armnn.git -

Age	Commit message (Collapse)	Author
2021-10-22	IVGCVSW-6166 Add Support for Conv3d to TFLite Delegate	Matthew Sloyan
	* Conv3d is only correctly supported for external delegates from TF v2.6, as there was a breaking bug in v2.5. Signed-off-by: Matthew Sloyan <matthew.sloyan@arm.com> Change-Id: Ib7941307f4c7b0d3dbb7deaa5a90aceb63c1162f
2021-06-16	IVGCVSW-5826 Change weights layout for depthwise to [1,H,W,I*M]	Jan Eilers
	* This change is necessary because tflite uses a [1,H,W,IM] format and uses the IM dimension for per axis quantization. Our previous layout [M,I,H,W] can't handle the correlating quantization scales. * Updates Onnx-, TfLiteParser and TfliteDelegate * Updates the CpuRef, CpuAcc and GpuAcc backends * Adjusts unit tests * Adds test to ensure models with old layout can still be read and executed * Adds conversion function to previous layout [1,H,W,I*M] --> [M,I,H,W] which can be used by backend developers !android-nn-driver:5553 Signed-off-by: Jan Eilers <jan.eilers@arm.com> Change-Id: Ifef23368b8c3702cf315a5838d214f7dc13c0152
2021-04-21	IVGCVSW-5842 Remove cross-wiring in depthwise	Jan Eilers
	* Reading tensor infos won't allow a permutation vector anymore. The permutation only changed the quantization dimension not the shape and was therefore misleading * The permutation of the full tensor info is now performed in armnnUtils::Permuted * Changed TfLite Parser depthwise parsing function * Added unit tests to TfLite Parser with more random data * Changed TfLite Delegate depthwise parsing function * Added unit test to the delegate with per channel quantization !android-nn-driver:5412 Signed-off-by: Jan Eilers <jan.eilers@arm.com> Change-Id: I1f985ee69547bcaf16a72201e00a6b6fe1ef9a97
2020-11-30	IVGCVSW-5374 Provide Android Build for Delegate	Keith Davis
	* Fix Arm Android Compiler errors Signed-off-by: Keith Davis <keith.davis@arm.com> Change-Id: If5fae0fda08b6102eb46217564a096f87a3b6740
2020-11-20	IVGCVSW-5538 Fix delegate DepthwiseConv2d, DIV, Reshape	Narumol Prangnawarat
	* Correct filter shape for DepthwiseConv2d * Remove non-support data type * Allow check for flatten on Reshape Signed-off-by: Narumol Prangnawarat <narumol.prangnawarat@arm.com> Change-Id: Ic4be63d7c2f3a2b5e13a1530025a49464c21171b
2020-11-16	IVGCVSW-5338 TfLiteDelegate: Implement the Convolution operators	Sadik Armagan
	* Add Convolution, DepthwiseConvolution and TransposeConvolution Signed-off-by: Kevin May <kevin.may@arm.com> Signed-off-by: Sadik Armagan <sadik.armagan@arm.com> Change-Id: I797e42844dfee0cc80beb64eabc3111b96320daf
2020-10-27	IVGCVSW-5366 'Add a do nothing SubGraph class'	Sadik Armagan
	IVGCVSW-5373 'Implement the ABS operator in the Delegate' * Added a Switch statement into the VisitNode() function * Separated the Visit functions into the categorized source files * Implemented VisitElementwiseUnary() function * Added tests for ABS and SQRT Signed-off-by: Sadik Armagan <sadik.armagan@arm.com> Change-Id: If9654d0a8d8ff7dcd6fb5cbe0dc312941772affb