diff options
author | Aron Virginas-Tar <Aron.Virginas-Tar@arm.com> | 2019-11-15 15:59:51 +0000 |
---|---|---|
committer | Aron Virginas-Tar <Aron.Virginas-Tar@arm.com> | 2019-11-18 13:59:40 +0000 |
commit | 65a1b1d600cbccf7269409cb7ca0947f0222cb8b (patch) | |
tree | f1c536abaa78b9d57e315987736e3400bf7f976f /Utils.hpp | |
parent | 444268f77ca864857a52a2f2e1638ddfc7cfe7e6 (diff) | |
download | android-nn-driver-65a1b1d600cbccf7269409cb7ca0947f0222cb8b.tar.gz |
IVGCVSW-4139 Fix regression in ConvertDequantize()
* Removed TENSOR_QUANT8_SYMM from the list of generally supported
tensor data types
* Fixed tensor info in DequantizeIfRequired() for on the fly
dequantized QSymm8 weights
* Moved code for checking whether a Dequantize operator is linked
to FullyConnected or Lstm weights from ConvertDequantize() into
a separate function inside 1.2/HalPolicy.cpp
Signed-off-by: Aron Virginas-Tar <Aron.Virginas-Tar@arm.com>
Change-Id: I19ea6f89a90f553a964b87d44f8ad8a064e96f7f
Diffstat (limited to 'Utils.hpp')
0 files changed, 0 insertions, 0 deletions