[loco] Infer the shape of bias-taking nodes (#6332)
author박종현/On-Device Lab(SR)/Staff Engineer/삼성전자 <jh1302.park@samsung.com>
Thu, 8 Aug 2019 02:41:16 +0000 (11:41 +0900)
committerGitHub Enterprise <noreply-CODE@samsung.com>
Thu, 8 Aug 2019 02:41:16 +0000 (11:41 +0900)
commitfbb6dd28a94823d385c37509a55d693bb660cd98
tree309f6b7e94a8b7179c22f58af3cb5697075bc013
parent92365ce6468173c1c355b93e183db470966ff2af
[loco] Infer the shape of bias-taking nodes (#6332)

* [loco] Infer the shape of bias-taking nodes

CanonicalShapeInferenceRule is now able to infer the shape of
BiasEncode, FeatureBiasAdd, and TensorBiasAdd nodes.

Signed-off-by: Jonghyun Park <jh1302.park@samsung.com>
* Fix a typo
compiler/loco/src/Service/CanonicalShapeInferenceRule.cpp