diff options
author | Aron Virginas-Tar <Aron.Virginas-Tar@arm.com> | 2019-11-04 15:00:19 +0000 |
---|---|---|
committer | Áron Virginás-Tar <aron.virginas-tar@arm.com> | 2019-11-05 12:36:31 +0000 |
commit | b67f95796b03c1a5d3b3fa6a40f6baf85bdd09cb (patch) | |
tree | d96468d22624886f9495dbaf8b381f232d347b8b /src/backends/reference/RefTensorHandle.cpp | |
parent | 13b653fd246b31279ae6cb42261671462b52d1be (diff) | |
download | armnn-b67f95796b03c1a5d3b3fa6a40f6baf85bdd09cb.tar.gz |
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
Diffstat (limited to 'src/backends/reference/RefTensorHandle.cpp')
0 files changed, 0 insertions, 0 deletions