Age | Commit message (Collapse) | Author |
|
* This change is necessary because tflite uses a [1,H,W,I*M] format
and uses the I*M dimension for per axis quantization. Our previous
layout [M,I,H,W] can't handle the correlating quantization scales.
* Updates Onnx-, TfLiteParser and TfliteDelegate
* Updates the CpuRef, CpuAcc and GpuAcc backends
* Adjusts unit tests
* Adds test to ensure models with old layout can still be read and
executed
* Adds conversion function to previous layout [1,H,W,I*M] --> [M,I,H,W]
which can be used by backend developers
!android-nn-driver:5553
Signed-off-by: Jan Eilers <jan.eilers@arm.com>
Change-Id: Ifef23368b8c3702cf315a5838d214f7dc13c0152
|
|
* Replaced all instances of boost::multi_array with flat vectors.
* Updated LayerTestResult struct with new member variables.
* Updated CompareTensor function to compare flat vectors and the shape.
* Removed MakeTensor function from TensorHelpers.hpp.
* Removed GetTensorShapeAsArray function from LayerTestResult.hpp.
* Removed boost::array usage.
* Removed boost::extents usages.
* Removed boost::random usages.
Signed-off-by: Matthew Sloyan <matthew.sloyan@arm.com>
Signed-off-by: Sadik Armagan <sadik.armagan@arm.com>
Change-Id: Iccde9d6640b534940292ff048fb80c00b38c4743
|
|
* Generalises ConstCpuTensorHandle and inherited
classes by removing 'Cpu' from aliases.
* New renamed classes: ConstTensorHandle, TensorHandle,
ScopedTensorHandle, PassthroughTensorHandle,
ConstPassthroughTensorHandle.
Signed-off-by: James Conroy <james.conroy@arm.com>
Change-Id: I1824e0e134202735fb77051f20a7252f161dfe16
|
|
* Floating point casts now use armnn::numeric_cast.
* Also removed remaining header imports.
Signed-off-by: Matthew Sloyan <matthew.sloyan@arm.com>
Change-Id: I2d37847d67f164fc0a0ae17f34d49ff3d2210c30
|
|
* Replaced with armnn/utility/NumericCast.hpp
* Some exclusions in reference backend
* Excluded as requires float implementation in NumericCast.hpp
Signed-off-by: Matthew Sloyan <matthew.sloyan@arm.com>
Change-Id: I9e4e9cd502c865452128fa04415fd6f250baa855
|
|
for all layers between C-D
Signed-off-by: Keith Davis <keith.davis@arm.com>
Change-Id: I9583adf50e67e63e73833f400d1c50fbff57f60c
|
|
Signed-off-by: Teresa Charlin <teresa.charlinreyes@arm.com>
Change-Id: I3c2c3d0c5d743b9faf05e6e9bcb4a9c9fd369ebc
|
|
* Remove redundant asserts for unsigned ints being positive
* Remove unneeded include of lightweight_test.hpp header
* Remove unused exception variable names
* Replace hardcoded 0.0f with T() for some template functions
* Add a few static_casts
Change-Id: I290b0433cf995f6d0199422eaa10f816e5fd8eb9
Signed-off-by: Robert Hughes <robert.hughes@arm.com>
|
|
operators
Signed-off-by: Teresa Charlin <teresa.charlinreyes@arm.com>
Signed-off-by: Sadik Armagan <sadik.armagan@arm.com>
Change-Id: I094125ba80699cc3cf5226bda6662a54e6caa988
|
|
* 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
|
|
* Modify SimpleConvolution2dNhwcTestImpl to allow different input and
out types
* Add unit tests for Conv2D with Bfloat16 input and Float32 output to
compare the accuracy with Float32 for small value inputs and big value inputs
Signed-off-by: Narumol Prangnawarat <narumol.prangnawarat@arm.com>
Change-Id: Ia59c92a22001b41f2681dafb951203a2223d3367
|
|
Signed-off-by: Narumol Prangnawarat <narumol.prangnawarat@arm.com>
Change-Id: Ifaae4d5aac468ba927b2c6a4bf31b8c8522aeb2e
|
|
!referencetests:229377
Signed-off-by: Jan Eilers <jan.eilers@arm.com>
Change-Id: Ia9b360b4a057fe7bbce5b268092627c09a0dba82
|
|
!android-nn-driver:2622
Change-Id: If99d3eff71ff66ba28af1e5af248299fe04511b9
Signed-off-by: Derek Lamberti <derek.lamberti@arm.com>
|
|
Signed-off-by: Matthew Bentham <Matthew.Bentham@arm.com>
Change-Id: Idb583f8de4470eefb47c90189cd3c90e74e0440a
|
|
!android-nn-driver:2572
Change-Id: I8fe52ceb09987b3d05c539409510f535165455cc
Signed-off-by: Derek Lamberti <derek.lamberti@arm.com>
|
|
Change-Id: If3d98e45a6e2fa8e1afd19a4052334335feacf63
Signed-off-by: Derek Lamberti <derek.lamberti@arm.com>
|
|
* 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
|
|
!android-nn-driver:2260
Signed-off-by: Teresa Charlin <teresa.charlinreyes@arm.com>
Change-Id: Iad93c1940568ffa65ed314c8871ea66caf4f9e4a
|
|
Convolution2d workload
Signed-off-by: Aron Virginas-Tar <Aron.Virginas-Tar@arm.com>
Change-Id: I0ac08ba4864d48e6f64c4ac645dad8ea850be112
|
|
* Moved QuntizeHelper.hpp to armnnUtils
* Reordered parameters for QuantizedVector and added default
values for qScale and qOffset to make life easier when
using the function for non-quantized types such as Float16
Signed-off-by: Aron Virginas-Tar <Aron.Virginas-Tar@arm.com>
Change-Id: I28c263dfa425f1316feccb4116839a84f5d568e5
|
|
Signed-off-by: Aron Virginas-Tar <Aron.Virginas-Tar@arm.com>
Change-Id: Icf39434f09fd340ad664cb3b97b8bee6d9da4838
|