Age | Commit message (Collapse) | Author |
|
* Use new INetwork::AddConvolution2dLayer
instead of deprecated version
* Remove duplicated test in SerlializerTests
* Fix some cosmetics
Signed-off-by: Keith Davis <keith.davis@arm.com>
Change-Id: I3407815bfdc1cdc01ca0a667b8e4d80d8621783f
|
|
* No trailing permute layer after a constant layer
* Unit test for optimization
Signed-off-by: Cathal Corbett <cathal.corbett@arm.com>
Change-Id: I0d098f5af41d2c55df7cef1ccfb848093320ddc1
|
|
* Update Front-end and Tools.
* Updated Serializer, Deserializer and unit tests to reflect this.
* Updated TfLiteDelegate, TfLiteParser and OnnxParser.
* Updated Ref.
* Fixed resulting Neon / CL tests
* Unified optimizers for conv2d ops
* Optimizer Fix - Fp32ToBf16
* Partial implementation for ACL backends to fix VTS failures
!android-nn-driver:7477
Signed-off-by: Keith Davis <keith.davis@arm.com>
Change-Id: I5fb18877f7ee32643e15a9818945356274bb401b
|
|
!android-nn-driver:7418
* Update Front-end and Tools.
* Updated Serializer, Deserializer and unit tests to reflect this.
* Updated TfLiteDelegate, TfLiteParser and OnnxParser.
* Change NNDriver to new API.
* Updated Ref.
* Neon and Cl backend partially completed (Backend.cpp files).
* Added dynamic or constant input EndToEnd tests.
* Added ConstantTensorAsInputMemeberVariableRedirect Optimization.
Signed-off-by: Cathal Corbett <cathal.corbett@arm.com>
Change-Id: Ib18b6c10a093042e165e25237dc04a4c67ba82da
|
|
and batch size is unknown to ONNX parser
Signed-off-by: Narumol Prangnawarat <narumol.prangnawarat@arm.com>
Change-Id: I46b2daccce9e1a21d9d0550ac4126d2c79dbd37b
|
|
Signed-off-by: Narumol Prangnawarat <narumol.prangnawarat@arm.com>
Change-Id: Ia7dbf0735619d406d6b4e34a71f14f20d92586e6
|
|
Signed-off-by: Narumol Prangnawarat <narumol.prangnawarat@arm.com>
Change-Id: I3c6979c72d44a15fb2dc3afc22ac30d1428684b0
|
|
Signed-off-by: Narumol Prangnawarat <narumol.prangnawarat@arm.com>
Change-Id: Id1e933f6ae55ddc1a57c80c9f6a5757ccb61f018
|
|
Signed-off-by: Narumol Prangnawarat <narumol.prangnawarat@arm.com>
Change-Id: I435723160e9b639a70e0b48ee9d722d306461291
|
|
Signed-off-by: Narumol Prangnawarat <narumol.prangnawarat@arm.com>
Change-Id: Ie0b68b08fc31444c58b0ffc9babdd456bbb51f35
|
|
* Add ParseGather to support Gather operator on ONNX
* Add Support of int64 converted to int32 for constant
* Add OnnxParserTestUtils
* Refactor ValidateTensorShapesFromInputs of GatherLayer
* Unit tests
Signed-off-by: Narumol Prangnawarat <narumol.prangnawarat@arm.com>
Change-Id: Ie9dff640240e14a062fef38f7faf0ccc212de5f7
|
|
Signed-off-by: Narumol Prangnawarat <narumol.prangnawarat@arm.com>
Change-Id: I3547effcbebf1ebc02d3b20f5db394a26991424d
|
|
Signed-off-by: Narumol Prangnawarat <narumol.prangnawarat@arm.com>
Change-Id: I1bae42dade7eabf3da09252066e912e803a8ea32
|
|
* Constant weights and biases are now stored as Constant layers.
* Updated Serializer, Deserializer and unit tests to reflect this.
* Updated TfLiteDelegate, TfLiteParser and OnnxParser.
* Updated Schema with IsConstant and ConstantTensorsAsInputs.
* Updated Ref backend to handle constant weights and
bias as inputs rather than reading from member variables.
* Added dynamic or constant input EndToEnd tests.
