Age | Commit message (Collapse) | Author |
|
Signed-off-by: Nikhil Raj <nikhil.raj@arm.com>
Change-Id: I6e0474d88fcfed8812d7a1b565e09b12256b9956
|
|
quantization params
* TensorInfo can have multiple scales and quantization dimension.
Signed-off-by: Sadik Armagan <sadik.armagan@arm.com>
Change-Id: I0ff02e3766996b6a9da6dc4e92d366bc9505c77d
|
|
Convolution2d and FullyConnected layers
* Add InsertConvertFp32ToBf16LayersBefore
* Add ConvertWeight to ConvertFp32NetworkToBf16Impl for Conv2d and FullyConnected
* Allow different input and output when input is BF16 and output is FP32
Conv2d and FullyConnected layers
* Unit tests
Signed-off-by: Narumol Prangnawarat <narumol.prangnawarat@arm.com>
Change-Id: Ic8f92ff28edcae08a72a3114a28f50c4619f919b
|
|
Signed-off-by: Nikhil Raj <nikhil.raj@arm.com>
Change-Id: I1d255e21f3786bc5afb1aec71cab6e523e5e4ac9
|
|
* Use default keyword for armnn::Optional assignment.
* Use default keyword for BFloat16 copy constructor and assignment.
* Remove unnecessary const from static_cast template argument which
was giving ignored-qualifiers warning.
Signed-off-by: Francis Murtagh <francis.murtagh@arm.com>
Change-Id: Ie3f4ce0a0c199a578d8cca2fea8f5dcef63dba4d
|
|
* The std::thread::id is included in some timeline packages of the
profiler. But the size of thread::id is platform dependent. That's why
some tests expected a wrong package size
Signed-off-by: Jan Eilers <jan.eilers@arm.com>
Change-Id: I4794ebbdda2d75ed5be7112f6a3bf2e5f14f221b
|
|
Change-Id: I500f82e9fff881e0a49aa5a7cc580c6c4923d33c
Signed-off-by: Finn Williams <Finn.Williams@arm.com>
|
|
Signed-off-by: Nikhil Raj <nikhil.raj@arm.com>
Change-Id: I114dff0427b9ae6f49b3138e78ade97d07684fd1
|
|
Signed-off-by: Narumol Prangnawarat <narumol.prangnawarat@arm.com>
Change-Id: I57ec47adf98680254fa481fb91d5a98dea8f032e
|
|
Signed-off-by: Finn Williams <Finn.Williams@arm.com>
Change-Id: I35e0a891cd69f2c130b8886460089c441d8e666d
|
|
android-nn-driver
* Implemented ClNegWorkload
* Implemented NeonNegWorkload
* Enabled 'NEG' operator on CL and Neon as well as Ref
* Implemented unit tests for 'NEG' operator
Signed-off-by: Sadik Armagan <sadik.armagan@arm.com>
Change-Id: I3d7a892692716636cae6bdf8ddd238e3d1ea064f
|
|
Signed-off-by: Nikhil Raj <nikhil.raj@arm.com>
Change-Id: I2f72b559594c227e2c5181fb9ec22a776ec9dcb1
|
|
Signed-off-by: Nikhil Raj <nikhil.raj@arm.com>
Change-Id: I0d9b2ba0d3f2569baf6fc824f06a9c1412f2814e
|
|
* Add ReduceFp32ToBf16 to OptimizerOptions
* Add ConvertFp32NetworkToBf16
* Add utility functions to insert conversion layers
* Add constant conversion BF16 <-> FP32
* Unit tests
Signed-off-by: Narumol Prangnawarat <narumol.prangnawarat@arm.com>
Change-Id: Iaff77e20c721400b052cb37eb9ef6fe16d7abaff
|
|
Signed-off-by: Finn Williams <Finn.Williams@arm.com>
Change-Id: Ia42f962ba53d7684f5ad75f5b1b91e2d9f3a2f9c
|
|
* Added new layer QLstm (Android R HAL 1.3)
* Made necessary updates to APIs
* Added unit tests
* This layer is functionally equivalent to the
original unquantized LSTM layer with some
additonal quantization features added. Due
to this, original LstmParams are used for
this layer.
