IVGCVSW-5842 Remove cross-wiring in depthwise

 * Reading tensor infos won't allow a permutation vector anymore.
   The permutation only changed the quantization dimension not the
   shape and was therefore misleading
 * The permutation of the full tensor info is now performed in
   armnnUtils::Permuted
 * Changed TfLite Parser depthwise parsing function
 * Added unit tests to TfLite Parser with more random data
 * Changed TfLite Delegate depthwise parsing function
 * Added unit test to the delegate with per channel quantization

!android-nn-driver:5412

Signed-off-by: Jan Eilers <jan.eilers@arm.com>
Change-Id: I1f985ee69547bcaf16a72201e00a6b6fe1ef9a97

1 files changed, 4 insertions, 2 deletions

diff --git a/delegate/src/test/Convolution2dTest.cpp b/delegate/src/test/Convolution2dTest.cpp
index 2ce2944a79..6f498ce22e 100644
--- a/delegate/src/test/Convolution2dTest.cpp
+++ b/delegate/src/test/Convolution2dTest.cpp
@@ -166,8 +166,10 @@ void Conv2DWithBiasesReluUint8Test(std::vector<armnn::BackendId>& backends)
                                             expectedOutputValues,
                                             biasShape,
                                             biasValues,
-                                            1, // filter scale
-                                            4, // filter offset
+                                            {1.0f}, // biasScale
+                                            {0},    // biasOffset
+                                            {1.0f}, // filterScale
+                                            {4},    // filterOffsets
                                             2, // output scale
                                             20); // output offset
 }