tequilaOS/platform_hardware_interfaces
2
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity

Adds TENSOR_QUANT8_SYMM support to test infrastructure

Browse source 
This is needed to be able to test DEQUANTIZE after adding
TENSOR_QUANT8_SYMM support.

Test: NeuralNetworksTest_static
Test: VtsHalNeuralnetworksV1_2TargetTest
Change-Id: Iba9b286df70919d7b67cd77c91e625a044bd686c
Merged-In: Iba9b286df70919d7b67cd77c91e625a044bd686c
(cherry picked from commit bf26a9e3d7)
This commit is contained in:
Lev Proleev 2019-02-20 12:49:14 +00:00
parent 7d30a90b5e
commit 603244cb70
1 changed files with 2 additions and 1 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

3
neuralnetworks/1.0/vts/functional/GeneratedTestHarness.cpp
View file

@ -72,7 +72,8 @@ void copy_back(MixedTyped* dst, const std::vector<RequestArgument>& ra, char* sr
copy_back_(&dst->bool8Operands, ra, src); copy_back_(&dst->bool8Operands, ra, src);
copy_back_(&dst->quant8ChannelOperands, ra, src); copy_back_(&dst->quant8ChannelOperands, ra, src);
copy_back_(&dst->quant16AsymmOperands, ra, src); copy_back_(&dst->quant16AsymmOperands, ra, src);
static_assert(8 == MixedTyped::kNumTypes, copy_back_(&dst->quant8SymmOperands, ra, src);
static_assert(9 == MixedTyped::kNumTypes,
"Number of types in MixedTyped changed, but copy_back function wasn't updated"); "Number of types in MixedTyped changed, but copy_back function wasn't updated");
} }