projects / platform / upstream / armnn.git / commit
? search:
summary | shortlog | log | commit | commitdiff | tree
(parent: 13b653f) | patch
IVGCVSW-3836 Add support for Int32 per-axis scales
authorAron Virginas-Tar <Aron.Virginas-Tar@arm.com>
Mon, 4 Nov 2019 15:00:19 +0000 (15:00 +0000)
committerÁron Virginás-Tar <aron.virginas-tar@arm.com>
Tue, 5 Nov 2019 12:36:31 +0000 (12:36 +0000)
commitb67f95796b03c1a5d3b3fa6a40f6baf85bdd09cb
treed96468d22624886f9495dbaf8b381f232d347b8btree | snapshot
parent13b653fd246b31279ae6cb42261671462b52d1becommit | diff
IVGCVSW-3836 Add support for Int32 per-axis scales

* Added ScaledInt32PerAxisDecoder implementation
* Added new case for Signed32 in MakeDecoder that returns a
  ScaledInt32PerAxisDecoder if the tensor info has multiple
  quantization scales

Signed-off-by: Aron Virginas-Tar <Aron.Virginas-Tar@arm.com>
Change-Id: I8b3c11091644da993044d2a0fe2aba6b06b5af56
include/armnn/TypesUtils.hpp diff | blob | history
src/armnnUtils/TensorUtils.cpp diff | blob | history
src/armnnUtils/TensorUtils.hpp diff | blob | history
src/backends/reference/workloads/BaseIterator.hpp diff | blob | history
src/backends/reference/workloads/Decoders.hpp diff | blob | history
Domain: Machine Learning / ML Framework;