COMPMID-3484: Regression in Transpose convolution Android R CTS test.

- Removing _flip_axis from _memory_group management

Change-Id: Ica3039fa7b545b34de231bcd7620d76914681808
Signed-off-by: Manuel Bottini <manuel.bottini@arm.com>
Reviewed-on: https://review.mlplatform.org/c/ml/ComputeLibrary/+/3191
Comments-Addressed: Arm Jenkins <bsgcomp@arm.com>
Reviewed-by: Michele Di Giorgio <michele.digiorgio@arm.com>
Tested-by: Arm Jenkins <bsgcomp@arm.com>

diff --git a/src/runtime/NEON/functions/NEDeconvolutionLayer.cpp b/src/runtime/NEON/functions/NEDeconvolutionLayer.cpp
index c87dac60dcfab3bf084fd3c5bd3eb4b93ebf5ad7..dd53fbbdc3d667f68d3b47a5a61c43cd1bf44fe2 100644 (file)
--- a/src/runtime/NEON/functions/NEDeconvolutionLayer.cpp
+++ b/src/runtime/NEON/functions/NEDeconvolutionLayer.cpp
@@ -161,7 +161,6 @@ void NEDeconvolutionLayer::configure(ITensor *input, const ITensor *weights, con
 
     _flip_axis.allocator()->init(TensorInfo(TensorShape(2U), 1, DataType::U32));
     _memory_group.manage(&_scaled_output);
-    _memory_group.manage(&_flip_axis);
 
     _weights_flipped.allocator()->init(weights->info()->clone()->set_data_layout(data_layout));
     _flip_weights.configure(weights, &_weights_flipped, &_flip_axis);