diff options
| author | Jerry Ge <jerry.ge@arm.com> | 2022-11-09 14:30:59 -0800 |
|---|---|---|
| committer | Eric Kunze <eric.kunze@arm.com> | 2022-11-19 01:11:04 +0000 |
| commit | a633bc61b156f3a4a2cd9f313a738ace459befc1 (patch) | |
| tree | bfd65f79d9936f1d5ab442ae434908fe702f7bd4 /.pre-commit-config.yaml | |
| parent | e4b08ffbe457c8932740e3171964cf2e7cd69b4f (diff) | |
| download | reference_model-a633bc61b156f3a4a2cd9f313a738ace459befc1.tar.gz | |
Fix the floating point precision issue for Sigmoid FP32
The original calculation was auto-promoted to FP64 and causing the
discrepencies between TFL and TOSA. Sigmoid is now calculated with
only single precision floating point values.
Signed-off-by: Jerry Ge <jerry.ge@arm.com>
Change-Id: Ia65b491ccf8af2493cc01ca66c28faff841407c2
Diffstat (limited to '.pre-commit-config.yaml')
0 files changed, 0 insertions, 0 deletions