review.tizen.org Git - platform/upstream/dldt.git/commit

author	Evgeny Lazarev <evgeny.lazarev@intel.com>
	Mon, 17 Aug 2020 13:32:53 +0000 (16:32 +0300)
committer	GitHub <noreply@github.com>
	Mon, 17 Aug 2020 13:32:53 +0000 (16:32 +0300)
commit	125a4624009674ca4d84bf68078d48ba97228000
tree	0b907c88fa29f99558c71f4ea4525776fbd24194	tree \| snapshot
parent	7c9815b4c12d80eb60bf4928297c0cadd67dafe4	commit \| diff

Enable ReduceL1 and ReduceL2 operations (#1799)

* 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

docs/MO_DG/prepare_model/Supported_Frameworks_Layers.md		diff \| blob \| history
docs/ops/opset4.md		diff \| blob \| history
docs/ops/reduction/ReduceL1_4.md	[moved from docs/ops/reduction/ReduceLp_4.md with 76% similarity]	diff \| blob \| history
docs/ops/reduction/ReduceL2_4.md	[new file with mode: 0644]	blob
inference-engine/src/cldnn_engine/cldnn_engine.cpp		diff \| blob \| history
inference-engine/src/legacy_api/src/convert_function_to_cnn_network.cpp		diff \| blob \| history
inference-engine/src/legacy_api/src/ie_cnn_layer_builder_ngraph.cpp		diff \| blob \| history
inference-engine/src/mkldnn_plugin/mkldnn_plugin.cpp		diff \| blob \| history
inference-engine/src/readers/ir_reader/ie_ir_parser.cpp		diff \| blob \| history
inference-engine/src/transformations/include/transformations/reduce_l1_decomposition.hpp	[new file with mode: 0644]	blob
inference-engine/src/transformations/include/transformations/reduce_l2_decomposition.hpp	[new file with mode: 0644]	blob
inference-engine/src/transformations/src/transformations/convert_opset1_to_legacy/convert_opset1_to_legacy.cpp		diff \| blob \| history
inference-engine/src/transformations/src/transformations/reduce_l1_decomposition.cpp	[new file with mode: 0644]	blob
inference-engine/src/transformations/src/transformations/reduce_l2_decomposition.cpp	[new file with mode: 0644]	blob
inference-engine/tests/functional/inference_engine/transformations/reduce_l1_decomposition_test.cpp	[new file with mode: 0644]	blob
inference-engine/tests/functional/inference_engine/transformations/reduce_l2_decomposition_test.cpp	[new file with mode: 0644]	blob
model-optimizer/automation/package_BOM.txt		diff \| blob \| history
model-optimizer/extensions/back/ReduceMerge.py	[moved from model-optimizer/extensions/back/ReduceToPooling.py with 100% similarity]	blob \| history
model-optimizer/extensions/back/TransposeReduceFusing.py		diff \| blob \| history
model-optimizer/extensions/front/ReduceL2Decomposition.py	[deleted file]	blob \| history
model-optimizer/extensions/front/ReduceL2Decomposition_test.py	[deleted file]	blob \| history
model-optimizer/extensions/front/onnx/reduce_ext.py	[new file with mode: 0644]	blob
model-optimizer/extensions/front/onnx/reduce_l2_ext.py	[deleted file]	blob \| history
model-optimizer/extensions/front/onnx/reduce_max_ext.py	[deleted file]	blob \| history
model-optimizer/extensions/front/onnx/reduce_mean_ext.py	[deleted file]	blob \| history
model-optimizer/extensions/front/onnx/reduce_min_ext.py	[deleted file]	blob \| history
model-optimizer/extensions/front/onnx/reduce_prod_ext.py	[deleted file]	blob \| history
model-optimizer/extensions/front/onnx/reduce_sum_ext.py	[deleted file]	blob \| history
