commit a28aebc5f80630683f50ce934e8584c6b0004beb
author Pablo Tello <pablo.tello@arm.com> Mon Jun 03 14:59:48 2019 +0100
committer Pablo Marquez <pablo.tello@arm.com> Thu Jun 20 16:24:33 2019 +0000
tree 0764f6b51f76985ac3c788d123bb8f1e50da9ff5
parent e16c8906a2aedf00e910754a01fca8bc4189cfc7

COMPMID-2383: DepthwiseConv use output qinfo

There was a problem in depthwise_conv where when needing to run
permute it was calling auto_init to initialise the temporary tensor
with input's qinfo instead of output's qinfo. This patch fixes
this and adds some tests to exercise the cases where we have different
qinfos

Change-Id: I396fbb4d73f6aa5efe03dc2dd727b3e13154d6f5
Signed-off-by: Pablo Tello <pablo.tello@arm.com>
Reviewed-on: https://review.mlplatform.org/c/1270
Tested-by: Arm Jenkins <bsgcomp@arm.com>
Comments-Addressed: Arm Jenkins <bsgcomp@arm.com>
Reviewed-by: Giuseppe Rossini <giuseppe.rossini@arm.com>
Reviewed-by: Georgios Pinitas <georgios.pinitas@arm.com>

src/runtime/CL/functions/CLDepthwiseConvolutionLayer.cpp

diff --git a/src/runtime/CL/functions/CLDepthwiseConvolutionLayer.cpp b/src/runtime/CL/functions/CLDepthwiseConvolutionLayer.cpp
index e912740..1608277 100644
--- a/src/runtime/CL/functions/CLDepthwiseConvolutionLayer.cpp
+++ b/src/runtime/CL/functions/CLDepthwiseConvolutionLayer.cpp
@@ -90,6 +90,7 @@
         // Configure the function to transform the weights tensor from HWI -> IHW
         _permute_weights_to_nchw.configure(weights, &_permuted_weights, PermutationVector(1U, 2U, 0U));
         _permuted_weights.info()->set_data_layout(DataLayout::NCHW);
+        _permuted_output.info()->set_quantization_info(output->info()->quantization_info());
 
         input_to_use   = &_permuted_input;
         weights_to_use = &_permuted_weights;