Age | Commit message (Collapse) | Author |
|
Change-Id: I2463c44e79e8df3dc081c645b2aa37468d5b9f0b
Reviewed-on: https://review.mlplatform.org/346
Tested-by: Arm Jenkins <bsgcomp@arm.com>
Reviewed-by: Anthony Barbier <Anthony.barbier@arm.com>
|
|
Change-Id: Ie0d5387c0546045e14e62c84c03894a9b0339585
Reviewed-on: https://review.mlplatform.org/335
Reviewed-by: Pablo Marquez <pablo.tello@arm.com>
Tested-by: Arm Jenkins <bsgcomp@arm.com>
|
|
Change-Id: I10696b7835eb8ab74ddd5611a278ac0b39d879ca
Reviewed-on: https://review.mlplatform.org/333
Tested-by: Arm Jenkins <bsgcomp@arm.com>
Reviewed-by: Anthony Barbier <Anthony.barbier@arm.com>
|
|
Change-Id: Ic9f3d3b4ed452efd1bea4d79d235350c8e521bc9
Reviewed-on: https://review.mlplatform.org/312
Tested-by: Arm Jenkins <bsgcomp@arm.com>
Reviewed-by: Giuseppe Rossini <giuseppe.rossini@arm.com>
Reviewed-by: Anthony Barbier <Anthony.barbier@arm.com>
|
|
-Removes shift from depth conversion tests.
-Changes Cast tolerance between float conversions to zero
Change-Id: I6c456f7d910eb3c02069f1e4d5df7b257d6d784e
Reviewed-on: https://review.mlplatform.org/341
Reviewed-by: Anthony Barbier <Anthony.barbier@arm.com>
Tested-by: Arm Jenkins <bsgcomp@arm.com>
|
|
Change-Id: I9bbe40f8c5c99dfc057d4d5ba4c2fcb193fc99f3
Reviewed-on: https://review.mlplatform.org/336
Reviewed-by: Anthony Barbier <Anthony.barbier@arm.com>
Tested-by: Arm Jenkins <bsgcomp@arm.com>
|
|
Change-Id: I3de6bb33746d52f8d8c337ab7776eccee8c205fb
Reviewed-on: https://review.mlplatform.org/328
Reviewed-by: Georgios Pinitas <georgios.pinitas@arm.com>
Reviewed-by: Pablo Marquez <pablo.tello@arm.com>
Tested-by: Arm Jenkins <bsgcomp@arm.com>
|
|
NELSTM, NEFullyConnectedLayer(For quantised types only), NERNN and NEWinogradLayer were all defaulting to on-the-fly reshaping of B
Fixed a bug in GemmInterleaved: it was ignoring the 'multis' dimension of the tensor to allocate the memory for B reshaped
Change-Id: I7b30f7f57fc65d6a03cccde0bf5515a811f17b54
Reviewed-on: https://review.mlplatform.org/323
Tested-by: Arm Jenkins <bsgcomp@arm.com>
Reviewed-by: Georgios Pinitas <georgios.pinitas@arm.com>
|
|
Change-Id: Ice653e48211053bd3cd20a693bd76de6b4efc370
Reviewed-on: https://review.mlplatform.org/270
Reviewed-by: Georgios Pinitas <georgios.pinitas@arm.com>
Tested-by: Arm Jenkins <bsgcomp@arm.com>
|
|
Change-Id: I7eae2e55cc0b0b7bbebb7617299daaca6f75f40c
Reviewed-on: https://review.mlplatform.org/292
Tested-by: Arm Jenkins <bsgcomp@arm.com>
Reviewed-by: Georgios Pinitas <georgios.pinitas@arm.com>
|
|
INESimpleFunctionNoBorder
Change-Id: Ia9fdc75b23e9a6208058f8406fb7b5fcd917de2c
Reviewed-on: https://review.mlplatform.org/311
Tested-by: Arm Jenkins <bsgcomp@arm.com>
Reviewed-by: Michele Di Giorgio <michele.digiorgio@arm.com>
|
|
Change-Id: I02a4ea0270e1776daf8ac1084f28dd054257be4a
Reviewed-on: https://review.mlplatform.org/309
Reviewed-by: Pablo Marquez <pablo.tello@arm.com>
Tested-by: Arm Jenkins <bsgcomp@arm.com>
|
|
Change-Id: I4e3269f1dc83ce9278230b6fc70a7981d05c61f6
Reviewed-on: https://review.mlplatform.org/315
Reviewed-by: Surabhi Mehta <surabhi.mehta@arm.com>
Tested-by: Arm Jenkins <bsgcomp@arm.com>
|
|
Fixed Segfault by removing bias iterator from specialized function which assumes no bias
being provided.
