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, 5 insertions, 8 deletions

diff --git a/src/armnn/layers/DepthwiseConvolution2dLayer.cpp b/src/armnn/layers/DepthwiseConvolution2dLayer.cpp
index b96c567504..ed52b39050 100644
--- a/src/armnn/layers/DepthwiseConvolution2dLayer.cpp
+++ b/src/armnn/layers/DepthwiseConvolution2dLayer.cpp
@@ -98,24 +98,21 @@ DepthwiseConvolution2dLayer::InferOutputShapes(const std::vector<TensorShape>& i
     unsigned int inputBatchSize = inputShape[0];
     unsigned int inputHeight    = inputShape[dataLayoutIndex.GetHeightIndex()];
     unsigned int inputWidth     = inputShape[dataLayoutIndex.GetWidthIndex()];
-    unsigned int inputChannels  = inputShape[dataLayoutIndex.GetChannelsIndex()];
 
-    // Expected filter shape: [ M, I, H, W ] - This shape does NOT depend on the data layout
-    // Namely: [ depth multiplier, input channels, filter height, filter width ]
-    // Output channels = input channels * depthMultiplier
-    unsigned int depthMultiplier = filterShape[0];
+    // Expected filter shape: [ 1, H, W, O ] - This shape does NOT depend on the data layout
+    // Namely: [ 1, filter height, filter width, output channels ]
 
-    unsigned int filterHeight = filterShape[2];
+    unsigned int filterHeight = filterShape[1];
     unsigned int dilatedFilterHeight = filterHeight + (m_Param.m_DilationY - 1) * (filterHeight - 1);
     unsigned int readHeight   = (inputHeight + m_Param.m_PadTop + m_Param.m_PadBottom) - dilatedFilterHeight;
     unsigned int outputHeight = 1 + (readHeight / m_Param.m_StrideY);
 
-    unsigned int filterWidth = filterShape[3];
+    unsigned int filterWidth = filterShape[2];
     unsigned int dilatedFilterWidth = filterWidth + (m_Param.m_DilationX - 1) * (filterWidth - 1);
     unsigned int readWidth   = (inputWidth + m_Param.m_PadLeft + m_Param.m_PadRight) - dilatedFilterWidth;
     unsigned int outputWidth = 1 + (readWidth / m_Param.m_StrideX);
 
-    unsigned int outputChannels  = inputChannels * depthMultiplier;
+    unsigned int outputChannels  = filterShape[3];
     unsigned int outputBatchSize = inputBatchSize;
 
     TensorShape tensorShape = m_Param.m_DataLayout == armnn::DataLayout::NHWC ?