projects / platform / core / ml / nnfw.git / commit
? search:
summary | shortlog | log | commit | commitdiff | tree
(parent: f95bd49) | patch
Set arm_compute::TensorShape for bias correctly (#549)
author박종현/동작제어Lab(SR)/Senior Engineer/삼성전자 <jh1302.park@samsung.com>
Wed, 11 Apr 2018 00:56:28 +0000 (09:56 +0900)
committer김정현/동작제어Lab(SR)/Senior Engineer/삼성전자 <jh0822.kim@samsung.com>
Wed, 11 Apr 2018 00:56:28 +0000 (09:56 +0900)
commitaadb745d12fe96636654ce2c0f873d051028dd01
treeb41ea8179732ea5769cb1b1c308919f532bad6ectree | snapshot
parentf95bd499f280c593fe19191c862819a05adb5a77commit | diff
Set arm_compute::TensorShape for bias correctly (#549)

This commit revises convFloat32 implementation based on ARM Compute to
correctly set bias shape. This change fixes clBuffer exception during
bias memory allocation.

Signed-off-by: Jonghyun Park <jh1302.park@samsung.com>
src/kernel/acl/src/Conv2D_acl.cpp diff | blob | history
Domain: Machine Learning / ML Framework;