Age | Commit message (Collapse) | Author |
|
* Reenabling support for NCHW for Convolution, Pooling and Resize.
Signed-off-by: Mike Kelly <mike.kelly@arm.com>
Change-Id: I6ceb1ab0983e19d200ba353b0017b0f0cd1628e0
|
|
Change-Id: If4fd1abdedf7de2046435d418fb1ee95ceb73419
Signed-off-by: FinnWilliamsArm <Finn.Williams@Arm.com>
|
|
Signed-off-by: Teresa Charlin <teresa.charlinreyes@arm.com>
Change-Id: I07c9ca1247ee823ed6411fb5a7df9245c1330c7c
|
|
This reverts commit b3680df4298a2f4d4ef8b637f35c3bc343b05339.
Signed-off-by: Kevin May <kevin.may@arm.com>
Change-Id: Iad15bb7360817eb91428681c05cfb065e317b4d0
|
|
Signed-off-by: Kevin May <kevin.may@arm.com>
Change-Id: I85ed84b818c15f402b220f223fb9e728e08dceed
|
|
Signed-off-by: Derek Lamberti <derek.lamberti@arm.com>
Change-Id: I4db6ea4ed0a192c85f124c4a9ced60b1666a3870
|
|
* Also re-enable NCHW on BatchToSpace, SpaceToBatch and Transpose Conv
Signed-off-by: Kevin May <kevin.may@arm.com>
Change-Id: I386eb3d852978e7cc611efad4f9f0c982140865a
|
|
Change-Id: Ib2a057d63a0722d90191ae69af2751cd03c33910
Signed-off-by: Pablo Tello <pablo.tello@arm.com>
|
|
* Re-enabled Float16
* Re-enabled Concatenation
Signed-off-by: Mike Kelly <mike.kelly@arm.com>
Change-Id: I03bbe978947d5282d50daa2ed9795d042dc93cb0
|
|
* Also fix segfault in previous graph dump code
Change-Id: I01915f47ae17d89ad3595430d073a17b1a1fda58
Signed-off-by: Jim Flynn <jim.flynn@arm.com>
|
|
* .dot file will start with the same number as the associated input
and output tensor dump files
Change-Id: Ic64539854c2b8c34a7034fa18a142b2dfe67df7d
Signed-off-by: Jim Flynn <jim.flynn@arm.com>
|
|
* Disable Concatenation and L2_POOL_2D in Hal 1.2
Signed-off-by: Mike Kelly <mike.kelly@arm.com>
Signed-off-by: Sadik Armagan <sadik.armagan@arm.com>
Change-Id: Ib3ac6702eb3e10d51be430c1c644c0e6398ee875
|
|
* Disabled support for NCHW
* Disabled support for Float16
Signed-off-by: Mike Kelly <mike.kelly@arm.com>
Change-Id: I0f5ee8a8ddda1edc7800f167d6a82e4a15c6069b
|
|
!armnn:2466
* Add calls before addition of these layers in ConvertConcatenation
* Add outputInfo parameter wherever needed for IsReshapeSupported
Signed-off-by: Kevin May <kevin.may@arm.com>
Change-Id: Ic5d142ea046161960ff2fc137bd261ebb4e6ac0c
|
|
Change-Id: Iff91ce6857a9f96a7af65f79883c1cbe59a15dd2
Signed-off-by: Jim Flynn <jim.flynn@arm.com>
|
|
Signed-off-by: Derek Lamberti <derek.lamberti@arm.com>
MLCE-143 Fix for reference implementation for service stopping when running CTS.
*ConvertDepthwise reports that weights are not supported with the first dimension of the tensor is not 1
*ConvertConcat was missing one case for reporting unsupported inputs.
