Age | Commit message (Collapse) | Author |
|
!android-nn-driver:2435
Signed-off-by: Finn Williams <Finn.Williams@arm.com>
Change-Id: I10ecd4a8937725953396805f33a3562a5384c4d4
|
|
* Create a public API for the common backend files
* Move OutputHandler to armnn internal
* Remove unused headers
Signed-off-by: Matteo Martincigh <matteo.martincigh@arm.com>
Signed-off-by: Narumol Prangnawarat <narumol.prangnawarat@arm.com>
Change-Id: I3e86d908b021e3561befa9d45158d87d2cbb18c0
|
|
to per-axis case
Signed-off-by: Aron Virginas-Tar <Aron.Virginas-Tar@arm.com>
Change-Id: I66a8360b6d86e95325dee58927dcbe62ccf6ad58
|
|
* Add Guid to Workload
* Remove circular dependency
Signed-off-by: Narumol Prangnawarat <narumol.prangnawarat@arm.com>
Signed-off-by: janeil01 <jan.eilers@arm.com>
Change-Id: I15342fa7481c6bdc050e057dce2d74bba07fe2dd
|
|
* Fixed numerous CTS/VTS failures related to Quantization
Signed-off-by: Mike Kelly <mike.kelly@arm.com>
Change-Id: If5c20256366e80b6b9bbc46b2a1c410a9b8c48e1
|
|
* Added support for QuantizedSymm8PerAxis to ArmComputeTensorUtils.
Signed-off-by: Mike Kelly <mike.kelly@arm.com>
Change-Id: Ib8662f216bc4b6b54e0099780f73bcf6ef05384b
|
|
Signed-off-by: Aron Virginas-Tar <Aron.Virginas-Tar@arm.com>
Change-Id: I0bb0e9da306eee3e19dc9967a6c8bb01da998deb
|
|
Signed-off-by: Jammy Zhou <jammy.zhou@gmail.com>
Change-Id: I12562c4a9671cd43884e7c0c023ca463a99c3aa2
|
|
* Enable fp_mixed_precision flag for the failing test case
Signed-off-by: Sadik Armagan <sadik.armagan@arm.com>
Change-Id: If13552165eb6598a84d213b82847b56a8c5f2783
|
|
* Update ACL pin to include change of ArgMinMax NEON/CL output type to Signed32
!android-nn-driver:2013
Signed-off-by: Narumol Prangnawarat <narumol.prangnawarat@arm.com>
Change-Id: I2a0c80e0557f619a213790027efca8b84bf6e58a
|
|
The following NeuralNetworkTests tests were failing on GpuAcc and CpuAcc:
GeneratedTests.softmax_v1_2_relaxed
GeneratedTests.softmax_v1_2_quant8
GeneratedTests.softmax_v1_2_2
GeneratedTests.softmax_v1_2_relaxed_2
GeneratedTests.softmax_v1_2_quant8_2
The default value for Softmax axis parameter in Android is -1 but is 1 in ACL.
Detect and handle this in ArmComputeUtils.ComputeSoftmaxAclAxis.
Signed-off-by: Colm Donelan <Colm.Donelan@arm.com>
Change-Id: Ibb0660e4cb0dc6bd4c804c4397fbd61f38acdd9c
|
|
* Increased MaxNumOfTensorDimensions and fixed issues related to its use
* Fixed issues caused by assuming 5d tensors are invalid
* Updated ArmComputeTensorUtils for 5d tensors
* Added 5d tensor unit tests for add, mul, stack and reshape (needed by IVGCVSW-3527)
Signed-off-by: Matthew Jackson <matthew.jackson@arm.com>
Change-Id: I5bcd64942d0d04efcc6c5acb240ad4b88e010743
|
|
* Pad value for QASYMM8 is no longer stored in quantized form.
Signed-off-by: Mike Kelly <mike.kelly@arm.com>
Change-Id: I048e1d233353c0560ae03a7cc1ed5199295352bc
|
|
Signed-off-by: Aron Virginas-Tar <Aron.Virginas-Tar@arm.com>
Change-Id: I7f4c722141837939fd8904c52e75704a15c8a5e3
|
|
Use it for intermediate tensors on reference backend.
Lays the groundwork for memory management in the reference backend.
