diff options
| author | SiCong Li <sicong.li@arm.com> | 2019-08-20 11:09:11 +0100 |
|---|---|---|
| committer | Gian Marco Iodice <gianmarco.iodice@arm.com> | 2019-08-20 17:07:25 +0100 |
| commit | 7b5aa651217946a6098cb0116c98ce41edfdfd30 (patch) | |
| tree | a5fbc04a8c37f9e38b7662245405c5f566fff371 /src/core/NEON/kernels/arm_gemm/quantized.cpp | |
| parent | ee090c92bfaec90b5b23f3d969ea35f278a22066 (diff) | |
| download | ComputeLibrary-7b5aa651217946a6098cb0116c98ce41edfdfd30.tar.gz | |
COMPMID-2492 Fix Segfault in NEDeconvolutionLayer for NHWC
Manually manage the tensor _permuted_weights instead of letting memory
group manage it. This is because the operation _permute_weights occurs
inside the prepare stage.
Signed-off-by: SiCong Li <sicong.li@arm.com>
Change-Id: Idb639dffcc9942b4acf1bb8dab05f516bdec60d1
Reviewed-on: https://review.mlplatform.org/c/1769
Comments-Addressed: Arm Jenkins <bsgcomp@arm.com>
Tested-by: Arm Jenkins <bsgcomp@arm.com>
Reviewed-by: Michele Di Giorgio <michele.digiorgio@arm.com>
Diffstat (limited to 'src/core/NEON/kernels/arm_gemm/quantized.cpp')
0 files changed, 0 insertions, 0 deletions