| Age | Commit message (Collapse) | Author |
|---|
|
!armnn:8742
* Done as part of 22.11/23.02 innovation days.
* IsLayerSupported() is called in model prepare (delegate, android-nn-driver and shim/support_library)
and again in ArmNN once model optimization is performed.
* From calling IsLayerSupported() the first time, we should know that the layers are supported
and what backend they are supported on.
* Solution is to set the BackendId of the IConnectableLayer when IsLayerSupported() is called the first time,
* In the Optimize() function we then check if the backend is set. If so, we do not call IsLayerSupported() again.
* In the case a layer that is supported gets optimized, then the BackendId of that layer get set to "Unknown"
for the new optimized layer and IsLayerSupported() will get called on the newly optimized layer.
Signed-off-by: Cathal Corbett <cathal.corbett@arm.com>
Change-Id: Ie5c6c9cd10d81f90b1ee78dd6e3442f353b6c109
|
|
* Changed asserts to check for errors and return appropriate values or
throw exceptions
* Changed unit tests to use Doctest's long macro names as the short
macro names clashed with Android's Logging macros
* Removed unused #includes
* Clarified ambiguous #includes
Signed-off-by: Mike Kelly <mike.kelly@arm.com>
Change-Id: Ice92a37590df727fd581d3be5ff2716665f26a13
|
|
* Add ConvertLogicalBinary
* Add support for LOGICAL_AND, LOGICAL_NOT, LOGICAL_OR
Signed-off-by: Narumol Prangnawarat <narumol.prangnawarat@arm.com>
Change-Id: I4dcecbebe031915b8c237fd5b9b92c8844847fb7
|
|
* Move ProcessActivation from Convert<LayerName>
to SetupAndTrackLayerOutputSlot by passing optional ActivationFn
* Connect Activation after IsTensorInfoSet() is called
Signed-off-by: Kevin May <kevin.may@arm.com>
Change-Id: I472bcb65b12ae6e934bd1e9af8a6f6aceb311c0e
|
|
* Enabled Dynamic Tensors in QUANTIZED_LSTM operator.
!android-nn-driver:3897
Signed-off-by: Sadik Armagan <sadik.armagan@arm.com>
Change-Id: I415014d19729aac255479099e372e5ff1a6dd3e2
|
|
* ConvertToActivation
* ConvertAdd
* ConvertArgMinMax
* ConvertConv2d
* ConvertDepthToSpace
* ConvertDepthwiseConv2d
* ConvertDiv
* ConvertFloor
* ConvertFullyConnected
* ConvertL2Normalization
* ConvertLocalResponseNormalization
* ConvertMean
* ConvertMul
* ConvertPad
* ConvertReshape
* ConvertSub
* ConvertStridedSlice
* ConvertTranspose
* ConvertBatchToSpaceNd
* ConvertSpaceToBatchNd
* ConvertComparison_1_2
* ConvertConv2d_1_2
* ConvertDepthwiseConv2d_1_2
* ConvertElementwiseUnary
* ConvertExpandDims
* ConvertGather
* ConvertGroupedConv2d
* ConvertInstanceNormalization
* ConvertLogSoftmax
* ConvertMaximum
* ConvertMinimum
* ConvertPadV2
* ConvertPrelu
* ConvertQuantize
* ConvertResize
* ConvertSpaceToDepth
* ConvertSoftmax
* ConvertTransposeConv2d
Signed-off-by: Finn Williams <Finn.Williams@Arm.com>
Signed-off-by: Teresa Charlin <teresa.charlinreyes@arm.com>
Signed-off-by: Kevin May <kevin.may@arm.com>
Change-Id: Idacf16e5eab56d83fce293570bbc89381ae056dc
|
|
!armnn:3330
Signed-off-by: Finn Williams <Finn.Williams@Arm.com>
Change-Id: Icc429d9fabb570193d12bffef0e00dda7b51032f
|
|
* Added FILL operator support to HAL 1.3 Driver
!armnn:3447
Signed-off-by: Sadik Armagan <sadik.armagan@arm.com>
Change-Id: I271151857d805e8159b9dd675bd6e9e99e6ff69d
|
|
* Input 30 for QLSTM is zero point of the hidden state, ANEURALNETWORKS_INT32
* Input 31 for QLSTM is the scale of the hidden state, ANEURALNETWORKS_FLOAT32
Signed-off-by: Sadik Armagan <sadik.armagan@arm.com>
Change-Id: I1c6304fa4772895ce57286b58b2c3363c25c38e2
|
|
* Add QLSTM support for Android NN Driver
* Add overrideOutputInfo parameter to SetupAndTrackLayerOutputSlot
* Add optional condition to GetInputScalar
* Refactor Quantized 16 Bit LSTM impl
Change-Id: Ie8fa98ad5ee4a62174ef91ca80f1df62b7fde937
Signed-off-by: Keith Davis <keith.davis@arm.com>
Signed-off-by: Sadik Armagan <sadik.armagan@arm.com>
|
|
* Read alpha parameter for ELU operation
* Created ConvertionUtils_1_3 for 1.3 Driver
* Added QAsymmS8 data type support to swizzle the tensor
Signed-off-by: Sadik Armagan <sadik.armagan@arm.com>
Change-Id: I9d66a4e8d5468efa305bb8f6c352f13d27602274
|
