tree e0a101fbb7ba41cd50e30a1e0ce31529404175ed
parent 7f2c35a82ec11be50b3478bd15207320bbf3bd57
author FinnWilliamsArm <Finn.Williams@arm.com> 1558533055 +0100
committer Narumol Prangnawarat <narumol.prangnawarat@arm.com> 1559033984 +0100

IVGCVSW-3129 Image pre-processing fix for TFLite

 * Resized images for quantized models are now statically cast to uint8
   instead of quantized

 * Removed optional quantization parameters from ImagePreprocessor
   constructor

 * Changed mean and scale for TFLite models

Signed-off-by: FinnWilliamsArm <Finn.Williams@arm.com>
Change-Id: Id5ffdf77f3614d10c417e769bd8ffc4a4c07308b