IVGCVSW-3808 Add ElementwiseBinaryLayer
!android-nn-driver:9329
* Added ElementwiseBinaryLayer that can represent all ElementwiseBinary
operations including Add, Div, Sub, Maximum, Mul and Minimum.
* Updated Delegate to use ElementwiseBinaryLayer instead of the Add,
Div, Sub, Maximum, Mul and Minimum layers.
* Updated Deserializer to use ElementwiseBinaryLayer instead of the Add,
Div, Sub, Maximum, Mul and Minimum layers.
* Updated OnnxParser to use ElementwiseBinaryLayer instead of the Add
layer.
* Updated TfLiteParser to use ElementwiseBinaryLayer instead of the Add,
Div, Sub, Maximum, Mul and Minimum layers.
* Updated CL and Neon tests to use ElementwiseBinaryLayer.
* Updated CL and Neon Backend Specific Optimizations to accept
ElementBinaryLayers as well as Add, Div, Mul, Sub, Maximum and Minimum
layers.
Signed-off-by: Teresa Charlin <teresa.charlinreyes@arm.com>
Signed-off-by: Mike Kelly <mike.kelly@arm.com>
Change-Id: I7cbb96b60eb01f0e2b57b0541016d48a08b86c75
diff --git a/src/armnnOnnxParser/OnnxParser.cpp b/src/armnnOnnxParser/OnnxParser.cpp
index 936216f..26e2cee 100644
--- a/src/armnnOnnxParser/OnnxParser.cpp
+++ b/src/armnnOnnxParser/OnnxParser.cpp
@@ -1558,7 +1558,7 @@
}
- IConnectableLayer* layer = m_Network->AddAdditionLayer(node.name().c_str());
+ IConnectableLayer* layer = m_Network->AddElementwiseBinaryLayer(BinaryOperation::Add, node.name().c_str());
ARMNN_ASSERT(layer != nullptr);
auto outputInfo = ComputeOutputInfo({ node.output(0) }, layer,