armnn.git -

Age	Commit message (Collapse)	Author
2020-07-26	IVGCVSW-5155 Update Arm NN API to allow for call to shape inference	Finn Williams
	Signed-off-by: Finn Williams <Finn.Williams@arm.com> Change-Id: I0a2babe5b5b09eb81c9900dc3a05071034a0440b
2020-07-10	IVGCVSW-4929 Implement ShapeInferenceMethod in all Layers	Finn Williams
	Signed-off-by: Finn Williams <Finn.Williams@arm.com> Change-Id: I2c2d99f97cf89814140b057a9f93f41b364197f5
2020-07-06	IVGCVSW-4988 Add handling output shape parameter to TransposeConvolution2d	Colm Donelan
	* Add m_OutputShape and m_OutputShapeEnabled to TransposeConvolution2dDescriptor. * Update TfLite parser to populate m_OutputShape if found in the model. Handle both Signed32 from tflite files and QAsymmU8 from test fixtures. * Update TransposeConvolution2dLayer to use m_OutputShape instead of InferOutputShapes if specified. Signed-off-by: Colm Donelan <Colm.Donelan@arm.com> Change-Id: Ia6933065375eb8006c916f1ca67c38dc50bc205c
2020-06-26	IVGCVSW-4928 Introduce "ShapeInferenceMethod" Option.	Teresa Charlin
	Signed-off-by: Teresa Charlin <teresa.charlinreyes@arm.com> Change-Id: I70ef1a9f3cefa1d4cf9220f0e13131d11e7c6418
2020-06-23	IVGCVSW-4924 Fix edge case for transposeConv2d shape inference	Finn Williams
	Signed-off-by: Finn Williams <Finn.Williams@arm.com> Change-Id: I0147ad10aeb16cf5c876cbf09434279ba6813714
2020-04-06	IVGCVSW-4485 Remove Boost assert	Narumol Prangnawarat
	* Change boost assert to armnn assert * Change include file to armnn assert * Fix ARMNN_ASSERT_MSG issue with multiple conditions * Change BOOST_ASSERT to BOOST_TEST where appropriate * Remove unused include statements Signed-off-by: Narumol Prangnawarat <narumol.prangnawarat@arm.com> Change-Id: I5d0fa3a37b7c1c921216de68f0073aa34702c9ff
2019-12-31	IVGCVSW-4246 Clean build Layers with -Wextra	Derek Lamberti
	Change-Id: I649cd2304fb0040164763d31a12fc77c6c3bed87 Signed-off-by: Derek Lamberti <derek.lamberti@arm.com>
2019-11-29	IVGCVSW-4209 Create a public API for the ArmNN Utils	Matteo Martincigh
	* Moved the relevant armnnUtils headers to the new location: include/armnnUtils * Update the header usage throughout the source code !android-nn-driver:2387 Signed-off-by: Matteo Martincigh <matteo.martincigh@arm.com> Change-Id: I2ba15cebcacafad2b5a1a7b9c3312ffc585e09d6
2019-09-17	IVGCVSW-3879 Fix output shape inference formula for TransposeConvolution2d	Aron Virginas-Tar
	Signed-off-by: Aron Virginas-Tar <Aron.Virginas-Tar@arm.com> Change-Id: I766f4297b9daa26edacc2079fe62a083ba2fa68f
2019-08-02	IVGCVSW-3604 Fix channel shape calculation in ↵	Narumol Prangnawarat
	TransposeConvolution2dLayer::InferOutputShapes Signed-off-by: Narumol Prangnawarat <narumol.prangnawarat@arm.com> Change-Id: I2e3d5922bb89c8f3b84ff5458fda981ff177c3ce
2019-06-27	IVGCVSW-3324 Add end-to-end tests for TransposeConvolution2d on CpuRef	Aron Virginas-Tar
	* Added one end-to-end test for all supported data types and data layout * Implemented RefLayerSupport::IsTransposeConvolution2dSupported() * Fixed formula used in TransposeConvolution2dLayer::InferOutputShapes() Signed-off-by: Aron Virginas-Tar <Aron.Virginas-Tar@arm.com> Change-Id: If1ba3c226ecfa17f7fceffae857f39297c6433f2
2019-06-21	IVGCVSW-3319 Add frontend support for TransposeConvolution2d Layer	Aron Virginas-Tar
	Signed-off-by: Aron Virginas-Tar <Aron.Virginas-Tar@arm.com> Change-Id: Ic06f63f1eff255e697facf319e2ac4c83d782e7c