diff options
| author | Lev Proleev <levp@google.com> | 2019-10-03 14:43:18 +0100 |
|---|---|---|
| committer | Lev Proleev <levp@google.com> | 2019-11-18 17:20:55 +0000 |
| commit | c88f4c60a8564809231cea78734396f8d79b98f3 (patch) | |
| tree | dc34a020d61050502198acabd76b7f943b8b86aa /audio/effect/all-versions/default/Effect.cpp | |
| parent | 16df70e269f8eba0bb40e50f3c95fc40c2629cf0 (diff) | |
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
Diffstat (limited to 'audio/effect/all-versions/default/Effect.cpp')
0 files changed, 0 insertions, 0 deletions