projects / platform / upstream / armnn.git / commit
? search:
summary | shortlog | log | commit | commitdiff | tree
(parent: 9a5f9f2) | patch
Increase tolerance for bias scale quantization calculation for ResNet50v2
authorricbur01 <richard.burton@arm.com>
Thu, 31 Oct 2019 16:22:18 +0000 (16:22 +0000)
committerMatteo Martincigh <matteo.martincigh@arm.com>
Fri, 1 Nov 2019 08:38:16 +0000 (08:38 +0000)
commit3f4d7104cdd5fd0ca6238afd4d22ac8734fd84ae
tree69cbc14e7216f0d5a28560a60fab5e735e03c51ctree | snapshot
parent9a5f9f2c3b6709003dfb935ecf65150145b9c73bcommit | diff
Increase tolerance for bias scale quantization calculation for ResNet50v2

Signed-off-by: Richard Burton <richard.burton@arm.com>
Change-Id: I033ef445fa8e5ae825cfde29927b88e97e20f093
src/backends/backendsCommon/WorkloadData.cpp diff | blob | history
Domain: Machine Learning / ML Framework;