Age | Commit message (Collapse) | Author |
|
* Add ConvertFloat32ToBFloat16
* Add ConvertBFloat16ToFloat32
* Add BFloat16Encoder
* Add BFloat16Decoder
* Unit tests
Signed-off-by: Narumol Prangnawarat <narumol.prangnawarat@arm.com>
Change-Id: I198888384c923aba28cfbed09a02edc6f8194b3e
|
|
* Added Quantization Scheme for QAsymmS8
* Added Unit Tests for QAsymmS8
* Renamed QAsymm8 calls to QAsymmU8
Signed-off-by: Ryan OShea <Ryan.OShea2@arm.com>
Change-Id: I897b4e018ba1d808cc3f8c113f2be2dbad49c8db
|
|
!android-nn-driver:2622
Change-Id: If99d3eff71ff66ba28af1e5af248299fe04511b9
Signed-off-by: Derek Lamberti <derek.lamberti@arm.com>
|
|
!android-nn-driver:2572
Change-Id: I8fe52ceb09987b3d05c539409510f535165455cc
Signed-off-by: Derek Lamberti <derek.lamberti@arm.com>
|
|
!android-nn-driver:2435
Signed-off-by: Finn Williams <Finn.Williams@arm.com>
Change-Id: I10ecd4a8937725953396805f33a3562a5384c4d4
|
|
* 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
|
|
* Added ScaledInt32PerAxisDecoder implementation
* Added new case for Signed32 in MakeDecoder that returns a
ScaledInt32PerAxisDecoder if the tensor info has multiple
quantization scales
Signed-off-by: Aron Virginas-Tar <Aron.Virginas-Tar@arm.com>
Change-Id: I8b3c11091644da993044d2a0fe2aba6b06b5af56
|
|
* Add QuantizedSymm8PerAxis to armnn DataType (types.hpp) and
* Add Quantize and Dequantize template for int8 in TypeUtils to be able to compute QSymm8 of the weight
* Create PerAxisIterator for per-axis quantization
* Create QSymm8PerAxisDecoder
* Create QSymm8PerAxisEncoder
Signed-off-by: Keith Davis <keith.davis@arm.com>
Change-Id: Ibcfe0288a197b7ee50b543bdbd77b7edb8a547c2
|
|
* Implement Float 16 Encoder and Decoder
* Add Stack Float 16 layer and create workload tests
Signed-off-by: Matthew Jackson <matthew.jackson@arm.com>
Change-Id: Ice4678226f4d22c06ebcc6db3052d42ce0c1bd67
|
|
* Added Int32Decoder and Int32Encoder to decode INT32 tensors
* Changed MakeDecoder to return ScaledInt32Decoder only
if the scale is different from 0, i.e. for quantized bias
tensors
Signed-off-by: Aron Virginas-Tar <Aron.Virginas-Tar@arm.com>
Change-Id: I278061d445d1c549c7ace11f51aa172ce7c691ae
|
|
Change-Id: I445c69d2e99d8c93622e739af61f721e61b0f90f
Signed-off-by: Matthew Bentham <Matthew.Bentham@arm.com>
|
|
* Refactor FullyConnected workloads into single workload.
* Refactor FullyConnected ref implementation to use Encoders
and Decoders to support all DataTypes.
* Deleted RefFullyConnectedFloat32Workload and
RefFullyConnected2dUint8Workload.
Change-Id: Iad30fb0287ab7491e1297997e7d61f1d00785541
Signed-off-by: Francis Murtagh <francis.murtagh@arm.com>
|
|
* Refactored RefConvolution2dWorkload to support all DataTypes through Encoders and Decoders.
* Added Convolute function to ConvImpl that uses Encoders and Decoders to support all DataTypes.
* Deleted RefConvolution2dFloat32Workload and RefConvolution2dUint8Workload.
Signed-off-by: Mike Kelly <mike.kelly@arm.com>
Signed-off-by: Teresa Charlin <teresa.charlinreyes@arm.com>
Change-Id: Ic5ef0f499d08b948fa65fdee54b5f681fd0b1c05
|
|
Change-Id: Ia3b9a56787cc68822a3c1635de82e03ecc0aae27
Signed-off-by: Nattapat Chaimanowong <nattapat.chaimanowong@arm.com>
|
|
+ Added PostAllocationConfigure() method to workload interface
+ Elementwise function now deduces types based on Functor
- Replaced RefComparisonWorkload with RefElementwiseWorkload specialization
+ Fixed up unit tests and minor formatting
Change-Id: I33d08797767bba01cf4efb2904920ce0f950a4fe
Signed-off-by: Derek Lamberti <derek.lamberti@arm.com>
|