IVGCVSW-5826 Change weights layout for depthwise to [1,H,W,I*M]

 * This change is necessary because tflite uses a [1,H,W,I*M] format
   and uses the I*M dimension for per axis quantization. Our previous
   layout [M,I,H,W] can't handle the correlating quantization scales.
 * Updates Onnx-, TfLiteParser and TfliteDelegate
 * Updates the CpuRef, CpuAcc and GpuAcc backends
 * Adjusts unit tests
 * Adds test to ensure models with old layout can still be read and
   executed
 * Adds conversion function to previous layout [1,H,W,I*M] --> [M,I,H,W]
   which can be used by backend developers

!android-nn-driver:5553

Signed-off-by: Jan Eilers <jan.eilers@arm.com>
Change-Id: Ifef23368b8c3702cf315a5838d214f7dc13c0152

1 files changed, 2 insertions, 2 deletions

diff --git a/src/armnn/test/CreateWorkload.hpp b/src/armnn/test/CreateWorkload.hpp
index 581c621a16..b07e3b80a5 100644
--- a/src/armnn/test/CreateWorkload.hpp
+++ b/src/armnn/test/CreateWorkload.hpp
@@ -1149,7 +1149,7 @@ std::unique_ptr<DepthwiseConvolution2dFloat32Workload> CreateDepthwiseConvolutio
 
     DepthwiseConvolution2dLayer* const layer = graph.AddLayer<DepthwiseConvolution2dLayer>(layerDesc, "layer");
 
-    layer->m_Weight = std::make_unique<ScopedTensorHandle>(TensorInfo({1, 2, 4, 4}, DataType)); // [ M, I, H, W ]
+    layer->m_Weight = std::make_unique<ScopedTensorHandle>(TensorInfo({1, 4, 4, 2}, DataType)); // [ 1, H, W, I*M ]
     layer->m_Weight->Allocate();
 
     // Creates extra layers.
@@ -1181,7 +1181,7 @@ std::unique_ptr<DepthwiseConvolution2dFloat32Workload> CreateDepthwiseConvolutio
 
     CHECK(queueDescriptor.m_Inputs.size() == 1);
     CHECK(queueDescriptor.m_Outputs.size() == 1);
-    CHECK((queueDescriptor.m_Weight->GetTensorInfo() == TensorInfo({1, 2, 4, 4}, DataType)));
+    CHECK((queueDescriptor.m_Weight->GetTensorInfo() == TensorInfo({1, 4, 4, 2}, DataType)));
 
     // Returns so we can do extra, backend-specific tests.
     return workload;