diff options
author | Matteo Martincigh <matteo.martincigh@arm.com> | 2018-12-18 09:26:39 +0000 |
---|---|---|
committer | Matteo Martincigh <matteo.martincigh@arm.com> | 2019-01-04 17:28:07 +0000 |
commit | 747ef82c88f9afe14a8b80b6b3b34118353e97f2 (patch) | |
tree | a29ac33b84fb96a41103a0a97327189495374cc9 /src/armnn/test/OptimizerTests.cpp | |
parent | 760892724d131c7da4b9baad05cddd49276ad6bb (diff) | |
download | armnn-747ef82c88f9afe14a8b80b6b3b34118353e97f2.tar.gz |
MLCE-77 Depthwise Convolution with depth multiplier > 1 doesn't work
* Unified ArmNN's weight format to [ M, I, H, W ] for the depthwise convolution
* Added conversion utilities to permute/reshape the weights as appropriate
when using CL and Neon backends
* Updated the reference implementation of the convolution
* Updated the relevant unit tests accordingly
!android-nn-driver:459
Change-Id: I07d0818efa9d1ca1e5dad82983aac1fe78eadb18
Diffstat (limited to 'src/armnn/test/OptimizerTests.cpp')
-rw-r--r-- | src/armnn/test/OptimizerTests.cpp | 2 |
1 files changed, 1 insertions, 1 deletions
diff --git a/src/armnn/test/OptimizerTests.cpp b/src/armnn/test/OptimizerTests.cpp index 29d1702c64..80addb4bfd 100644 --- a/src/armnn/test/OptimizerTests.cpp +++ b/src/armnn/test/OptimizerTests.cpp @@ -898,7 +898,7 @@ BOOST_AUTO_TEST_CASE(DepthwiseConv2dValidateTensorShapesFromInputsNhwc) { Graph graph; const unsigned int inputShape[] = { 1, 3, 3, 2 }; - const unsigned int weightsShape[] = { 1, 3, 3, 2 }; + const unsigned int weightsShape[] = { 1, 2, 3, 3 }; const unsigned int outputShape[] = { 1, 1, 1, 2 }; CreateDepthwiseConvolution2dGraph(graph, inputShape, weightsShape, outputShape, DataLayout::NHWC); |