Age | Commit message (Collapse) | Author |
|
* Pass in new window parameter to the schedule_op function
Signed-off-by: Nikhil Raj <nikhil.raj@arm.com>
Change-Id: I8579d2d6e55ab9888471bd780628df0f73438498
|
|
* Add neon detection for linux using HWCAPs
* Add test to check for backend throwing BackendUnavailable exception
Signed-off-by: Francis Murtagh <francis.murtagh@arm.com>
Change-Id: Ib74aeb06abe5f88f21ecdd1edb2a1cd20ee2019d
|
|
* Added GATHER operator support to TfLiteParser
* Added DEPTH_TO_SPACE operator support to TfLiteParser
Signed-off-by: Sadik Armagan <sadik.armagan@arm.com>
Change-Id: Id5d3b54e2d850eb9f19417029efbeb73a3029e69
|
|
* Implemented external delegate adaptor interface for TfLite
* Activated armnn logging for delegate
* Added logging info to indicate if gpu tuning is turned on
* Added pytests to ensure functionality of the external delegate adaptor
* Included the delegate directory into doxygen
* Added documentation on how to use the external delegate in python
Signed-off-by: Finn Williams <Finn.Williams@arm.com>
Signed-off-by: Jan Eilers <jan.eilers@arm.com>
Change-Id: Id3b4588fb0b9ac7e3f47ba2c19feead7beb58e18
|
|
Signed-off-by: Teresa Charlin <teresa.charlinreyes@arm.com>
Change-Id: I6504e922113aa9e397f53e570ebcf47e1f133945
|
|
* Report the error thrown
Signed-off-by: Sadik Armagan <sadik.armagan@arm.com>
Change-Id: If5e5160f43c11a284b919d76b04d9c4d53e9c56c
|
|
* Added ARG_MIN and ARG_MAX support to armnn_delegate
Signed-off-by: Sadik Armagan <sadik.armagan@arm.com>
Change-Id: Ia000c4b64378e28320164edd4df2902ca13dcda6
|
|
* Added generated schema file to the source tree
* Updated the ANdroid.mk file to pick up the Serializer/Deserializer source
Signed-off-by: Sadik Armagan <sadik.armagan@arm.com>
Change-Id: I12c2bf2ae7aa12374c60e671ff3a97eac5b7f161
|
|
* Added ModelOptions documentation to CLBackendModelContext
* Improved options descriptions in ExecuteNetworkProgramOptions.cpp
Signed-off-by: Matthew Sloyan <matthew.sloyan@arm.com>
Change-Id: I14f0c8bb4f299809b89f49c616b691e2f7956d5b
|
|
Signed-off-by: Nikhil Raj <nikhil.raj@arm.com>
Change-Id: I33dc1127627b4b89c02a3bea246eaf7499e5a780
|
|
* Added support for bias vector in TransposeConv to TfLite parser
* Added UnitTest
Signed-off-by: David Monahan <david.monahan@arm.com>
Change-Id: I6483986a9da9216084b4b885b7fd980fc3580fa9
|
|
* ArmnnQuantizer incorrectly converts boolean or integer DataTypes to quantized
DataTypes. This breaks layers like ArgMinMax where the output contains the
index of an element along an axis.
Signed-off-by: Mike Kelly <mike.kelly@arm.com>
Change-Id: I272c3d0f48bf884a2480bfa43eb14ec265fcda6b
|
|
* Fixed the ContributorGuide display issue
Signed-off-by: Sadik Armagan <sadik.armagan@arm.com>
Change-Id: I7be39cda5682a220dbd3708692230ab7421f80e0
|
|
Current we use 'A'rmNNQuantizer name for executable
and 'a'rmNNQuantizer as library name.
Since cmake does not allow same name for executable and library.
The old way is to use a captial letter for the executable name.
But it will create a problem on system (like macosx) that the file
system is case insensitive by default. Since it will create/overwritten
file on the same folder during the cmake build which makes build failed
when BUILD_ARMNN_QUANTIZER is enabled.
Fixed this by using ArmNNQuantizerMain as the executable
name during build, then rename it back to ArmNNQuantizer using
set_target_property OUTPUT_NAME function.
