projects / platform / adaptation / npu / trix-engine.git / commit
? search:
summary | shortlog | log | commit | commitdiff | tree
(parent: 2d66854) | patch
[npubinfmt/v2] add quantization parameters for each input/output tensor
authorDongju Chae <dongju.chae@samsung.com>
Fri, 10 Jan 2020 07:25:05 +0000 (16:25 +0900)
committer파리차이카푸르/On-Device Lab(SR)/Engineer/삼성전자 <pk.kapoor@samsung.com>
Mon, 13 Jan 2020 10:18:36 +0000 (19:18 +0900)
commitbef61b9db86c199867a6b5ec479df0063a769bf7
tree4f643869cef507afcd0fbfcd7ac52c13597a43d6tree | snapshot
parent2d6685442c14bf6e3b7fc14d63c1c6914701e98fcommit | diff
[npubinfmt/v2] add quantization parameters for each input/output tensor

This commit adds quantization parameters to npubinfmt.h (v2), which will
be used to quantize each input/output activation.

Signed-off-by: Dongju Chae <dongju.chae@samsung.com>
include/common/npubinfmt.h diff | blob | history
Domain: Machine Learning / ML Framework;