diff options
Diffstat (limited to 'src/armnn/Network.hpp')
-rw-r--r-- | src/armnn/Network.hpp | 2 |
1 files changed, 2 insertions, 0 deletions
diff --git a/src/armnn/Network.hpp b/src/armnn/Network.hpp index a84a0e9ba4..34549248bc 100644 --- a/src/armnn/Network.hpp +++ b/src/armnn/Network.hpp @@ -350,6 +350,8 @@ struct OptimizerOptionsOpaqueImpl } /// Reduces all Fp32 operators in the model to Fp16 for faster processing. + /// If the first preferred backend does not have Fp16 support, this option will be disabled. + /// If the value of converted Fp16 is infinity, round to the closest finite Fp16 value. /// @Note This feature works best if all operators of the model are in Fp32. ArmNN will add conversion layers /// between layers that weren't in Fp32 in the first place or if the operator is not supported in Fp16. /// The overhead of these conversions can lead to a slower overall performance if too many conversions are |