diff options
author | Francis Murtagh <francis.murtagh@arm.com> | 2019-06-07 11:28:49 +0100 |
---|---|---|
committer | Francis Murtagh <francis.murtagh@arm.com> | 2019-06-07 12:23:15 +0000 |
commit | edf5230830f8d9794ef0aeb8986da99734ff925f (patch) | |
tree | e2f35f3088e594fdde2361af4b73fb23485f3702 /CMakeLists.txt | |
parent | 49ab7ada17a354caa5b6263c3a732e55d9cd2743 (diff) | |
download | armnn-edf5230830f8d9794ef0aeb8986da99734ff925f.tar.gz |
IVGCVSW-3228 Fix bias quantization to be INT32 not QAsymm8
* Add function to calculate bias tensor quantization scale
from input and weights scales.
* Change visitor method of Conv2d, DepthwiseConv and FullyConnected to use
the new function.
* Fix Unit tests to expect correctly calculated quantization parameters.
Change-Id: Ic36f47ceea81243c813d74ccf791e984c819cc71
Signed-off-by: Francis Murtagh <francis.murtagh@arm.com>
Diffstat (limited to 'CMakeLists.txt')
0 files changed, 0 insertions, 0 deletions