Signed-off-by: James Conroy <james.conroy@arm.com>
Change-Id: I5b7f2d2fb6e17e81573b41a31bc55f49ae79608f
|
|
Signed-off-by: Nikhil Raj <nikhil.raj@arm.com>
Change-Id: I90bbe9406d81320289d9878700d738f6b33d8a94
|
|
* ProfilingService reference field not required in TimelineUtilityMethods
Signed-off-by: Sadik Armagan <sadik.armagan@arm.com>
Change-Id: I83ca13e577d35fb9497d7df1535607ec66c201bf
|
|
the Backends CI job
* Enable the GetProfilingService() function to BackendProfilingTests and ProfilingTestUtils
Signed-off-by: Sadik Armagan <sadik.armagan@arm.com>
Change-Id: I32e3625db0f465883f2ec27fb7c2fad4e91b6306
|
|
* Enabled Boolean and Int32 data types in Reference Comparison inputs
* Added decoder for Boolean data type
* Refactored ClGreaterWorkload to work with any data type
* Refactored NeonGreaterWorkload to work with any data type
!android-nn-driver:2902
Signed-off-by: Sadik Armagan <sadik.armagan@arm.com>
Change-Id: I92772810b744b388831c9dca0119ebf8cb7a447e
|
|
* Added new m_FileFormat variable in ExternalProfilingOptions
* Added new profiling option to ExecuteNetwork
* Added check for file format in ProfilingConnectionFactory
* Added test in profiling tests
Change-Id: I0e9cb8ecac919dc0ed03dcf77324a65621f07ae7
Signed-off-by: Isabella Gottardi <isabella.gottardi@arm.com>
|
|
Signed-off-by: Narumol Prangnawarat <narumol.prangnawarat@arm.com>
Change-Id: I9099a4f840fb747336f77d20a0868b64e801a310
|
|
Signed-off-by: Finn Williams <Finn.Williams@arm.com>
Change-Id: I174f83c9a454b5499f817baf0bddcd4a49cac523
|
|
Signed-off-by: Finn Williams <Finn.Williams@arm.com>
Change-Id: I84ab68c048675a39a67045430b2dde571b45e479
|
|
* adds convert from armnn HardSwish to Acl HardSwish
* adds EndToEnd tests for Ref, Cl and Neon
Signed-off-by: Jan Eilers <jan.eilers@arm.com>
Change-Id: If997dad783ff45d7f061254e7e30bb69d4d4d564
|
|
* implemented activation layer end to end test
* adds support for different tolerances in layer tests
* added tests for Elu (Ref, Cl, Neon)
Signed-off-by: Jan Eilers <jan.eilers@arm.com>
Change-Id: I81e28cfb4456e815bae2fb31f5c345134ff2432f
|
|
Signed-off-by: Sadik Armagan <sadik.armagan@arm.com>
Change-Id: I345c39a10a4693a500aa1687d9a5cee76da791c3
|
|
!armnn:2810
Signed-off-by: Finn Williams <Finn.Williams@arm.com>
Change-Id: Idf56d42bd767baa5df0059a2f489f75281f8ac71
|
|
Signed-off-by: Nikhil Raj <nikhil.raj@arm.com>
Change-Id: I83bf33aeec93326b9b2c99db4e5151404df5bb30
|
|
Signed-off-by: Narumol Prangnawarat <narumol.prangnawarat@arm.com>
Change-Id: Ida6d7e1d2c9abe0618f8b711bab9d62c011090d6
|
|
Change-Id: Icae7c40abb307e1bbdd383ab3f835f5a1bee2db1
Signed-off-by: Derek Lamberti <derek.lamberti@arm.com>
|
|
* Improved error reporting by using VisitorThrowingPolicy in
DynamicQuantizationVisitor.
