diff options
author | Annop Wongwathanarat <annop.wongwathanarat@arm.com> | 2023-01-16 14:36:45 +0000 |
---|---|---|
committer | Annop Wongwathanarat <annop.wongwathanarat@arm.com> | 2023-01-30 15:59:43 +0000 |
commit | b609c93e81b1ff60764c5b724f4f5511215c84d6 (patch) | |
tree | 3822ed89e9b99778994362cadb1f62b97aef6764 /arm_compute/runtime/NEON | |
parent | fbbfa5388d7e430ff7e9a3fb0bff8045574706e4 (diff) | |
download | ComputeLibrary-b609c93e81b1ff60764c5b724f4f5511215c84d6.tar.gz |
Skip upsampling for deconvolution when not needed
If the input tensor's stride is 1 and the kernel size is 1x1,
skip upsampling step and pass the input tensor pointer for
convolution directly.
Partially resolve: [ONCPUML-1137]
Change-Id: I9de9444ff99cf35d44a51ccbe0fa6facc1035d27
Signed-off-by: Annop Wongwathanarat <annop.wongwathanarat@arm.com>
Reviewed-on: https://review.mlplatform.org/c/ml/ComputeLibrary/+/8994
Tested-by: Arm Jenkins <bsgcomp@arm.com>
Comments-Addressed: Arm Jenkins <bsgcomp@arm.com>
Reviewed-by: Gunes Bayir <gunes.bayir@arm.com>
Benchmark: Arm Jenkins <bsgcomp@arm.com>
Diffstat (limited to 'arm_compute/runtime/NEON')
-rw-r--r-- | arm_compute/runtime/NEON/functions/NEDeconvolutionLayer.h | 1 |
1 files changed, 1 insertions, 0 deletions
diff --git a/arm_compute/runtime/NEON/functions/NEDeconvolutionLayer.h b/arm_compute/runtime/NEON/functions/NEDeconvolutionLayer.h index 15124d6041..869df69f11 100644 --- a/arm_compute/runtime/NEON/functions/NEDeconvolutionLayer.h +++ b/arm_compute/runtime/NEON/functions/NEDeconvolutionLayer.h @@ -148,6 +148,7 @@ private: ITensor *_input; PadStrideInfo _info; bool _is_prepared; + bool _do_upsampling; }; } // arm_compute #endif /* ARM_COMPUTE_NEDECONVOLUTIONLAYER_H */ |