diff options
| author | Teresa Charlin <teresa.charlinreyes@arm.com> | 2022-10-27 11:37:29 +0100 |
|---|---|---|
| committer | TeresaARM <teresa.charlinreyes@arm.com> | 2022-10-28 10:23:36 +0000 |
| commit | 4d85adf436092d01ca0957967156e36060e8be68 (patch) | |
| tree | ad13e2320c98f93c058b0cd43186005e7258d1ee /scripts/get_compute_library.sh | |
| parent | 0f86ecfce593a302ebd2baf8b70c9f6f50616f81 (diff) | |
| download | armnn-4d85adf436092d01ca0957967156e36060e8be68.tar.gz | |
IVGCVSW-7296 REDUCE_PROD tests fail when using Tf 2.10
* In TF what ArmNN calls quantized data types can be non-quantized as well.
* This patch creates 2 models:
* ArmNN: model where int8 and uint8 will always be quantized, but scale can be 1 and offset 0
* TFLite: model where int8 and uint8 can be quantized and non-quantized
Signed-off-by: Teresa Charlin <teresa.charlinreyes@arm.com>
Change-Id: Id960f2f30988f2bbec88cb4e0c52c189ac957bae
Diffstat (limited to 'scripts/get_compute_library.sh')
0 files changed, 0 insertions, 0 deletions