Fixed CVS-47220 (#3958) * Add MVN-6 reference implementation and tests (#3896) * Add MVN-6 reference implementation and tests * Return old version reference * Apply feedback * Fix build * Remove ops from Layer Creator/ Node Converter - part 7 (#3961) * remove result op from layer creator * remove squareddifference op from layer creator * remove regionyolo op from layer creator * fix indentation * [BUG] Serialize loses runtime info (#3903) * rt_info serialization for ngraph::Node * add test for it info serialization * try to fix centos build Co-authored-by: Patryk Elszkowski <[email protected]> * Cleanup in ngraph_test_utils.hpp/cpp (#3959) Co-authored-by: Patryk Elszkowski <[email protected]> * Added export / import for Template and Hetero plugins (#3940) * Added export / import for Template and Hetero plugins * Added WA for Apple RTTI * Maxpool fix bug (#3718) * style-apply * Update spec * Remove maxpool back_prop method * style-apply * Revise reduce mean (#3786) * Update spec * create type_prop tests * add reduce_mean type_prop tests to CMakeList * Update spec * fix typo * Add dynamic type_prop tests * style fix * Visitor api loop deserialization (#3894) * Add on_adpater() implementation for special body parts. * Remove NodeConverter and LayerCreator for Loop. Add WA for different number of inputs during Loop init by constructor and visit_attributes(). * Format files. * Implement use case external_port_id=-1 for output port_map,change API for map_type_in_function. * Replace GetStrAttr() with GetInt64Attr(). * Correct WA for input_offset when using visitorAPI. It shall search all input descriptions for duplicated indexes. * Apply proper file format. * Throw exception when input_offset < 0. * Add more detailed description for input_offset WA. * Add missing types in convertIE2nGraphPrc() test util function. (#3957) * Unused variables (#3963) * Added -Wused-variable flag * Fixes for clang compiler * Removed wrong -Wno-error from protobuf compilation * More fixes * delete unwanted doc script (#3960) * ConcatTransformation naming fix (#3965) * concat naming fix * [LPT] concat with child and output plugin tests * Python API For compare_functions (#3938) * Added python API for compare_functions * Fixed compare_funcion constant comparision, graph traversal * Add tests for python API functions * Move CompareNetworks to separate python module * Update python API tests * Added dev package support * ENABLE_TESTS * Update constant comparator * Fix merge conflict * Imironov/ref ngraph ctc gready decoder (#3867) * Add ctc gready decoder sec len op to ngraph * Remove some comments * Add second constructor * Fix code style * Fix code style * Add unit tests * Add tests to cmake * Fix according to review * Fix code style * fix * Change input layoyt * Fix code style * Add unit tests * Add 3 input tensor check * Update shell impl * Fix code style * Fix code style * Add doxy gen * Fix code style * Update doxigen * Update constructor description * Fix code style * Refactoring code * fix code style * Optimize op constructor * Add macros. Optimize code for validate_and_infer_types * Refactoring code * Fix code style * Fix code style * Fix check blanck_index shape * Fix code style * Add ref impl * Fix unit test for dynemic case * Fix code style * Fix copyryting * reverse changes * Update copyrite * Add ref implemintation * rollback * Fix code style * Fix code style * Fix * Add unit tests * Refactoring ref impl * Refactoring code style * Fix code style * Fix code style * fix unit tests * Refactoring code * Refactoring code * Fix code style * Refactoring unit tests * Fix style * Fix style * Missing attr seriazliation (#3920) * add override method for int since attribute keep_top_k from detection_output requires it * remove if statement to prevent gtest tests duplicate names for avg_pool * add single layer tests for seriazliation for AvgPool, PriorBoxClustered and DetectionOutput operators * add apropiate styling of the code * [IE CLDNN] Disabled v3 -> v1 conversion for Broadcast (#3991) * [IE CLDNN] Disabled