Age | Commit message (Collapse) | Author |
|
Adding constraint for faulty reshape operators. Number of elements
for IFM and OFM must be the same.
Change-Id: I2e31e9d1e39b5aa3a0c595032a66e14374a0719e
Signed-off-by: Johan Alfven <johan.alfven@arm.com>
|
|
- Updated release notes for 3.7.0
- Updated tag in SUPPORTED_OPS and setup.py
- Tidied up README
Change-Id: Ib33a3d85383ce297b10acd74f8a2455d738276be
Signed-off-by: Tim Hall <tim.hall@arm.com>
|
|
Reinstate constraint for stride height to (1,3) instead of (1,4) for
Conv2D and update unit tests.
Change-Id: I17389ee040eeff0cea08279cab1c038e951569ea
Signed-off-by: Raul Farkas <raul.farkas@arm.com>
|
|
* Extend stride range from (1,3) to (1,4)
* Add stride 4 support when optimising CONV_2D
* Add some tests for various strides
Change-Id: Iddaeb42c4a6e02695ecdd3740bc8b9dd59a7eb3c
Signed-off-by: Raul Farkas <raul.farkas@arm.com>
|
|
- An assert in Vela is triggered when the number of splits does
not evenly divide the input.shape[axis] value and the split offsets
are calculated wrongly.
- The fix is to add the same constraints as in the reference kernel
and only run the Split op on the NPU when the criterias are fulfilled.
- Modified test to reflect the new constraints
- Updated SUPPORTED_OPS.md
Change-Id: I4103ff4a3fdf9a813f5fcb7f51081b859e611100
Signed-off-by: Johan Alfven <johan.alfven@arm.com>
|
|
- Only 1D bias shape is supported
- Modified test to reflect the constraint
- Update SUPPORTED_OPS.md
Signed-off-by: Johan Alfven <johan.alfven@arm.com>
Change-Id: I00ae4b229d5f89512cb94f87f276af61cc66a6fd
|
|
- Update SUPPORTED_OPS.md with release version
- Update setup.py with release version
- Update RELEASES.md with release notes and comments
Change-Id: If5cd5525d8a52a13245940bfbb262db8c9e13003
Signed-off-by: Rickard Bolin <rickard.bolin@arm.com>
|
|
- Added graph optimisation pass to support dilations greater than 2
in either dimension
- Removed supported operators restrictions
- Removed erroneous dilation on TRANSPOSE_CONV
- Updated unit tests and documentation
Signed-off-by: Tim Hall <tim.hall@arm.com>
Change-Id: Ide302374b0d5eff25c20501383a63f6aa7625c52
|
|
The reference kernel for the MEAN operator has changed.
As a result, the mean implementation can be simplified
and the constraint for mean int8 can be removed.
Signed-off-by: Johan Alfven <johan.alfven@arm.com>
Change-Id: I318e9b495eefea99e7ac4aea4b8c436c83753405
|
|
- The op contained supported operator checks for both the stride being
in the range 1 to 3, and being equal to 2. Whilst both are correct, only
the later is needed
- Removed the stride in the range 1 to 3 check for TRANSPOSE_CONV
- Regenerated the documentation
Signed-off-by: Tim Hall <tim.hall@arm.com>
Change-Id: I9789cdbd3ed65ce310f1529036abbac62296d2ca
|
|
- Removed half pixel centers constraint for resize nearest neightbor.
- Supported scale 2x, 4x and 8x.
- Removed test_constraint_resize_half_pixel_centers
- Regenerated SUPPORTED_OPS.md
Signed-off-by: Johan Alfven <johan.alfven@arm.com>
Change-Id: Ic3e02e9c2b2034d537c9a9841b8fb4ee433c96dc
|
|
The test failed since the tanh had batch size > 1.
Added checks for batch size for all supported operators.
Signed-off-by: Fredrik Svedberg <fredrik.svedberg@arm.com>
Change-Id: I3570352740c40eb96bd9db965dfa3c91c81ff2ad
|
|
Setting bias tensor dtype to DataType.int32 solves rounding issues for
RB HPC int16.