Signed-off-by: Teresa Charlin <teresa.charlinreyes@arm.com>
MLCE-144 Cts NNAPI test cases failed
* Fixed numerous CTS/VTS failures related to Quantization
!armnn:2457
Signed-off-by: Mike Kelly <mike.kelly@arm.com>
MLCE-144 Fix 2d pooling convert function
Signed-off-by: FinnWilliamsArm <Finn.Williams@Arm.com>
Change-Id: I054635ebfd52cb5575490c3bfaae0104eb1685cc
|
|
* Removed unsupported operation sections
Signed-off-by: Mike Kelly <mike.kelly@arm.com>
Change-Id: I79216c5c015efeb5d2e19cd85f186c2f73bd1ca8
|
|
* Renamed the cl/neon backend macros to their original values, as
they were renamed by mistake
* Reverted misleading comment
* Updated the readme file
!armnn:1838
Change-Id: I49faabae2c8ad196f51eca5f8dd049ecf74b36e1
Signed-off-by: Matteo Martincigh <matteo.martincigh@arm.com>
|
|
* Renamed ARMCOMPUTEREF to ARMNNREF (and relative symbols) as the
previous name was misleading
Change-Id: Ia0400a7d63a76c80fb5bdd26410553db1c15cba0
Signed-off-by: Matteo Martincigh <matteo.martincigh@arm.com>
|
|
Signed-off-by: Ellen Norris-Thompson <ellen.norris-thompson@arm.com>
Change-Id: Ie3c535789186571df9000d75ad2a62ac8c94dcb4
|
|
* Templated AddPoolAndGetData and AddPoolAndSetData to accept different types
* Moved scale and offset to arguments of Add*Operand functions
Signed-off-by: Ellen Norris-Thompson <ellen.norris-thompson@arm.com>
Change-Id: Iaf4c2d5f4183ea54799bedae20950b23b914a727
|
|
Signed-off-by: Sadik Armagan <sadik.armagan@arm.com>
Change-Id: Ie222e046f2fe832ad48d4b2279c8815f860f76d5
|
|
* Added ARMNN_COMPUTE_REF_ENABLED to programmatically
build the reference backend
* Adjusted the makefiles to allow any backend combination to build
* Refactoring where necessary
Change-Id: I04cf23245971fcd460b776dd60e01cacb0458dab
Signed-off-by: Matteo Martincigh <matteo.martincigh@arm.com>
|
|
* Added IsReshapeSupported check on available backend(s) after adding Reshape layer.
Signed-off-by: Sadik Armagan <sadik.armagan@arm.com>
Change-Id: I38a36d5a3db0d67f0e4b4be2ef672dedb75bff22
|
|
* Added check for unsupported optional parameters for L2Normalization and LocalResponseNormalization to skip the related tests rather than fail them.
Signed-off-by: Mike Kelly <mike.kelly@arm.com>
Change-Id: Ia17be706b14b2e2faf8eb5a0ec335c2e3863bf16
|
|
* Templated and moved V1.0 and V1.1 Convert methods to ensure they can work with later versions of models, operations and operands.
* The V1.2 HalPolicy no longer converts V1.2 models, operations and operands to earlier versions.
* The V1.2 HalPolicy no longer passes operations to the V1.1 or V1.0 HalPolicies for conversion.
Signed-off-by: Mike Kelly <mike.kelly@arm.com>
Change-Id: I5de59d43a3abb1f8ac0253dc637ad68318960c76
|
|
* Fixed TransposedConv2d failures
calculateExplicitPaddingTransposeConv expects int32_t.
Signed-off-by: Sadik Armagan <sadik.armagan@arm.com>
Change-Id: I6ea9ea2d1ccfd17debcf93ee518287a083815f01
|
|
* Updated the makefiles to include boost::filesystem
!armnn:1702
Change-Id: Ibe0a696d9fd473b552602266a89465289e9dc043
Signed-off-by: Matteo Martincigh <matteo.martincigh@arm.com>
|
|
* PReLU layers were being skipped due to logic error.
Resubmitting due to accidental reversion.
Signed-off-by: Mike Kelly <mike.kelly@arm.com>
Change-Id: I6aeed11519d19ba7ec8b4993694e414f58799028
|
|
Signed-off-by: Narumol Prangnawarat <narumol.prangnawarat@arm.com>
Change-Id: I3ef659c8b87f2c0a3d3ed5d14f74f3b05a9f94b9
|
|
* Added conversion method to HAL1.2 Policy
Signed-off-by: Ellen Norris-Thompson <ellen.norris-thompson@arm.com>
Change-Id: Ida6734d34931148add2f3464c3283191ea34b712
|
|
Change-Id: I6829921c08898865ce61ea1ae32eebdfe4a5c98c
Signed-off-by: Narumol Prangnawarat <narumol.prangnawarat@arm.com>
|
|
Signed-off-by: Narumol Prangnawarat <narumol.prangnawarat@arm.com>
Signed-off-by: Aron Virginas-Tar <aron.virginas-tar@arm.com>
Change-Id: I5c10ab18343ecf0ebeab24a436e5be2b6c2831c7
|
|
!armnn:1679
Signed-off-by: Aron Virginas-Tar <Aron.Virginas-Tar@arm.com>
Change-Id: I09e75e8182d647bd16b25a815812ca2b03ad7614
|
|
Signed-off-by: Aron Virginas-Tar <Aron.Virginas-Tar@arm.com>
Change-Id: I92700da149a800f1d8215e964d1e67056628f067
|
|
* Fixed Skipped VTS Concatenate Tests.
