armnn.git -

Age	Commit message (Collapse)	Author
2019-05-31	IVGCVSW-3182 Updated Validation files	FinnWilliamsArm
	* Validation files need to be changed due to image pre-processor fix: IVGCVSW-3129 * Updated TfLiteVGG16Quantized-Armnn Validation.txt * Updated TfLiteMobileNetQuantizedSoftmax Validation.txt Change-Id: I801978cc9d658542e5b5d966347de3381191ad66 Signed-off-by: FinnWilliamsArm <Finn.Williams@arm.com>
2019-05-30	IVGCVSW-3182 Corrected expected model predictions	FinnWilliamsArm
	* Changed expected predictions for TfLiteVGG16Quantized-Armnn.cpp * Changed expected predictions for TfLiteMobileNetQuantizedSoftmax-Armnn Change-Id: I3fe0bd3f6e44655b14b10887bc40fb0df31f81c8 Signed-off-by: FinnWilliamsArm <Finn.Williams@arm.com>
2019-05-27	IVGCVSW-3129 Image pre-processing fix for TFLite	FinnWilliamsArm
	* 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
2019-04-23	IVGCVSW-2657: Model update to fix failing timings test: TfLiteVGG16Quantized	David Monahan
	Signed-off-by: David Monahan <david.monahan@arm.com> Change-Id: I49bd93766f8f3cf41a9471c87c1c61ed1ec6034c
2019-01-15	IVGCVSW-2454 Merge together the pluggable backends work (was in a	Matteo Martincigh
	separate branch) and master * Brings in all the changes done for the pluggable backends * Added sub-graph support and tests * Added precompiled layer support and tests * Moved BackendSettings to a separate file * Removed the backend-specific code * Ported DebugLayer and associated functionality * Included fixes to make those changes work with master Change-Id: Id7028fa7917527b844628d5aff5732e3d94c0488
2018-10-31	IVGCVSW-1970 TfLite VGG16: Use same number of iterations as other tests	Matthew Bentham
	I had forgotten that as a workaround for the testing using a different number of test cases for different hardware backends, we repeat the expected test results an arbitrary number of times Change-Id: I4d1ea8daa1cbfd63ebcd7ac93ac30acb5806fafe
2018-10-30	IVGCVSW-1970 TfLite VGG16: Correct number of iterations	Matthew Bentham
	Change-Id: Iaf03755b0d30598f5d09ca36af8eeeb369191950
2018-10-30	IVGCVSW-1970 TfLite VGG16: Add Validation.txt for continuous integration	Matthew Bentham
	Change-Id: Ib7ea0a0b809bdfe1d705b31a08f42e1b7815b0d2
2018-10-29	IVGCVSW-2029 Tweak results handling for batch size 2 test	Matthew Bentham
	When looking for the top probability, use the 'first' result not the 'second'. This avoids an issue where for batched tests the classification index was reported wrongly. Still doesn't correctly handle multiple results with the exact probabibility, or batched testing, but it's slightly more correct than before. Change-Id: I57d33552754667613e222d9d2037e12c87a96854
2018-10-26	IVGCVSW-2029 Fix fully connected layer support in TfLite Parser and ↵	Nattapat Chaimanowong
	implement test for TfLite VGG16 quantized Change-Id: I2061f62f62684b963fa0f090718f1dcffe5c93ce