Removing the input data type check also solves the issue of resize
nearest neighbor int16 ops incorrectly getting placed on the CPU.
Signed-off-by: Rickard Bolin <rickard.bolin@arm.com>
Change-Id: Iee352bcb78e581c0cde3c203dfbe866f1f6fae18
|
|
- Added support for Resize Bilinear with half pixel centers for int8 and
uint8.
- Utilizes the new "TILE" padding mode.
- Utilizes ofm stride multipliers and modified tile base offsets to
write OFMs interleaved.
Signed-off-by: Rickard Bolin <rickard.bolin@arm.com>
Change-Id: I37fa77c022a368f05fda0ead75d8696c9205f833
|
|
- Updated SUPPORT_OPERATORS.md with Resize operators
- Updated release notes with the main changes and bug fixes
- Updated version numbers
Signed-off-by: oliper01 <oliver.perssonbogdanovski@arm.com>
Signed-off-by: Tim Hall <tim.hall@arm.com>
Change-Id: If25b5fab708098bc3e7eb243924b55a50f148c3a
|
|
Added SHAPE operator to the supported operators report.
Updated the constraints for QUANTIZE and SHAPE operator.
Also fixed RESHAPE consuming statically optimised shape.
Signed-off-by: Fredrik Svedberg <fredrik.svedberg@arm.com>
Change-Id: I1d964d602d3f361a0f16dae8133197280dd84c48
|
|
*Quantise op becomes constant if input is known at compile time
*Quantised values calculated if input of op is const and float
*Const inputs to quant op that are int are requantized
Change-Id: Ic94a72a392af709fe6a640d7dacbb5dc2334f16f
Signed-off-by: Ayaan Masood <Ayaan.Masood@arm.com>
|
|
*Shape OP value is available at compile time hence
it can be optimised
*Disconnected shape OP at compile time from parent
tensor
*Transformed shape OP tensor into constant
Change-Id: I0a024269e2b592c6146dd72e62d7a41951fb727a
Signed-off-by: Ayaan Masood <Ayaan.Masood@arm.com>
|
|
- Updated release notes and setup.py tag for 3.4
- Regenerated supported ops information
Signed-off-by: Tim Hall <tim.hall@arm.com>
Change-Id: I4ec88544b84cab168cb3e5cbc6bc392b6b3d8a39
|
|
- Bump minor release version and add release notes
- Update README and SUPPORTED_OPS versions
Change-Id: Ic14d028483c12d281e69515b25f66346d9a3afeb
Signed-off-by: James Peet <james.peet@arm.com>
Signed-off-by: Tim Hall <tim.hall@arm.com>
|
|
Updated constraints affect:
- Constant tensors
- MEAN operations
- RESIZE_BILINEAR operations
Signed-off-by: James Peet <james.peet@arm.com>
Change-Id: I2a041fa2300a9ba6da048cc61e164f34897b2f50
|
|
This commit updates the release notes for Vela
version 3.2.0.
It also updates the SUPPORTED_OPS.md file with new
constraints.
Updated the API version as a result of the bug fix
commit 399c4a2d77df791e5d988c51d7fb1824ac4f266f.
Updated Vela version in setup.py.
Signed-off-by: Dwight Lidman <dwight.lidman@arm.com>
Change-Id: I181e89f639a1da6013e8511ebe2d7e4f81242916
|
|
Fixed by adjusting zero points for ops with int8 IFM and asymmetric weights
since the reference does not support asymmetric weights for int8 IFM and
ignores the zero points.
Signed-off-by: Fredrik Svedberg <fredrik.svedberg@arm.com>
Change-Id: I2a206a01a471a53aa864a6a3616aa23d2a5a23c8
|
|
Memory only operators such as Reshape, Squeeze and ExpandDims are
removed in the graph optimiser step.
- Added semantic check that memory only operators have same
quantisation parameters on ifm/ofm.