Change-Id: Ic897435ee9427d4359e8ab989a03e951da0d7ce0
Reviewed-on: https://review.mlplatform.org/314
Reviewed-by: Anthony Barbier <Anthony.barbier@arm.com>
Tested-by: Arm Jenkins <bsgcomp@arm.com>
|
|
Wrong check in the function
Change-Id: I38e4d5f01039c8352c0e83f0711455af85f9c3fe
|
|
Change-Id: I3f8175538152cd801c8ed4244a8ae3f75d182997
|
|
Adds support for Equal,NotEqual,Less,LessEqual,Greater,GreaterEqual
Change-Id: If0cdf4aae7f95c94709b195eee485f6663f45909
|
|
Change-Id: I2a18f0acea382960a8bc71a8f56928a5998f0dd6
|
|
Change-Id: Icadce1298f9e52dc6f4b0adc1556ede9dd9a2a2e
|
|
Change-Id: Id74cc7ba8e5cabee6acd3798d4779f88b1f00a9b
|
|
Change-Id: I49b2e8b4200c9ed654736d9451e4ab9c073b4b10
|
|
-Fixes NEWinogradConvolution memory manager usage
-Moves allocations in prepare staged for GEMMDispatchWrapper.
Change-Id: Ic1c709ee473eb4968f5a081f2bc26960f882f8db
|
|
Change-Id: I9d4ba7d00d50a84f650f0449faa8a25226068fed
|
|
Change-Id: I29e35024e29781a6b943b568abec9c73649215e6
|
|
Change-Id: I6ee2c0b670727fc808fa636c53ddfaec3a0036c9
|
|
Change-Id: I49f1d865f5e7562f1d80db849353a89ef77e6a9e
|
|
Output of Priorbox should be independent of the input
data layout and should always be in NCHW format
Change-Id: Ie80cd4e51c78945b158c0db1af1923bdf8d7ea7b
|
|
Change-Id: I95fdf5bd85becfe081f6ae587284f3b294681308
|
|
Change-Id: I62d937533967b29505d3ac8a51b513f0c6de8cd0
|
|
Fixes for:
- ReduceMean, reduction on the X axis for FP16 with 8 elements was
performed only up to a certain point. The fix now takes into account the
number of elements of the vector and does as many reductions as
necessary.
- YOLOLayer, activation for FP16 has to be performed on 32 bits until
the FP16 approximations is fixed.
Change-Id: I75373f4edd37de476e6fe1a56de3ef386b65c619
|
|
NHWC reduction on 0 axis requires a lot of memory. Testing only
axis 1 and 2 for now.
Change-Id: I82e16a27b6dfc6b426e6294cde63c3d88cb41a09
|
|
-Simplifies import memory interface
-Changes the used of void** handles with appropriate interfaces.
Change-Id: I5918c855c11f46352058864623336b352162a4b7
|
|
-Adds NHWC support for FP16
Change-Id: I61addf8efecf511ac8cd5f8aa9afc3e09c476aaf
|
|
Changed random distribution to [1, 2] as values close to
zero generate mismatches.
Change-Id: I4a00fc4f445b123dea624dd8459efce945f06126
|
|
Change-Id: I376d29aa6ec1b52d978c4d49de63c6713d6036e3
|
|
FP mixed precision support added to GEMM kernel used for fp16 winograd conv on Midgard GPUs
Change-Id: I1619beb025fc484a1ac9d3e528d785edabbc7ee6
|
|
Change-Id: I770b044b67d93510ef65e556905135b34be7ea0a
|
|
Change-Id: I5f99e448e208be6ca819bf4ab2c7b367c874d3f5
|
|
Change-Id: I4c84a3156114d973fcff22a6b86a3c0044502fc8
|
|
Change-Id: I6e7dee8bd615a5eff01c523f208a218574ee5eab
|
|
Change-Id: Ieb6f0638174ea1deb8b457d8df81511651a246a9
|
|
kernels
Change-Id: I98183f95814442b6f3dbb67a1bdae99df05b9b01
|
|
Change-Id: I88c4a3b55943ed3bcf63cad63b0c7570770c2056
|
|
Change-Id: I54a3f34aa3657396e931f18c81af2941d3b56903
|
|
Change-Id: I5d2ed5dcc342abff8124762f7bdee587cdf20032
|
|
- Fixing a bug for which we did not scale the boxes before transforming them
- Adding the correct_transform_coords option to BoundingBoxTransformInfo
Change-Id: I40281254bcf87e7c8583c119e99562414fe59822
|
|
BoxWithNMSLimitKernel
COMPMID-1792: Accuracy issue in CLGenerateProposals
This patch does the following:
- Some fixes for GenerateProposals function and tests
- Adapting BoxWithNMSLimitKernel to only accept U32 tensors as keeps_size
- Update 3rdparty
- Adds a small tolerance for a GenerateProposals test
Change-Id: Ia8ec1cdfe941fe05003645e86deb9ea6a6044d74
|
|
Introduced F32 accumulation for F16 winograd gemm and output transform
WinogradConvolution will be available for F16 only if fast math flag is enabled
Change-Id: I215593c205236a0f9669218437bb40b184ec6a4f
|
|
With this patch we are able to dispatch a single GPU job also in case of
batched-flatten
Change-Id: I755e7af29d44b24f67fa04bad3c9b7646e8deefc
|
|
Increase tolerance for FP16
Change-Id: I88f95da5471bbceb7449f453e2e33cf0bc4da23e
|