d2871fd52c
* Fix mypy for numpy==1.21.6
* Apply CR changes
* Allow Python 3.6 for open source
* Attempt to silence mypy
* Revert to 3.6 in setup.pys
* Fix merge conflict
* Add newline
* Fix Python version assert
* Test Python 3.10 CI
* Try bumping up pybind to 2.10
* Link default python to python 3.10
* Add sudo to changing default python
* Bump python version in setupvars
* Fix exception in test
* Do the same for compatibility
* Apply same CI changes to other pipelines
* Attempt to fix arm and windows CIs
* Fix win py lib version and links?
* Try to fix CI
* Fix win python path
* Update win path
* Test disable PDPD
* Disable TF for testing CI
* Add sudo to rm
* Test linux
* Update requirements
* RM sudo
* Add debug step to CI on ARM
* build py from source on linux
* Remove debug step from ARM
* Fix err
* Fill num_proc
* Fic py installation
* Bump pdpd to 2.3.1
* Bump np vers
* Try to upgrade onnx to 1.12.0
* Revert onnx upgrade, enable frontends
* Build py shared
* Export library
* activate py env
* Bump scipy for py3.10
* Another scipy bump
* Fix Windows path, add nfs helper for mount
* Attempt to fix win_cc
* Batch of changes
* Try to fix ngraph-onnx-lin
* Install lsb-release for docker on ngraph-onnx-lin
* Link lsb_release
* Try bumping Ubuntu to 22.04
* Revert ubuntu change in dockerfile
* Refactor tests for onnx1.12
* Fix ONNX compatibility and numpy warnings
* Refactor tests for onnx1.12
* Fix ONNX compatibility and numpy warnings
* Upgrade ONNX to 1.12 in cpp
* Skip unsupported ops
* Revert "Fix ONNX compatibility and numpy warnings"
This reverts commit
|
||
|---|---|---|
| .. | ||
| common | ||
| README.md | ||
| conftest.py | ||
| env_config.yml | ||
| requirements.txt | ||
| test_benchmark_app.py | ||
| test_classification_sample_async.py | ||
| test_hello_classification.py | ||
| test_hello_nv12_input_classification.py | ||
| test_hello_query_device.py | ||
| test_hello_reshape_ssd.py | ||
| test_speech_sample.py | ||
README.md
These tests execute IE samples on pregenerated IR
<INSTALL_DIR> - OpenVINO install directory
You can run tests not only from the <INSTALL_DIR>, but in this case you need to remember to adjust the environment variables like as WORKSPACE and SHARE
To install smoke tests:
bash - cd <working directory>/tests/samples_tests/smoke_tests - mkdir build && cd build - cmake ../.. - cmake -DCOMPONENT=tests -DCMAKE_INSTALL_PREFIX=<INSTALL_DIR> -P cmake_install.cmake
- To run tests from install directory required installing some dependencies:
- pip3 install -r <INSTALL_DIR>\tests\smoke_tests\requirements.txt
- Call setupvars script and then set the environment variables:
a. Required:
- IE_APP_PATH : coomon path to C++ and C samples, e.g. '<INSTALL_DIR>/samples_bin'
- IE_APP_PYTHON_PATH : path to python IE samples, e.g. '<INSTALL_DIR>/samples/python/'
- IE_APP_PYTHON_TOOL_PATH : path to python IE tools for benchmark_app, e.g. '<INSTALL_DIR>/tools/' b. Optional:
- TEST_DEVICE = CPU by default
- Configure env_config.yml according to your paths:
- Set WORKSPACE : working directory, e.g. '<INSTALL_DIR>'
- Set SHARE : path to loaded data with models, e.g. '<INSTALL_DIR>/tests/smoke_tests/samples_smoke_tests_data/'
- Run all test via pytest:
- python -m pytest --env_conf env_config.yml -s
- Run only one sample (for example, classification_sample_async):
- python -m pytest test_classification_sample_async.py --env_conf env_config.yml -s
- To run performance add pytest key: "performance n", where n is number of perf iteration. Test finds in output of sample 'fps', if it exists, then tests rerun that sample adding key 'niter n' with number of perfomance run (that you passed to pytest with '--performance n' keys) Not to add 'niter' key, please, execute pytest "--performance 0"
This test using pregenerated IRs, that located right now in shared folder mentioned above. Also data (images, videos and others) locates in that shared folder.