| commit | c88f4c60a8564809231cea78734396f8d79b98f3 | [log] [tgz] |
|---|---|---|
| author | Lev Proleev <levp@google.com> | Thu Oct 03 14:43:18 2019 +0100 |
| committer | Lev Proleev <levp@google.com> | Mon Nov 18 17:20:55 2019 +0000 |
| tree | dc34a020d61050502198acabd76b7f943b8b86aa | |
| 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