platform_hardware_interfaces/neuralnetworks
Xusong Wang 39c865b3aa Fix logics for floating-point comparision in VTS test.
Set the acceptable error range based on both absolute tolerance and
relative tolerance.

Currently, absolute tolerance is set to 1e-5 for FP32 and 5 epsilon
(~5e-3) for FP16 relaxed computation. The relative tolerance is set to
5ULP of the corresponding precision. Add a TODO mark for potential
future adjustment on error limit based on testing.

Bug: 111768023

Test: none
Change-Id: Idedcec3e09fd7de9696811b93c81d0f180e896ef
2018-09-06 21:41:06 +00:00
..
1.0 Fix logics for floating-point comparision in VTS test. 2018-09-06 21:41:06 +00:00
1.1 NNAPI: sync NDK and HAL documentation 2018-04-27 14:45:32 -07:00
README Add README to NeuralNetworks HAL 2018-02-01 13:49:49 -08:00

NeuralNetworks sample driver implementation is located at
frameworks/ml/nn/driver/sample.