projects / platform / core / ml / nnfw.git / commit
? search:
summary | shortlog | log | commit | commitdiff | tree
(parent: 2139d0d) | patch
[mir] New interface for PadOp (#6708)
authorСергей Баранников/AI Tools Lab /SRR/Engineer/삼성전자 <s.barannikov@samsung.com>
Tue, 20 Aug 2019 10:40:18 +0000 (19:40 +0900)
committerAlexander Efimov/AI Tools Lab/./Samsung Electronics <a.efimov@samsung.com>
Tue, 20 Aug 2019 10:40:18 +0000 (13:40 +0300)
commita74d04f0963c1cb8dfc85af884020155e1873b3a
treeacca2642d581c78042834bf2092e8ee4b7715a1ftree | snapshot
parent2139d0df304d4582b2b8de00dade2343f7a299facommit | diff
[mir] New interface for PadOp (#6708)

* Remove redundant `num_dims` parameter of constructor.
* Make padding arguments consistent with other operations (two vectors instead of vector of pairs).
* Change the type of the value to be used for padding from `Scalar` to `float` (it is `float` in all supported input frameworks).

Signed-off-by: Sergei Barannikov <s.barannikov@samsung.com>
compiler/mir/include/mir/ops/PadOp.h diff | blob | history
compiler/mir/src/ops/PadOp.cpp diff | blob | history
Domain: Machine Learning / ML Framework;