Signed-off-by: Keith Mok <ek9852@gmail.com>
Change-Id: I3e0779770c851c0eb6804e300a24836be955d07a
|
|
* Fixed issue where nightly job couldn't find flatbuffers import.
* Removed unnecessary commented code.
Signed-off-by: Matthew Sloyan <matthew.sloyan@arm.com>
Change-Id: If201f3fe54bf3bdd167aaf5d108154165d2a910d
|
|
* Float16 unit tests for Reshape
* Remove unsupported data type from Pad
Signed-off-by: Narumol Prangnawarat <narumol.prangnawarat@arm.com>
Change-Id: Ib1804bb6e708a0552fb40d05fe8a6511936f9793
|
|
* Remove need to update the guide for each release
by allowing user to check for newest version
Signed-off-by: Francis Murtagh <francis.murtagh@arm.com>
Change-Id: Ic6dda46524916762a06f24444bd7368ff1cde159
|
|
* Use ECONNREFUSED #define instead for connection refused error no.
* As error code on mips for example is 146
Change-Id: I2c725dc93ab8951d4f42a3ba51e747e01ced3a68
Signed-off-by: Francis Murtagh <francis.murtagh@arm.com>
|
|
* Enable ability to save/load ClContext in ExecuteNetwork.
Signed-off-by: Matthew Sloyan <matthew.sloyan@arm.com>
Change-Id: I58c61a53f6713853eb06520cc372ed47baf7f8c4
|
|
* Implemented Serialization and Deserialization of CLContext.
* Fixed flatbuffers android-nn-driver dependency.
!android-nn-driver:4772
Signed-off-by: Matthew Sloyan <matthew.sloyan@arm.com>
Signed-off-by: Sadik Armagan <sadik.armagan@arm.com>
Change-Id: If806f050535ffaa70922ba0f1ffe7bb10f902329
|
|
Signed-off-by: Keith Mok <ek9852@gmail.com>
Change-Id: I4b2926342bbf8621f7b7f5695cf1526dd7281bef
|
|
On macosx, the section rodata syntax is a
little bit different, add ifdef __MACH__
to fix that.
Signed-off-by: Keith Mok <ek9852@gmail.com>
Change-Id: Ic11d6faf8b8d3f3b521fd4305e6cdc3562a1c8ae
|
|
Signed-off-by: Nikhil Raj <nikhil.raj@arm.com>
Change-Id: I10e46b3c4b7d69bcb742014cb2633cfc061eb718
|
|
armnn support argmax and deconv , but caffe parser does not.
Add back this feature.
Signed-off-by: Keith Mok <ek9852@gmail.com>
Change-Id: I6b99cc4b58491204c41c6e1d11f583c65c628ee4
|
|
Signed-off-by: Keith Mok <ek9852@gmail.com>
Change-Id: I3a85de2d082d489fbf5a775c2ae551080d189294
|
|
Signed-off-by: Teresa Charlin <teresa.charlinreyes@arm.com>
Change-Id: I6a00045967fa48ec0913c8708ffc146a72ed2b87
|
|
Signed-off-by: Nikhil Raj <nikhil.raj@arm.com>
Change-Id: Ie4fd3fe2671050537eb0ab85032922f6464c9d24
|
|
Signed-off-by: Nikhil Raj <nikhil.raj@arm.com>
Change-Id: I1422eab2beb3d59841f827b60d822f987e08f326
|
|
* Add Pad and PadV2 operators support to Armnn Delegate
* Add dimension check to CompareOutputData test utility
* Unit tests
Signed-off-by: Narumol Prangnawarat <narumol.prangnawarat@arm.com>
Change-Id: I9d00eb08f71e791498908fcbdb9de561e1c01aef
|
|
Signed-off-by: Finn Williams <Finn.Williams@arm.com>
Change-Id: I33eb8c650be654ad891afd2295f2057f13a9d084
|
|
* Added CL implementation of Rank Workload
* Removed references to memcpy_s as it's a windows only function
Signed-off-by: David Monahan <david.monahan@arm.com>