model-optimizer/extensions/front/reduce_axis_normalizer.py		diff \| blob \| history
model-optimizer/extensions/front/tf/reduce_ext.py		diff \| blob \| history
model-optimizer/extensions/ops/ReduceOps.py		diff \| blob \| history
model-optimizer/extensions/ops/ReduceOps_test.py		diff \| blob \| history
ngraph/core/include/ngraph/op/reduce_l1.hpp	[new file with mode: 0644]	blob
ngraph/core/include/ngraph/op/reduce_l2.hpp	[new file with mode: 0644]	blob
ngraph/core/include/ngraph/ops.hpp		diff \| blob \| history
ngraph/core/include/ngraph/opsets/opset4_tbl.hpp		diff \| blob \| history
ngraph/core/include/ngraph/runtime/reference/any.hpp		diff \| blob \| history
ngraph/core/include/ngraph/runtime/reference/autobroadcast_binop.hpp		diff \| blob \| history
ngraph/core/include/ngraph/runtime/reference/broadcast.hpp		diff \| blob \| history
ngraph/core/include/ngraph/runtime/reference/logical_reduction.hpp		diff \| blob \| history
ngraph/core/include/ngraph/runtime/reference/max.hpp		diff \| blob \| history
ngraph/core/include/ngraph/runtime/reference/mean.hpp		diff \| blob \| history
ngraph/core/include/ngraph/runtime/reference/min.hpp		diff \| blob \| history
ngraph/core/include/ngraph/runtime/reference/product.hpp		diff \| blob \| history
ngraph/core/include/ngraph/runtime/reference/reduce_l1.hpp	[new file with mode: 0644]	blob
ngraph/core/include/ngraph/runtime/reference/reduce_l2.hpp	[new file with mode: 0644]	blob
ngraph/core/include/ngraph/runtime/reference/softmax.hpp		diff \| blob \| history
ngraph/core/include/ngraph/runtime/reference/sum.hpp		diff \| blob \| history
ngraph/core/include/ngraph/shape_util.hpp		diff \| blob \| history
ngraph/core/src/op/max.cpp		diff \| blob \| history
ngraph/core/src/op/min.cpp		diff \| blob \| history
ngraph/core/src/op/product.cpp		diff \| blob \| history
ngraph/core/src/op/reduce_l1.cpp	[new file with mode: 0644]	blob
ngraph/core/src/op/reduce_l2.cpp	[new file with mode: 0644]	blob
ngraph/core/src/op/reduce_logical_and.cpp		diff \| blob \| history
ngraph/core/src/op/reduce_logical_or.cpp		diff \| blob \| history
ngraph/core/src/op/reduce_mean.cpp		diff \| blob \| history
ngraph/core/src/op/reduce_prod.cpp		diff \| blob \| history
ngraph/core/src/op/reduce_sum.cpp		diff \| blob \| history
ngraph/core/src/op/sum.cpp		diff \| blob \| history
ngraph/core/src/pass/constant_folding_arithmetic_reduction.cpp		diff \| blob \| history
ngraph/core/src/pass/constant_folding_logical_reduction.cpp		diff \| blob \| history
ngraph/core/src/shape_util.cpp		diff \| blob \| history
ngraph/python/src/ngraph/__init__.py		diff \| blob \| history
ngraph/python/src/ngraph/opset4/__init__.py		diff \| blob \| history
ngraph/python/src/ngraph/opset4/ops.py		diff \| blob \| history
ngraph/test/CMakeLists.txt		diff \| blob \| history
ngraph/test/op_eval/reduce_l1.cpp	[new file with mode: 0644]	blob
ngraph/test/op_eval/reduce_l2.cpp	[new file with mode: 0644]	blob
ngraph/test/partial_shape.cpp		diff \| blob \| history
ngraph/test/runtime/interpreter/int_executable.hpp		diff \| blob \| history
ngraph/test/type_prop/reduce_l1.cpp	[new file with mode: 0644]	blob
ngraph/test/type_prop/reduce_l2.cpp	[new file with mode: 0644]	blob