projects / platform / upstream / armnn.git / commit
? search:
summary | shortlog | log | commit | commitdiff | tree
(parent: 9be4916) | patch
IVGCVSW-3842 Add per-axis quantization support to ValidateBiasTensorQuantization()
authorAron Virginas-Tar <Aron.Virginas-Tar@arm.com>
Wed, 30 Oct 2019 16:03:19 +0000 (16:03 +0000)
committerÁron Virginás-Tar <aron.virginas-tar@arm.com>
Thu, 31 Oct 2019 11:15:43 +0000 (11:15 +0000)
commitd90530719f6ab16417eb95d885317f50c662725f
tree0e705b49cbfbb4af6e36b0729429cd6fd61a95eftree | snapshot
parent9be4916397a3de0cc92824fe2ce92854cfc2d997commit | diff
IVGCVSW-3842 Add per-axis quantization support to ValidateBiasTensorQuantization()

* Altered the function to validate all the scale values in the bias
  tensor info when per-axis quantization is enabled
* Added unit test to check if ValidateBiasTensorQuantization() works
  as intended

Signed-off-by: Aron Virginas-Tar <Aron.Virginas-Tar@arm.com>
Change-Id: I676d17690cda6bbdd41da5fdbaa50a3d3b5fd102
src/backends/backendsCommon/WorkloadData.cpp diff | blob | history
src/backends/backendsCommon/test/WorkloadDataValidation.cpp diff | blob | history
Domain: Machine Learning / ML Framework;