IntenseWebs/openvino
3
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity
Files
babff1fd1553c4bb1a05191d32bcca3276bc6543
openvino/docs/Inference_Engine_Development_Procedure/COVERAGE.md
Nikolay Tyukaev ef45b5da8d Doc Migration (master) (#1377) 
* Doc Migration from Gitlab (#1289)

* doc migration

* fix

* Update FakeQuantize_1.md

* Update performance_benchmarks.md

* Updates graphs for FPGA

* Update performance_benchmarks.md

* Change DL Workbench structure (#1)

* Changed DL Workbench structure

* Fixed tags

* fixes

* Update ie_docs.xml

* Update performance_benchmarks_faq.md

* Fixes in DL Workbench layout

* Fixes for CVS-31290

* [DL Workbench] Minor correction

* Fix for CVS-30955

* Added nGraph deprecation notice as requested by Zoe

* fix broken links in api doxy layouts

* CVS-31131 fixes

* Additional fixes

* Fixed POT TOC

* Update PAC_Configure.md

PAC DCP 1.2.1 install guide.

* Update inference_engine_intro.md

* fix broken link

* Update opset.md

* fix

* added opset4 to layout

* added new opsets to layout, set labels for them

* Update VisionAcceleratorFPGA_Configure.md

Updated from 2020.3 to 2020.4

Co-authored-by: domi2000 <domi2000@users.noreply.github.com>
2020-07-20 17:36:08 +03:00

2.2 KiB
Raw Blame History

Inference Engine coverage report build

The coverage report is generated using Lcov tool and based on profile data generated by GCC. The generated reports are in HTML form and located in <dldt_build>/coverage. The reports are generated for the following components:

  1. inference_engine - main Inference Engine library
  2. inference_engine_legacy - legacy Inference Engine library
  3. inference_engine_ir_reader - Inference Engine IR reader library
  4. low_precision_transformations - library with Low Precision transformations.
  5. inference_engine_transformations - Ngraph-based transformation for Inference Engine.
  6. preprocessing - Inference Engine G-API based preprocessing plugin.
  7. Inference Engine open-sources plugins:
    • hetero_plugin - Heterogeneous plugin.
    • multi_device - Multi device plugin.
    • cldnn_engine - GPU plugin.
    • mkldnn_plugin - CPU plugin.
    • gna_plugin - GNA plugin.

Build with profiling data support

To build coverage report, compile DLDT with an additional CMake option -DENABLE_COVERAGE=ON:

$ cmake -DENABLE_COVERAGE=ON .

And build DLDT as usual.

Generate coverage report

In order to generate coverage reports, first of all, the tests must be run. Depending on how many tests are run, the better covegare percentage can be achieved. E.g. for inference_engine component, InferenceEngineUnitTests, ieUnitTests, ieFuncTests must be run as well as plugin tests.

$ ctest -V -L IE

After sufficient number of tests are executed, the coverage numbers can be calculated. In order to do this, run:

$ make ie_coverage

The following tree of reports are generated:

$ find coverage/ -maxdepth 2 -name index.html
coverage/hetero_plugin/index.html
coverage/inference_engine/index.html
coverage/inference_engine_ir_reader/index.html
coverage/inference_engine_legacy/index.html
coverage/low_precision_transformations/index.html
coverage/mkldnn_plugin/index.html
coverage/multi_device/index.html
coverage/preprocessing/index.html
coverage/inference_engine_transformations/index.html
coverage/gna_plugin/index.html
coverage/cldnn_engine/index.html