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

projects / platform / upstream / dldt.git / commit

author	Edward Shogulin <edward.shogulin@intel.com>
	Fri, 6 Nov 2020 13:15:27 +0000 (16:15 +0300)
committer	GitHub <noreply@github.com>
	Fri, 6 Nov 2020 13:15:27 +0000 (16:15 +0300)
commit	0f00e7f7031f8ed7399030452205cf161d0e855c
tree	6767c4eebaf795f478f5d8800b760d4c20131f84	tree \| snapshot
parent	1c3208ffe0888ee720ba21bfe80d3ed3a84f2796	commit \| diff

[LPT] integration branch: Reshape fix, Concat generalization, runtime info usage extending (#2930)

* [LPT] Concat transformation generalization

* [LPT] Reshape transformation fix

* [LPT] Legacy callback fix

* [LPT] * added rt_info propagation
* functional tests: added rt_info
* functional tests: added MoveDequatnizationAfter tests

Co-authored-by: Vladislav Golubev <vladislav.golubev@intel.com>

36 files changed:

inference-engine/src/low_precision_transformations/include/low_precision/network_helper.hpp		diff \| blob \| history
inference-engine/src/low_precision_transformations/src/common/add.cpp		diff \| blob \| history
inference-engine/src/low_precision_transformations/src/common/concat.cpp		diff \| blob \| history
inference-engine/src/low_precision_transformations/src/common/convolution.cpp		diff \| blob \| history
inference-engine/src/low_precision_transformations/src/common/fake_quantize.cpp		diff \| blob \| history
inference-engine/src/low_precision_transformations/src/common/fuse_convert.cpp		diff \| blob \| history
inference-engine/src/low_precision_transformations/src/common/mat_mul.cpp		diff \| blob \| history
inference-engine/src/low_precision_transformations/src/common/mvn.cpp		diff \| blob \| history
inference-engine/src/low_precision_transformations/src/common/network_helper.cpp		diff \| blob \| history
inference-engine/src/low_precision_transformations/src/common/normalize_l2.cpp		diff \| blob \| history
inference-engine/src/low_precision_transformations/src/common/reshape.cpp		diff \| blob \| history
inference-engine/src/mkldnn_plugin/mkldnn_plugin.cpp		diff \| blob \| history
inference-engine/tests/functional/inference_engine/lp_transformations/concat_transformation.cpp		diff \| blob \| history
inference-engine/tests/functional/inference_engine/lp_transformations/mat_mul_with_constant_transformation.cpp		diff \| blob \| history
inference-engine/tests/functional/inference_engine/lp_transformations/max_pool_transformation.cpp		diff \| blob \| history
inference-engine/tests/functional/inference_engine/lp_transformations/move_dequantization_after_transformation.cpp	[new file with mode: 0644]	blob
inference-engine/tests/functional/inference_engine/lp_transformations/normalize_l2_transformation.cpp		diff \| blob \| history
inference-engine/tests/functional/inference_engine/lp_transformations/relu_transformation.cpp		diff \| blob \| history
inference-engine/tests/functional/inference_engine/lp_transformations/reshape_transformation.cpp		diff \| blob \| history
inference-engine/tests/ngraph_functions/include/ngraph_functions/low_precision_transformations/common/builders.hpp		diff \| blob \| history
inference-engine/tests/ngraph_functions/include/ngraph_functions/low_precision_transformations/common/fake_quantize_on_data.hpp		diff \| blob \| history
inference-engine/tests/ngraph_functions/include/ngraph_functions/low_precision_transformations/concat_function.hpp		diff \| blob \| history
inference-engine/tests/ngraph_functions/include/ngraph_functions/low_precision_transformations/move_dequantization_after_function.hpp	[new file with mode: 0644]	blob
inference-engine/tests/ngraph_functions/src/low_precision_transformations/add_function.cpp		diff \| blob \| history
inference-engine/tests/ngraph_functions/src/low_precision_transformations/common/builders.cpp		diff \| blob \| history
inference-engine/tests/ngraph_functions/src/low_precision_transformations/concat_function.cpp		diff \| blob \| history
inference-engine/tests/ngraph_functions/src/low_precision_transformations/convert_mul_or_add_finally_with_dequantization_function.cpp		diff \| blob \| history
inference-engine/tests/ngraph_functions/src/low_precision_transformations/convolution_function.cpp		diff \| blob \| history
inference-engine/tests/ngraph_functions/src/low_precision_transformations/fake_quantize_function.cpp		diff \| blob \| history
inference-engine/tests/ngraph_functions/src/low_precision_transformations/mat_mul_function.cpp		diff \| blob \| history
inference-engine/tests/ngraph_functions/src/low_precision_transformations/max_pool_function.cpp		diff \| blob \| history
inference-engine/tests/ngraph_functions/src/low_precision_transformations/move_dequantization_after_function.cpp	[new file with mode: 0644]	blob
inference-engine/tests/ngraph_functions/src/low_precision_transformations/mul_add_to_scaleshift_or_power_function.cpp		diff \| blob \| history
inference-engine/tests/ngraph_functions/src/low_precision_transformations/multiply_function.cpp		diff \| blob \| history
inference-engine/tests/ngraph_functions/src/low_precision_transformations/mvn_function.cpp		diff \| blob \| history
inference-engine/tests/ngraph_functions/src/low_precision_transformations/normalize_l2_function.cpp		diff \| blob \| history

Domain: Machine Learning / ML Framework;

RSS Atom