IVGCVSW-3547 Use ExecuteNetwork to run a dynamic backend end to end test
* Added path override for dynamic backend loading
* Do not default to CpuRef, as there could be dynamic backends loaded at
runtime
* Do not check right away whether the backends are correct, as more of
them can be loaded at runtime as dynamic backends
Change-Id: If23f79aa1480b8dfce57e49b1746c23b6b9e6f82
Signed-off-by: Matteo Martincigh <matteo.martincigh@arm.com>
diff --git a/tests/InferenceTest.inl b/tests/InferenceTest.inl
index 04cae99..c91193f 100644
--- a/tests/InferenceTest.inl
+++ b/tests/InferenceTest.inl
@@ -397,7 +397,9 @@
modelParams.m_VisualizePostOptimizationModel = modelOptions.m_VisualizePostOptimizationModel;
modelParams.m_EnableFp16TurboMode = modelOptions.m_EnableFp16TurboMode;
- return std::make_unique<InferenceModel>(modelParams, commonOptions.m_EnableProfiling);
+ return std::make_unique<InferenceModel>(modelParams,
+ commonOptions.m_EnableProfiling,
+ commonOptions.m_DynamicBackendsPath);
});
});
}