Signed-off-by: Mike Kelly <mike.kelly@arm.com>
Change-Id: I29e7dcdedefc0e9c54f86fa5de23aa714c469585
|
|
Signed-off-by: Finn Williams <Finn.Williams@arm.com>
Change-Id: I9d0d0a75d54c25075d8d87c6265e350486157f5c
|
|
* Renamed to be consistent with ConvertConv2d() and ConvertDepthwiseConv2d()
Signed-off-by: Aron Virginas-Tar <Aron.Virginas-Tar@arm.com>
Change-Id: Iaa872498e32129178bc3971cabf7f43bdb9962af
|
|
Signed-off-by: Finn Williams <Finn.Williams@arm.com>
Change-Id: Ibd683c147b6f2fb966a8f90105c9213880100cf8
|
|
Signed-off-by: Finn Williams <Finn.Williams@arm.com>
Change-Id: I3f2928ba86a9d306a7eb400db3a420e42cf3fa7e
|
|
Signed-off-by: Ferran Balaguer <ferran.balaguer@arm.com>
Change-Id: I7c0d704b53caeac3a950c6957c4cab11686f6793
|
|
Signed-off-by: David Monahan <david.monahan@arm.com>
Signed-off-by: Narumol Prangnawarat <narumol.prangnawarat@arm.com>
Change-Id: I7b855efaddb18e8f184f4b85196b3b95b69bca6e
|
|
Signed-off-by: Sadik Armagan <sadik.armagan@arm.com>
Change-Id: Ie7421078b2bdd16d7ac67b635953b34721e8c8fe
|
|
* A model that has Inputs with different quantized scales is not compliant with 1.1
Signed-off-by: Mike Kelly <mike.kelly@arm.com>
Change-Id: Ifb8277d78f05b5ef017effa879322a08c0efc851
|
|
ConvertDepthwiseConv2d()
* Removed code for reading data layout flag (only available in HAL1.2)
* Removed code for reading dilation parameters (only available in HAL1.2)
* Added more restrictive input size checks (== instead of >=, as none
of the inputs are optional in HAL1.0/1.1)
* Removed superfluous input size validation from 1.0/HalPolicy.cpp
Signed-off-by: Aron Virginas-Tar <Aron.Virginas-Tar@arm.com>
Change-Id: I8387120b9abcc8458f7fac6df577cb6453051be3
|
|
* PReLU layers were being skipped due to logic error.
Signed-off-by: Mike Kelly <mike.kelly@arm.com>
Change-Id: Ic0ec707da784b44d72958dee02901b0173b25e5c
|
|
* Adding LSTM processing function in HAL 1.2 with normalization parameters
* Refactoring LSTM tests
!armnn:1608
Signed-off-by: Ferran Balaguer <ferran.balaguer@arm.com>
Change-Id: I0e00f14ef078a333e9f2f23d6278a5d92a3001d6
|
|
hal_1_0::HalPolicy
* LocalResponseNormalization
* Mul
* SpaceToDepth
* ResizeBilinear
Signed-off-by: Aron Virginas-Tar <Aron.Virginas-Tar@arm.com>
Change-Id: Ie52dd7b274d721f0ca715ad92277e12e4c2b1913
|
|
Signed-off-by: Sadik Armagan <sadik.armagan@arm.com>
Change-Id: I9f9d11b19de591ec8936822ca229b4090ed318fe
|
|
* Report dynamic output tensors as unsupported for all operations,
regardless of HAL level
Signed-off-by: Aron Virginas-Tar <Aron.Virginas-Tar@arm.com>
Change-Id: I2341dc96be965886666b75515e9a226d813a1591
|