IVGCVSW-6929 Support for models with implicit expanded
dimensions
* Added allow-expanded-dims to TFLite parser and ArmNN delegate
* If true ArmNN will disregard dimensions with a size of 1 when
validating tensor shapes. Tensor sizes must still match.
* This allows us to support models where tensors have expanded
dimensions (i.e. extra dimensions with a size of 1).
* Fixed bug in Network where it assumed that only the first option
could be ShapeInferenceMethod.
* Fixed bug where m_ShapeInferenceMethod was lost when copying or
moving Graphs.
* Changed Delegate to pass "infer-output-shape", "allow-expanded-dims"
and other BackendOptions through to the Network during construction.
Signed-off-by: Mike Kelly <mike.kelly@arm.com>
Change-Id: Ibe7c5ae6597796fc9164cb07bd372bd7f8f8cacf
diff --git a/src/backends/neon/NeonBackend.cpp b/src/backends/neon/NeonBackend.cpp
index 2433642..968bce4 100644
--- a/src/backends/neon/NeonBackend.cpp
+++ b/src/backends/neon/NeonBackend.cpp
@@ -139,9 +139,10 @@
return layerSupport;
}
-OptimizationViews NeonBackend::OptimizeSubgraphView(const SubgraphView& subgraph) const
+OptimizationViews NeonBackend::OptimizeSubgraphView(const SubgraphView& subgraph,
+ const ModelOptions& modelOptions) const
{
- OptimizationViews optimizationViews;
+ OptimizationViews optimizationViews(modelOptions);
auto it = subgraph.endIConnectable();
std::map<LayerGuid, Layer*> untouched;