Lev Proleev c88f4c60a8 Add quantization coupling test
Quantization coupling test is ran only on models that contain only one
operator and at least one of its inputs has a type of
TENSOR_QUANT8_ASYMM. The test verifies that a model with all the
operands converted to TENSOR_QUANT8_ASYMM_SIGNED will produce the same
result (OK/SKIPPED/FAILED).

Bug: 137828994
Test: VtsHalNeuralNetworksV1_3TargetTest --gtest_filter="*QuantizationCouplingTest*"
Change-Id: I5a2e09b2b1bd790e7e37dde133554e516155a34d
2019-11-18 17:20:55 +00:00
2019-11-08 12:17:34 -08:00
2019-11-07 13:03:11 -08:00
2019-11-12 13:54:42 -08:00
Description
No description provided
134 MiB
Languages
C++ 56.3%
AIDL 41.2%
C 1.5%
Rust 0.4%
Java 0.4%
Other 0.1%