armnn.git -

Age	Commit message (Collapse)	Author
2019-09-27	NNXSW-1826 Add an optimization step which combines Permute and BatchToSpace ↵	Rob Hughes
	into DepthToSpace This is only possible in some limited cases, but removes an extra layer from the graph and so should improve performance in all cases. Change-Id: I7b3e6ba5dacb4fdb816ad270edaecda1436ab4cf Signed-off-by: Rob Hughes <robert.hughes@arm.com>
2019-04-19	IVGCVSW-2925: Combine Pad with Convolution2d in the Optimizer	Nina Drozd
	* Added new optimization for folding pad layer into convolution2d layer following it * Added new test in OptimizerTests.cpp * Added new optimization into All optimizations * Added call to new optimization in Optimize in Network.cpp * Updated CMakeLists.txt Signed-off-by: Nina Drozd <nina.drozd@arm.com> Change-Id: I682e07c71bbd42c49c02dda30a848a9ab2b16e7e
2018-12-11	IVGCVSW-1434 Add debug mode to Optimizer	keidav01
	* Modified optimizer to support debug mode via DebugLayer Change-Id: Ic8f313778e55540c182cf99876c44a0823be04c6
2018-09-17	IVGCVSW-1807 : change license text in file headers	David Beck
	All changes are the same: // // Copyright © 2017 ARM Ltd. All rights reserved. -// See LICENSE file in the project root for full license information. +// SPDX-License-Identifier: MIT // Change-Id: I37eae011411133663ca9d2b059714d92f8bf8e24
2018-08-31	Release 18.08	telsoa01

2018-03-09	Release 18.02	telsoa01
	Change-Id: Id3c11dc5ee94ef664374a988fcc6901e9a232fa6