eltwise fusion to const node when second input is in data flow (#3993) * Remove ops from Layer Creator/ Node Converter - part 8 (#3979) * remove equal op from layer creator * remove greaterequal op from layer creator * remove lstmcell op from layer creator * remove psroipooling op from layer creator * add missing newline * alignment * Demo scripts improvements. (#3954) * Demo script improvements. - Detect Visual Studio version installed into not-default location - Fix change directory for a case VS and OpenVINO resideds on different disks - Align indents * fix indents * Pre-deprecation of ICNNNetwork (#3887) * Deprecated ICNNNetwork * MKLDNN plugin: partially * MYRIAD plugin: partially * Fixed Myriad Plugin * Improved GNA; fixed MKLDNN * Fixed tests * Fixed GNA * Fixed unit tests linkage * Removed ICNNNetwork from tests * Removed obsolete tests * [IE TESTS] Remove random weights generation of blobs (#3998) * Revise topk (#3819) * Add visit_attribute and node validation check * add type_prop test for default values * style-apply * Update node validation check for index_element_type * Update type_prop test for default index_element_type * Add index_element_type attribute to TopK_1 spec * Fix restoring constant ops with old numbering (#3951) * Add check to correct restoring constant ops with old numbering * Resolve comments * Update comment * [IE TESTS] Remove TEST_P(Range... from lib with shared_classes (#3999) * [nGraph][ONNX] WA for currently unsupported precisions (#3964) * [nGraph] Fix bound check for reference GatherElements (#3981) * fix bound check for reference GatherElements * apply review comments * Remove layerCreator for logical ops. (#3970) * Remove layerCreator for logical ops. * Remove visit_attributes() for LogicalOr op. * [LPT] Disabling failed on GPU LPT StridedSlice plugin tests (#4001) * [CMake] Fixes for TBB tmp location (#3997) * fixes for TBB tmp location: - DL_SDK_TEMP path is not normalized, that leads to paths check mismatch in CMake conditions - TBB is not downloaded again in a case tmp location is cleaned up and build restarted (TBB_DIR and TBBROOT are cache variables) * use reset_deps_cache & update_deps_cache for TBB_DIR var. * single reset_deps_cache call * [IE Common][VPU]: Fix small input size inference for dynamic model (#3847) * eliminate Unsqueeze+Gather pair, when Gather gathers data by 1 dimension which was previously added by Unsqueeze which is actually doing nothing. * calculate K only once in StaticShapeTopK. The problem happens when we have ShapeOf->Concat->ReduceMin subgraph for K evaluation. If we have a pretty small input size, the value that we received from ShapeOf may be less than one that it is concatenated with (e.g. ShapeOf 283 vs const 300), so ReduceMin returns 283. After ShapeOf elimination we don't have a chance to propagate 283 so we get 300 as a result and shape inference fail then. There are no problems with bigger input sizes just because ShapeOf always propagates value >300 and there are no such mismatch. * Move ClampFusion before HSwishFusion and HSigmoidFusion (#3994) HSwishFusion and HSigmoidFusion use Clamp in their patterns, so that change allows for even more fusions. * [CPU] GatherElements implementation. (#3860) * Add Loop serialization, SLT and regular test. (#3980) * Add Loop serialization, SLT and regular test. * Remove loop test from SerializationTensorIteratorTest, add bin for test loop xml. * Remove metadata section from loop xml file. * Remove m_num_iterations initialization, it is done during validate_and_infer_types(). * Bump tox from 3.20.1 to 3.21.2 in /ngraph/python (#4003) * Update ONNX build dependency to v 1.8 (#3716) * [IE COMMON] Fixes for EliminateUnsqueezeGather transformation (#4013) * Add a target to fetch and build Intel SEAPI (#3915) * [GNA] Fix ParseBlobName and message for output layer names (#3527) * Remove Fake Quantize OP decomposition (#3506) * Remove Fake Quantize OP decomposition * Fix FQ OP inheritance * [CPU] Plugin migration on oneDNN (v1.6) (#3725) * Add support for nonconstant