Change-Id: I7d3ee132cac31bde70ae6e1b815f4f0b03d550a6
Signed-off-by: Matthew Bentham <Matthew.Bentham@arm.com>
|
|
Signed-off-by: Aron Virginas-Tar <Aron.Virginas-Tar@arm.com>
Change-Id: I3b021c0828d30298d99ddb211c9aae17fe3636f0
|
|
* Added backend support for multiple types of TensorHandle factories
* Refactored the backend API to enable new tensor strategies
* Added mechanism to determine memory strategies during optimization
* Perform mem-copy only when Direct access is not found
* Explicitly deleted the copy-constructor from OutputSlot to prevent
accidental local copies that would cause the DisconnectAll to be
called by the destructor
Change-Id: I7e812c8e5e6c1c20db1c5932749ac70fd93db7f8
Signed-off-by: Derek Lamberti <derek.lamberti@arm.com>
Signed-off-by: Matteo Martincigh <matteo.martincigh@arm.com>
|
|
Change-Id: Ia68da09d8f0fb0a04af9cb61062d7edaa5f1b887
Signed-off-by: Derek Lamberti <derek.lamberti@arm.com>
|
|
* Add check if Sub-tensors cannot be used, call ACL function
* Add computation of SplitAxis from SplitterDescriptor
* Add NeonSplitterWorkload functions
* Modify IsSplitterSupported to call ACL validate function
if sub-tensor cannot be used
* Also check if quantization parameters match when using sub-tensors
* Add more unit tests for Splitter in TfParser and TfLiteParser
Signed-off-by: Narumol Prangnawarat <narumol.prangnawarat@arm.com>
Change-Id: I31e4c7d055117c83c65b598c4125442173242226
|
|
!android-nn-driver:968
Signed-off-by: Aron Virginas-Tar <Aron.Virginas-Tar@arm.com>
Change-Id: I03ccb4842b060a9893567542bfcadc180bbc7311
|
|
* Compute Softmax Acl axis for Cl and Neon
* Add unittests for Softmax in 3D and 4D
* Correct input and output layer names in CaffeSqueezeNet inference test
Change-Id: I2d369d9a2db19c40f2af3341039dd33f0c5637b1
Signed-off-by: Narumol Prangnawarat <narumol.prangnawarat@arm.com>
|
|
no longer work
* Added two master variables ARMNN_COMPUTE_CL_ENABLED and ARMNN_COMPUTE_NEON_ENABLED
to android-nn-driver/Android.mk to easily control backend support
* Setting either of those two new variables then properly sets the
corresponding build macro
* If a specific backend gets disabled, the corresponding source files
will be excluded from the build
* Unified the usage of the pre-compile macros
!android-nn-driver:613
Change-Id: I582ff73493b70ba9e22ca2e38d875a0f19566c8a
Signed-off-by: Matteo Martincigh <matteo.martincigh@arm.com>
|
|
Change-Id: I0ab3339e8803a3e4e700d8fec9883eccc524b31e
|
|
separate branch) and master
* Brings in all the changes done for the pluggable backends
* Added sub-graph support and tests
* Added precompiled layer support and tests
* Moved BackendSettings to a separate file
* Removed the backend-specific code
* Ported DebugLayer and associated functionality
* Included fixes to make those changes work with master
Change-Id: Id7028fa7917527b844628d5aff5732e3d94c0488
|
|
* Unified ArmNN's weight format to [ M, I, H, W ] for the depthwise convolution
* Added conversion utilities to permute/reshape the weights as appropriate
when using CL and Neon backends
* Updated the reference implementation of the convolution
* Updated the relevant unit tests accordingly
!android-nn-driver:459
Change-Id: I07d0818efa9d1ca1e5dad82983aac1fe78eadb18
|
|
Factor out new BuildArmComputeReductionCoordinates function
from CL backend into ArmComputeTensorUtils.
Update NEON LayerSupport and WorkloadFactory objects
Change-Id: Icc975ec699199bffafbdb207323df509d35e1e04
|
|
!android-nn-driver:428
Change-Id: I42e59ad96d2c80f46b085182855d34b710a74dfe
|
|
This is one of the reasons why the tests in https://review.mlplatform.org/#/c/ml/armnn/+/237/
are failing (but not the only reason).
Change-Id: If485bade2a6dd013cba826cec71d748fc7747249
|
|
Change-Id: Ie2f134fd51de919c50fa9d8d82bbb4ed4ee46469
|
|
Change-Id: Idc0f94590566ac362f7e1d1999361d025cc2f67a
|
|
Change-Id: I93223c8678165cbc3d39f461c36bb8610dc81c05
|
|
* Added quick workaround for the memory management errors in the
CL/Neon unit tests
Change-Id: I56250db462cdbdc1acc0a5824807d288fb0c1d11
|
|
Change-Id: I663a0a0fccb43ee960ec070121a59df9db0bb04e
|
|
as backend sources
Change-Id: Icafc644b64c591f4dc0e1560d02b806bf053a2da
|
|
Change-Id: I8d34419742152edd50f1ec438e32d3ccc4f38351
|
|
!android-nn-driver:153490
Change-Id: I1c2a5f942e3a1c3626e093c90545ca27c64ba5e8
|
|
Change-Id: Ie1c74a18de5c3dd1cd5285c222bd6327489c1508
|
|
Change-Id: I558a9a007604afc55e536d877f8da7d0215cc9c3
|
|
* Added NHWC unit test implementation
* Programmatically selected the channel dimension when creating
the ACL Normalization layer info
* Set the input/output data layout in the constructor of the L2Normalization
workload
Change-Id: Ie69f1a360022c29d1a3a3808c1f26b69243fa8f9
|
|
Change-Id: I15e689a6288b8476db7e67d7153899814c3cdf9e
|
|
Change-Id: I400be8e7c0cc5a31eb9d2a7396da145d50d51b6e
|