projects / platform / core / ml / nnfw.git / commit
? search:
summary | shortlog | log | commit | commitdiff | tree
(parent: f3c4aa9) | patch
Change the scale value of unit test related to the convolution. (#1887)
author장지섭/동작제어Lab(SR)/Engineer/삼성전자 <jiseob.jang@samsung.com>
Mon, 9 Jul 2018 05:43:23 +0000 (14:43 +0900)
committer박세희/동작제어Lab(SR)/Principal Engineer/삼성전자 <saehie.park@samsung.com>
Mon, 9 Jul 2018 05:43:23 +0000 (14:43 +0900)
commit606057e7ca9318a95349e464e78c43fbb3fabadc
tree93f0ecdb08eebfd04f712bc9689b69278fc0228ftree | snapshot
parentf3c4aa9133e93804742c68d811fa7c7d54006ffbcommit | diff
Change the scale value of unit test related to the convolution. (#1887)

This commit change the scale value of unit test related to the convolution.
- Change the scale value of output operand to 1.0f.
- Change the scale value of input and kernel operand to 0.02f.
- Change the scale value of bias to the value of multiplying input scale and kernel scale.

Signed-off-by: jiseob.jang <jiseob.jang@samsung.com>
tools/nnapi_unittests/tests/conv_quan_1.cpp diff | blob | history
tools/nnapi_unittests/tests/dconv_quan_1.cpp diff | blob | history
Domain: Machine Learning / ML Framework;