IVGCVSW-7209 Remove deprecated code due to be removed in 23.02

* Removed weights and bias from Convolution, DepthwiseConv & FullyConnected
  layers
* Removed the weight and bias ConstTensorHandles from the QueueDescriptors
* Updated Workloads to take tensors from WorkloadInfo rather than the
  QueueDescriptors
* Removed unused RedirectMembersToConstantInputs optimization and tests.

Signed-off-by: Teresa Charlin <teresa.charlinreyes@arm.com>
Signed-off-by: Mike Kelly <mike.kelly@arm.com>
Change-Id: I9ffcdc4a1c0dff725539dd69fc435b700bd98a56
diff --git a/src/backends/neon/workloads/NeonDepthwiseConvolutionWorkload.cpp b/src/backends/neon/workloads/NeonDepthwiseConvolutionWorkload.cpp
index e2d0a82..00d9d33 100644
--- a/src/backends/neon/workloads/NeonDepthwiseConvolutionWorkload.cpp
+++ b/src/backends/neon/workloads/NeonDepthwiseConvolutionWorkload.cpp
@@ -1,5 +1,5 @@
 //
-// Copyright © 2017 Arm Ltd and Contributors. All rights reserved.
+// Copyright © 2017,2022 Arm Ltd and Contributors. All rights reserved.
 // SPDX-License-Identifier: MIT
 //
 
@@ -141,10 +141,10 @@
 
     detailsInfo.m_InputTensorInfos = info.m_InputTensorInfos;
     detailsInfo.m_OutputTensorInfos = info.m_OutputTensorInfos;
-    detailsInfo.m_WeightsTensorInfo = armnn::Optional<armnn::TensorInfo>(descriptor.m_Weight->GetTensorInfo());
+    detailsInfo.m_WeightsTensorInfo = armnn::Optional<armnn::TensorInfo>(info.m_InputTensorInfos[1]);
     if (descriptor.m_Parameters.m_BiasEnabled)
     {
-        detailsInfo.m_BiasTensorInfo = armnn::Optional<armnn::TensorInfo>(descriptor.m_Bias->GetTensorInfo());
+        detailsInfo.m_BiasTensorInfo = armnn::Optional<armnn::TensorInfo>(info.m_InputTensorInfos[2]);
     }
 
     // Report Profiling Details