Change-Id: Ia63666b9640d76a775f2ab98b3cd7e9f77b5a507
|
|
Signed-off-by: Nikhil Raj <nikhil.raj@arm.com>
Change-Id: Icd92b46f7dcac091739e8a9b01e5c36bf16b0fcb
|
|
* Enabled Hard Swish and Elu in TfLiteDelegate
* Added support for Elu in TfLiteParser
Signed-off-by: Matthew Sloyan <matthew.sloyan@arm.com>
Change-Id: If09321b58568a98e14cabce610a1586556da041e
|
|
* QASymmS8 and BoundedReLU
* Float16 and ReLU in GpuAcc
* Remove layerName, not needed as 1 test per combination
Signed-off-by: Teresa Charlin <teresa.charlinreyes@arm.com>
Change-Id: I930c7a04d8d904f370f1b40c62cf9311c172bbdf
|
|
Signed-off-by: Narumol Prangnawarat <narumol.prangnawarat@arm.com>
Change-Id: I85f0c30757043f8c27c78d607f0f9dbbdd35b9fb
|
|
Signed-off-by: Nikhil Raj <nikhil.raj@arm.com>
Change-Id: Ib6d10096a5348f06d744c5629eb3b41f9c187059
|
|
Signed-off-by: Nikhil Raj <nikhil.raj@arm.com>
Change-Id: Ifff69c7ddce967f7a084c26837685e84f680e78a
|
|
Signed-off-by: Matthew Sloyan <matthew.sloyan@arm.com>
Change-Id: I28b2eca636b5ca9156865871b60447707bfa8647
|
|
Make it easier for backends to traverse the subgraph during optimization
Change-Id: I140cb11f78bab5f19c801a5b55efffb38c63837f
Signed-off-by: Derek Lamberti <derek.lamberti@arm.com>
|
|
Signed-off-by: Nikhil Raj <nikhil.raj@arm.com>
Change-Id: Idc5233a19a97a6feb42b6841e6aff9d793a88740
|
|
Change-Id: Iecd8d9b333fa4456d081b4787c1a5b5d0b4a2b79
Signed-off-by: Derek Lamberti <derek.lamberti@arm.com>
|
|
Signed-off-by: Nikhil Raj <nikhil.raj@arm.com>
Change-Id: I3c51a9a16908af2b1bc9250ada31b8ca46307fff
|
|
Signed-off-by: James Ward <james.ward@arm.com>
Change-Id: Iac19640fec7aabdfcbb88a0856d4fce3a15d3f27
|
|
* Fixed issue when running certain models with 2D shape tensor.
* Falls back to inbuilt options if encountered.
* Fixed ExecuteNetwork so that error messages are logged if NULL.
* Updated TfLiteDelegate docs to include Logical Operators.
Signed-off-by: Matthew Sloyan <matthew.sloyan@arm.com>
Signed-off-by: David Monahan <david.monahan@arm.com>
Signed-off-by: Narumol Prangnawarat <narumol.prangnawarat@arm.com>
Change-Id: I5dbaf30351f7fc86e6178a0caf46c152812088d3
|
|
* Use kernelShape[0] as channels for outputShape.
Signed-off-by: James Conroy <james.conroy@arm.com>
Change-Id: I070c7ff68ae365d9505a5eb28c76f9e52da1e5f9
|
|
Signed-off-by: Nina Drozd <nina.drozd@arm.com>
Change-Id: Ic999cb898933fa674f1cd3b4b85ab650154d587d
|
|
Signed-off-by: Teresa Charlin <teresa.charlinreyes@arm.com>
Change-Id: Ic4c7df887d460fd695ffec822437e0c8a5095baf
|
|
* Implemented Logical AND, NOT and OR operators.
* NOT uses existing ElementwiseUnary VisitLayer function & tests.
* AND/OR uses new LogicalBinary VisitLayer function & tests.
Signed-off-by: Matthew Sloyan <matthew.sloyan@arm.com>
Change-Id: I5e7f1e78b30c36ac7f14c70a712b54f98d664b83
|
|
Signed-off-by: David Monahan <david.monahan@arm.com>
Change-Id: I5a85597e75d2b879ae234c6929686fabe99d7bc8
|
|
Signed-off-by: Nikhil Raj <nikhil.raj@arm.com>
Change-Id: I2cafcbe087cb55e7252cbba2a7c8b649a98067e1
|