aboutsummaryrefslogtreecommitdiff
path: root/tests/TfLiteMobileNetQuantizedSoftmax-Armnn/TfLiteMobileNetQuantizedSoftmax-Armnn.cpp
AgeCommit message (Collapse)Author
2019-05-28IVGCVSW-3129 Image pre-processing fix for TFLitev19.05FinnWilliamsArm
* 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
2019-04-23IVGCVSW-2657: New Mobilenet Timings test which includes quantisation and softmaxDavid Monahan
Signed-off-by: David Monahan <david.monahan@arm.com> Change-Id: Ieeb6ead55a3af851eea666334e41c3c9c3e3803b