optional NMS-5 inputs (#3640) * [IE CLDNN] StridedSliceTransformation removed from GPU plugin (#4016) * [dependencies.cmake] Add license to tbb archive (#4018) * Generic LoadTime Optimizations (#4011) * Updated container passes to return false to avoid excess function validation * Added support for nested GraphRewrite registration * Updated passes to use MatcherPass; Reorganized CommonOptimizations pipeline * Disable node validation when graph is not modified * Enable Bersquad-10 in ONNX CI (#3889) * [Scripts] setupvars.bat: Added logic for passing '-pyver' option (#4026) * setupvars.bat: Added logic for passing '-pyver' option as we already have in Linux* setupvars * setupvars.bat: Fixed python_version name in echo * [GNA] Fix import model with header version 2.1 (#4023) [GNA] Fix import model with header version 2.1 Added fix version import Added template test Added test for backword compatibility added test * [GNA] Convolution without --disable_nhwc_to_nchw option for TF models. (#3918) * Fixed compilation with ENABLE_V7_SERIALIZE (#4037) * [LPT] Handle empty dequantization in MultiplyToGroupConvolution (#3818) Add const * [LPT] Add NormalizeDequantization function in NetworkHelper (#3458) * [LPT] Add NormalizeDequantization function in NetworkHelper. * [LPT] Handling subtract constant index in makeDequantization * [LPT] Extend Add and Multiply transformations with normalizeDequantization. * [LPT] Add/Subtract simplify normalizeDequantization call * [LPT] normalizeDequantization: usage replace_node instead of copy assignment * [LPT] Update lpt paths * [LPT] normalizeDequantization completion + refactoring Co-authored-by: Aleksandr Pertovsky <[email protected]> * [CPU] PSROIPooling node enhancements (#3851) - bf support for PSROIPooling - nhwc, blocking formats support - code refactor & performance improvements - cpu specific tests * Updated readme.md (#4052) * Add conditional compilation tests (#3996) * Added copy tools dir for all OS (#4007) * Fixed compilation of ngraph python on some compilers (#4015) * Fixed compilation of ngraph python on some compilers * Fixed ONNX importer dependencies compilation for gcc 5.4.0 and 5.5.0 * Removed obsolete ie_profiling.hpp (#4043) * Refactor install_openvino_dependencies script: extra options and cleanup (#3868) * Refactor install_openvino_dependencies script: extra options and cleanup * install_dependencies: added more python tools * install_openvino_dependencies: extra OS checks Verify consistency for future edits * install_openvino_dependencies: clarify messages * Proposal test uses special run() method to check exception throwing (#4062) * proposal test uses special run() method to check exception throwing * validate() removed from run() * Introduce the Broker API to map original framework names to OV (#3800) * Added tests * Fixed tests * Added tests to check addOutput method * Added support of port names in the IR * Update copyrights * Deprecate tensor name * Fixed comments * Enabled functional tests for GPU, GNA and Myriad * Fixed get_tensor().get_names() * Added unit test to check tensor names * Fixed code style * Skip add output test for GNA * Added serialization support * Added PythonAPI * Fixed tests * Fixed tests * Fixed typo * Try to disable GNA test * Fixed tests * Removed unused variables * Fixed tests * Update documentation * Fixed comment * -no-unused-XXX options added for selective build mode (#3702) * [CPU] Disabled input zero point fusing into fp32 Convolution (#4056) * Update operation attributes (#3814) * Allign attribute values in spec * Fix wrong attribute name in spec * Add `get_boolean_attr` function * Add get_type function * Update conv attrs * Update copyright year * Add missed attrs, update copyright year * Fix year in copyright * Update ir parser for RegionYolo layer * Remove wrong changes for BinaryConvolution * Remove get_type function as it no more needed * Update check for reduce ops * Fix error in reduce attrs * Update ir_engine to work with bool attrs * Update DetectionOutput operation * Update PSROIPooling * remove redundant attrs from spec * Update get_boolean_attr function * Update Reduce operations * Update DetectionOutput specification * Update specification for missed attrs * Apply comments * Fixconst renumbering logic * Fix typo * Change default value to fix broken shape inference * Add additional asserts * Add comment * model-optimizer/mo/utils/ir_reader/layer_to_class.py * Sort imports * Sort imports * Update year in copyright * Update const * Remove changes from const restoring * Rename function * remove unnecessary changes * model-optimizer/mo/front/extractor_test.py * Fix year in copyright * Add soft_get * Fix exclude-pad attribute name for AvgPool operation * Update exclude_pad attribute values * Remove useless comment * Update examples in specification * Remove file added by mistake * Resolve comments * Resolve comments * Add return value * Allign global_pool attribute * [compare_function] compare ops attributes (#3966) * [compare_function] compare ops attributes value by value * Storage cleanup * Add comparison for: - SubGraphOpInputDescription - SubGraphOpOutputDescription - SpecialBodyPorts * cleanup * Report error on unhandled types * Change comparison of floating-point to general approach Co-authored-by: Patryk Elszkowski <[email protected]> * Suppressing warning about unused variables for selective build of MKLDNN plugin. (#4039) * [CPU] ROIPooling with 1x1 pooled shape in bilinear mode fixed (#4020) * Added support for the MxNet op take (#4071) * Design test config and integrate in CC tests (#4051) * Prevent targets installation for 3rd party libs (mkl-dnn) (#4096) * [Python API] Support of FP16 blobs (#3893) * [Python API] Support of FP16 blobs * test_Blob refactoring * support fp16 for exec_net.infer method * add precisions Co-authored-by: anastasia.kuporosova <[email protected]> * added log extractor for tf (#4090) * Re-implement caffe old-style extractors with extractor extensions (#3675) * move crop extractor * Add concat_ext.py * Add roipooling_ext.py * Add roipooling_ext * Add scale extractor * Add scale extractor * Add bn_ext.py and dropout_ext.py * Add bn_ext.py and dropout_ext.py * Add bn_ext.py and dropout_ext.py * Fix bn.ext.py * Sort fix * Fix bn_test.py * rename to batchnorm_ext * Add bn_ext * Fix batchnorm_ext.py * small fix * Small fix * Add MVN-6 op to ONNX importer (#4012) * docs copy code button (#4017) * copy code button * copy code button updates * [IE][VPU]: Fixes Extract Dynamic Batch (#3978) LCA (Least Common Ancestor) search procedure must take sub-graph without external connections to be able to count depths of nodes. Previously, just 2 steps of removing external connections were executed (1 time for top sub-graph and 1 time for bottom one). In case if originally top sub-graph had no external connections, but bottom one had, after removing external nodes from bottom sub-graph, some of the nodes from top sub-graph could became external. In order to prevent that, removing external connections must always be a loop until no external connections found in both top and bottom sub-graphs. Signed-off-by: Gladilov, Gleb <[email protected]> * [CPU] Interpolate node: 5d support for onnx_linear mode (#3471) * Azure CI: Disable nGraph Mac tests IE_CPU/GRUSequenceOp.onnx_model_gru* * [DOC] ShapeInference.md update. slyalin comments (#3355) (#4104) * [DOC] ShapeInference.md update. slyalin comments * Apply suggestions from code review Co-authored-by: Alina Alborova <[email protected]> * Apply suggestions from code review Co-authored-by: Alina Alborova <[email protected]> * Update docs/IE_DG/ShapeInference.md Co-authored-by: Alina Alborova <[email protected]> Co-authored-by: Alina Alborova <[email protected]> * fix comments ngraph api - master (#3519) * fix comments ngraph api * remove whitespace * fixes Co-authored-by: Nikolay Tyukaev <[email protected]> * Update ONNX dependency to v 1.8.1 (#4114) * Update copyright Co-authored-by: Krishna Prabhakaran <[email protected]> Co-authored-by: Vladislav Volkov <[email protected]> Co-authored-by: Vladimir