diff options
| author | Benjamin Klimczak <benjamin.klimczak@arm.com> | 2022-06-23 10:42:43 +0100 |
|---|---|---|
| committer | Benjamin Klimczak <benjamin.klimczak@arm.com> | 2022-06-23 10:42:43 +0100 |
| commit | 7faf2c4763f299ee53b1ed100025ba50021c8313 (patch) | |
| tree | 42fdcf5e24033f776153f353394308eff99b06e5 /MANIFEST.in | |
| parent | 9097397073133ab4f61da329010839f638978462 (diff) | |
| download | mlia-7faf2c4763f299ee53b1ed100025ba50021c8313.tar.gz | |
MLIA-545 Make quantization non-strict
Use TFLITE_BUILTINS instead of TFLITE_BUILTINS_INT8 to make the
quantization non-strict.
Note: De facto this does not change the behavior of MLIA because the
TFLITE_BUILTINS_INT8 is not correctly applied with the new quantizer.
See: https://github.com/tensorflow/tensorflow/issues/56535
Change-Id: Ia0782ba22c5e9223fa10fec71c16aee60b79bb57
Diffstat (limited to 'MANIFEST.in')
0 files changed, 0 insertions, 0 deletions