armnn.git -

Age	Commit message (Collapse)	Author
2020-02-07	IVGCVSW-4386 Add ArmNN reference support for QAsymmS8	Ryan OShea
	* Added Quantization Scheme for QAsymmS8 * Added Unit Tests for QAsymmS8 * Renamed QAsymm8 calls to QAsymmU8 Signed-off-by: Ryan OShea <Ryan.OShea2@arm.com> Change-Id: I897b4e018ba1d808cc3f8c113f2be2dbad49c8db
2020-01-13	Rename quantized data types to remove ambiguity for signed/unsigned payloads	Derek Lamberti
	!android-nn-driver:2572 Change-Id: I8fe52ceb09987b3d05c539409510f535165455cc Signed-off-by: Derek Lamberti <derek.lamberti@arm.com>
2019-12-09	IVGCVSW-4211 Add Signed 8 bit Quantisation support into the Reference backend	Finn Williams
	!android-nn-driver:2435 Signed-off-by: Finn Williams <Finn.Williams@arm.com> Change-Id: I10ecd4a8937725953396805f33a3562a5384c4d4
2019-11-18	Fix quantizer crash by zero tensor	Tee Jung
	Signed-off-by: Jung Tae-young <tee.ty.jung@openedges.com> Signed-off-by: Matteo Martincigh <matteo.martincigh@arm.com> Change-Id: I1f0dfa4ca76e1c85a2b8fb5de12039a260224951
2019-05-22	IVGCVSW-3081 Quantizer min>=max error & missing layers	Les Bell
	* relaxed the check to min > max in the quantization schemes * added missing layer support for resnet_v2_50 model * Pad, Rsqrt, Multipilcation, Subtraction, Mean * sorted methods alphabetically in Quantizerlayer & LayerVisitorBase Change-Id: I003401ff7ac89b60580c959ea8fd9d6fef66b88e Signed-off-by: Les Bell <les.bell@arm.com>
2019-03-20	IVGCVSW-2858 Add support for QSymm16 quantization	Nattapat Chaimanowong
	Change-Id: Ia7c305c30c39ec0e9db447a461479be17fde250c Signed-off-by: Nattapat Chaimanowong <nattapat.chaimanowong@arm.com>