mirror of
https://github.com/Evolution-X/hardware_interfaces
synced 2026-02-01 22:04:26 +00:00
c88f4c60a8564809231cea78734396f8d79b98f3
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
…
…
…
…
…
…
…
…
…
…
…
…
…
Description
No description provided
Languages
C++
56.3%
AIDL
41.2%
C
1.5%
Rust
0.4%
Java
0.4%
Other
0.1%