Paramuzov <[email protected]> Co-authored-by: Gleb Kazantaev <[email protected]> Co-authored-by: Evgeny Lazarev <[email protected]> Co-authored-by: Alexander Zhogov <[email protected]> Co-authored-by: Alexey Varyzgin <[email protected]> Co-authored-by: Anastasiya Ageeva <[email protected]> Co-authored-by: Sergey Lyubimtsev <[email protected]> Co-authored-by: Bartosz Lesniewski <[email protected]> Co-authored-by: Andrey Somsikov <[email protected]> Co-authored-by: Tomasz Socha <[email protected]> Co-authored-by: Nikita Kudriavtsev <[email protected]> Co-authored-by: Anastasia Kuporosova <[email protected]> Co-authored-by: Ilya Lavrenov <[email protected]> Co-authored-by: Nikolay Tyukaev <[email protected]> Co-authored-by: Maksim Makridin <[email protected]> Co-authored-by: Mateusz Tabaka <[email protected]> Co-authored-by: Krzysztof Bruniecki <[email protected]> Co-authored-by: Gabriele Galiero Casay <[email protected]> Co-authored-by: Tomasz Dołbniak <[email protected]> Co-authored-by: Liubov Batanina <[email protected]> Co-authored-by: Gleb Kazantaev <[email protected]> Co-authored-by: Aleksandr Korolev <[email protected]> Co-authored-by: Anton Chetverikov <[email protected]> Co-authored-by: Maxim Vafin <[email protected]> Co-authored-by: Alexander Perepelkin <[email protected]> Co-authored-by: Vladimir Gavrilov <[email protected]> Co-authored-by: Bartosz Sledz <[email protected]> Co-authored-by: Mateusz Bencer <[email protected]> Co-authored-by: Ilya Churaev <[email protected]> Co-authored-by: Gorokhov Dmitriy <[email protected]> Co-authored-by: Maksim Kutakov <[email protected]> Co-authored-by: Vladislav Vinogradov <[email protected]> Co-authored-by: Sergey Shlyapnikov <[email protected]> Co-authored-by: Szymon Durawa <[email protected]> Co-authored-by: Tomasz Jankowski <[email protected]> Co-authored-by: Vitaliy Urusovskij <[email protected]> Co-authored-by: Yury Gaydaychuk <[email protected]> Co-authored-by: Andrey Sokolov <[email protected]> Co-authored-by: Andrew Bakalin <[email protected]> Co-authored-by: Ilya Znamenskiy <[email protected]> Co-authored-by: Vladislav Golubev <[email protected]> Co-authored-by: Irina Efode <[email protected]> Co-authored-by: Victor Kuznetsov <[email protected]> Co-authored-by: Anastasia Kazantaeva <[email protected]> Co-authored-by: Patryk Elszkowski <[email protected]> Co-authored-by: Patryk Elszkowski <[email protected]> Co-authored-by: Svetlana Dolinina <[email protected]> Co-authored-by: Roman Kazantsev <[email protected]> Co-authored-by: Piotr Szmelczynski <[email protected]> Co-authored-by: Jozef Daniecki <[email protected]> Co-authored-by: iliya mironov <[email protected]> Co-authored-by: Bartek Szmelczynski <[email protected]> Co-authored-by: Jan Iwaszkiewicz <[email protected]> Co-authored-by: Pavel Esir <[email protected]> Co-authored-by: Edward Shogulin <[email protected]> Co-authored-by: Nikolay Shchegolev <[email protected]> Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com> Co-authored-by: Michał Karzyński <[email protected]> Co-authored-by: Andrey Dmitriev <[email protected]> Co-authored-by: Mikhail Treskin <[email protected]> Co-authored-by: Alexey Suhov <[email protected]> Co-authored-by: Artyom Anokhov <[email protected]> Co-authored-by: Elizaveta Lobanova <[email protected]> Co-authored-by: Aleksandr Pertovsky <[email protected]> Co-authored-by: Anton Romanov <[email protected]> Co-authored-by: Maksim Shabunin <[email protected]> Co-authored-by: anastasia.kuporosova <[email protected]> Co-authored-by: Anna Likholat <[email protected]> Co-authored-by: Eugeny Volosenkov <[email protected]> Co-authored-by: Ewa Tusień <[email protected]> Co-authored-by: Gladilov, Gleb <[email protected]> Co-authored-by: Chenhu Wang <[email protected]> Co-authored-by: Evgenya Stepyreva <[email protected]> Co-authored-by: Alina Alborova <[email protected]> Co-authored-by: Nikolay Tyukaev <[email protected]> Co-authored-by: Yanglei Zou <[email protected]>
- Loading branch information
79 people
authored
Feb 3, 2021
1 parent
2414a6d
commit 2a82d33