Change-Id: I8a7d0975d448e6c2b6efb5f315ac255eec29f7a2
Signed-off-by: Pablo Tello <pablo.tello@arm.com>
|
|
Signed-off-by: Nikhil Raj <nikhil.raj@arm.com>
Change-Id: I035b3aeef778cd415224e9238f463bc706c00080
|
|
Signed-off-by: David Monahan <david.monahan@arm.com>
Change-Id: I7f6932f0d21b5678ab9822b0fc69f589bbbb07e5
|
|
* Upload current ArmNN Doxygen files
Signed-off-by: Ryan OShea <Ryan.OShea2@arm.com>
Change-Id: I8989ed16ee40a99a4495b100bd009cf3e24a7285
|
|
Signed-off-by: Nikhil Raj <nikhil.raj@arm.com>
Change-Id: Ie966c938752e06ddc8a6d03b973edd0291864a39
|
|
Signed-off-by: Narumol Prangnawarat <narumol.prangnawarat@arm.com>
Change-Id: Id179cb4774a4565e5e905e5fe4c34299178644de
|
|
Signed-off-by: Narumol Prangnawarat <narumol.prangnawarat@arm.com>
Change-Id: Ifaae4d5aac468ba927b2c6a4bf31b8c8522aeb2e
|
|
An empty line resulted in program exit.
* Ignore empty lines.
* Add error message when an invalid number of parameters to
SET or WAIT command is encountered.
Signed-off-by: Colm Donelan <Colm.Donelan@arm.com>
Change-Id: Ie2d229c1330b71b559d988d4ecb8019f2f850333
|
|
Change-Id: Ib4bbab387cec4780c8aae56fdede090fa265e4ba
Signed-off-by: Derek Lamberti <derek.lamberti@arm.com>
|
|
Signed-off-by: Nikhil Raj <nikhil.raj@arm.com>
Change-Id: Ic9180b560ba527a14800c452453cb027120fac0c
|
|
* Doxygen comment touch-ups
* Fixed markup in .dox files
* Fixed stylesheet
* Doxyfile changes
* Added logo file
* Added header file
Signed-off-by: Ryan OShea <Ryan.OShea2@arm.com>
Change-Id: I94c7f5a6923a0bbb5c6ed610f1f55d57e2bb8a49
|
|
* Added test to add multiple SwTraceMessages to the buffer
* Updated TimelineCaptureCommandHandler to iterate until there
are no more read functions in the packet
* Further commenting
Change-Id: I41d5acf4f7288ce5a51ffd10a5eea335ac3026ec
Signed-off-by: Keith Davis <keith.davis@arm.com>
|
|
* Added .dox files for main sections
* Merged .md files into .dox files
* Updated Doxyfile
* Stylesheet for Doxygen
Signed-off-by: Ryan OShea <Ryan.OShea2@arm.com>
Change-Id: Ic13c28b3235fca91aeb463cd5063750aa6d85be8
|
|
Signed-off-by: Nikhil Raj <nikhil.raj@arm.com>
Change-Id: I718d0553f1d30f0b62d75d8dfb03a9556eb2a347
|
|
Signed-off-by: Narumol Prangnawarat <narumol.prangnawarat@arm.com>
Change-Id: I85b6967469dc1fddbbc875b34ba107480b78089a
|
|
* Allow per layer quantization from Fp32 to Int8 (QAsymmS8) like TfLite
Signed-off-by: Francis Murtagh <francis.murtagh@arm.com>
Change-Id: I5bbf770aa29d81af3568c15b47d2b2c18e55bb28
|
|
As a last resort, check for shared Compute Library in standard paths.
This will work for Linux distribution builds where no static Compute
Library has been installed.
Change-Id: I1ea11d184ef9dcf4480ae0687a4ba81b402c5b2d
Signed-off-by: Matthew Bentham <Matthew.Bentham@arm.com>
|
|
!referencetests:229377
Signed-off-by: Jan Eilers <jan.eilers@arm.com>
Change-Id: Ia9b360b4a057fe7bbce5b268092627c09a0dba82
|
|
* Add ConvertFloat32ToBFloat16
* Add ConvertBFloat16ToFloat32
* Add BFloat16Encoder
* Add BFloat16Decoder
* Unit tests
Signed-off-by: Narumol Prangnawarat <narumol.prangnawarat@arm.com>
Change-Id: I198888384c923aba28cfbed09a02edc6f8194b3e
|