- Added support for the ExpandDims operator.
- Addition and cleanup of related unit tests.
- Removed TOSA from the generated SUPPORTED_OPS.md documentation.
Signed-off-by: Jonas Ohlsson <jonas.ohlsson@arm.com>
Change-Id: If848d8afc58c18806e10997ed94e4dae83f30879
|
|
Fix inception_v1/v3 output diffs.
Removing the Squeeze operator in the graph optimisation step.
The squeeze operator removes dimensions of size 1 from tensor shape.
The memory layout is preserved.
Signed-off-by: Jonas Ohlsson <jonas.ohlsson@arm.com>
Change-Id: I4ceffcbb141af5ed50b0d1a9d1d67622e638c2a1
|
|
Refactor supported operators by breaking out model semantics
into its own class. Model semantics checked right after model
read.
Signed-off-by: Jonas Ohlsson <jonas.ohlsson@arm.com>
Change-Id: If442b189efcd91dda01af60b2b3adedfacdf2fad
|
|
This is a small commit which changes one of
the four MEAN implementations to a simpler
one, using an AvgPool instead of a
DepthwiseConv.
Signed-off-by: Dwight Lidman <dwight.lidman@arm.com>
Change-Id: I9e8af071e8b820796577ee4792b4812a1212602b
|
|
This commit adds support for emulating the behavior
of the QuantizedMeanOrSum implementation of MEAN in
TensorFlow Lite.
Signed-off-by: Dwight Lidman <dwight.lidman@arm.com>
Change-Id: Ifd24e0e678e2f85cd66ab82deeaaf010d5351b1e
|
|
- Added full support for PAD operator
- Hardware padding is still used whenever possible
- Bug fix Pad followed by max pool if IFM contains negative values
Change-Id: Ifc64d1943737d94466f5e2821009dab12a49a965
Signed-off-by: Louis Verhaard <louis.verhaard@arm.com>
|
|
- Updated release notes
- Updated supported ops
- Clarified platform support
- Minor clean up of README
Signed-off-by: Tim Hall <tim.hall@arm.com>
Change-Id: I62b9ff66fc7729b184a5dbb322406cfcdef4e542
|
|
PAD followed by max/average pool is run on NPU if NPU
padding can be used. Average pool is converted to depthwise.
Change-Id: Icc3652e6d9ecff5ac3dc7d92080313d90c245404
Signed-off-by: Louis Verhaard <louis.verhaard@arm.com>
|
|
- Squeeze is no longer listed as supported operator
- Added missing doc-string for a Pad constraint
Change-Id: Ifd5e493acb0eb28bc4f104df74b3491589db8c29
Signed-off-by: Louis Verhaard <louis.verhaard@arm.com>
|
|
Signed-off-by: Jacob Bohlin <jacob.bohlin@arm.com>
Change-Id: I5c32b17caa8155e99387195732ce0141030d5599
|
|
When printing a set in the docstrings for the SUPPORTED_OPS.md file, the
order is random.
Reuse existing sorted string repr for the operator list and apply to
other printed sets (data types)
Signed-off-by: Michael McGeagh <michael.mcgeagh@arm.com>
Change-Id: I2ac12ea91c2637219e5c24f9a863aa0fc2086e77
|
|
mlplatform uses gitiles, which in turn renders markdown differently:
"There must be at least three hyphens in each column of the header row"
Updated the generation code and the snapshot file to respect this,
as well as changed the link from commonmark (which does not support
tables)
Signed-off-by: Michael McGeagh <michael.mcgeagh@arm.com>
Change-Id: If31860ce8e38ebe7d68bfec61faff805fc00345b
|
|
This file is generated from the vela option
--supported-ops-report
Each release, a snapshot will be taken and uploaded with the release.
This is for the 2.0.0 release
Signed-off-by: Michael McGeagh <michael.mcgeagh@arm.com>
Change-Id: I6b618889758a1a078e21244f1f98a56800a528a3
|