projects / platform / core / ml / nnfw.git / commit
? search:
summary | shortlog | log | commit | commitdiff | tree
(parent: 95c9f0a) | patch
[core.ADT.tensor] Squeeze Tensor Shape correctly. (#226)
author박종현/동작제어Lab(SR)/Senior Engineer/삼성전자 <jh1302.park@samsung.com>
Fri, 18 May 2018 00:09:02 +0000 (09:09 +0900)
committerGitHub Enterprise <noreply-CODE@samsung.com>
Fri, 18 May 2018 00:09:02 +0000 (09:09 +0900)
commit25042ad2f79ac4afe9e0450eeab8a4a626634973
treea910f2279f4d03f4a5eb1c96af5e0523a8adda25tree | snapshot
parent95c9f0a1c43612a79f7ec2912bede7fe27d1270fcommit | diff
[core.ADT.tensor] Squeeze Tensor Shape correctly. (#226)

Squeeze operation (in TensorFlow) removess axises whose dimensionality
is 1, but the current squeeze operation eliminates if their dimensionality
is null.

This commit fixes this mismatch on the semantics of squeeze operation.

Signed-off-by: Jonghyun Park <jh1302.park@samsung.com>
libs/core/src/nncc/core/ADT/tensor/Shape.cpp diff | blob | history
libs/core/src/nncc/core/ADT/tensor/Shape.test.cpp diff | blob | history
Domain: Machine Learning / ML Framework;