!android-nn-driver:5959
Signed-off-by: Matthew Sloyan <matthew.sloyan@arm.com>
Change-Id: Ibf3cf437df1100e4b322b0d303c575c6339f9696
|
|
* 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
|
|
* Added Version.hpp to all Parsers
* Added Version.hpp to TfLite Delegate
* Updated CMakeLists to use new versions
* Added GetVersion method to parsers and TfLite Delegate
Signed-off-by: Matthew Sloyan <matthew.sloyan@arm.com>
Change-Id: If29e1e6d9e615f9095ec1c01ad47acfff40b1dd5
|
|
Signed-off-by: Sadik Armagan <sadik.armagan@arm.com>
Change-Id: I4a0f07b1e8f80aff0d29405def1f33bde7944e31
|
|
Signed-off-by: Kevin May <kevin.may@arm.com>
Change-Id: I760dc4f33c0f87113cda2fa924da70f2e8c19025
|
|
* Use the single parameter version of SetTotalBytesLimit()
* Update CMakeLists to turn off deprecated declarartions
Signed-off-by: Nikhil Raj <nikhil.raj@arm.com>
Change-Id: I2d360966743986872cfef40c2ab1a3505fc5d99a
|
|
* replaced with fmt::format
* one case required std::stringstream instead
Signed-off-by: James Ward <james.ward@arm.com>
Change-Id: Ica9a7eb4e7bed04aa03172058dd9e3d10efc8548
|
|
* Replaced with armnn/utility/NumericCast.hpp
* Exclusions in armnnCaffeParser
* Three excluded as requires float implementation in NumericCast.hpp
Signed-off-by: Matthew Sloyan <matthew.sloyan@arm.com>
Change-Id: Ib468b606238694334a8319d0ed5db381ce37a915
|
|
* Added ParseFlatten method
* Added Read int64 attribute method
- Modified ComputeReshapeInfo method
- Modified ParseReshape
* Added unit tests
- Reorganised OnnxParser.cpp/.hpp
Signed-off-by: Ryan OShea <Ryan.OShea2@arm.com>
Change-Id: I8a9553438dd1e8c702d821b093587e0074c027d5
|
|
* 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
|
|
Change-Id: I68c842c5906f03b8f5a6131537fea3a1a0db980a
Signed-off-by: Finn Williams <Finn.Williams@arm.com>
|
|
* Fixed ParseConstant
* Fixed Exception
* Fixed 0 dimension tensor
* Add unit test to check addition as tensor and scalar
* Change C++ style comments to Doxygen style
Signed-off-by: Ryan OShea <Ryan.OShea2@arm.com>
Change-Id: Ied7cbe2e11e713c23d87106d2db39e0eb446c920
|
|
Signed-off-by: Matthew Bentham <Matthew.Bentham@arm.com>
Change-Id: I6c90eab1c6bad76d5c7b3bf094998fa4b454bcd1
|
|
parser
Signed-off-by: Jung Tae-young <tee.ty.jung@openedges.com>
Signed-off-by: Matteo Martincigh <matteo.martincigh@arm.com>
Change-Id: I396792d4d59172cccb50d77de7e6b74977b289ed
|
|
Signed-off-by: Jung Tae-young tee.ty.jung@openedges.com
Change-Id: I44d24b525b78b8d3fee0197abda7bd667eb04d83
|
|
* armnnOnnxParser makes tensorInfo from graph->value_info
but PyTorch does not add weight/bias tensor information to graph->value_info
so tensorInfo of const tensor should be extracted from graph->initializer
Signed-off-by: Jung Tae-young tee.ty.jung@openedges.com
Change-Id: Ib2656dd25abc522012cf413e843fe03949cb2eb0
|
|
!android-nn-driver:1210
Change-Id: I940b3b9e421c92bfd55ae996f7bc54ac077f2604
Signed-off-by: Jim Flynn <jim.flynn@arm.com>
|
|
* Used the new ARMNN_DEPRECATED_MSG macro instead of @deprecated
* Refactored the code to no longer use the deprecated methods where
applicable
!android-nn-driver:1126
Change-Id: Ib0578d3d6fc5a763f5fb922f67ba91fafc7796f6
Signed-off-by: Matteo Martincigh <matteo.martincigh@arm.com>
|
|
Fixed bug in ONNX parser: unable to load raw data from the binary
models.
Change-Id: Iec60d2f90b78ffe6910fdec6e6bd2eb05802ffd0
Signed-off-by: Pablo Tello <pablo.tello@arm.com>
|
|
!android-nn-driver:968
Signed-off-by: Aron Virginas-Tar <Aron.Virginas-Tar@arm.com>
Change-Id: I03ccb4842b060a9893567542bfcadc180bbc7311
|
|
* Fixed invalid conversion issues to onnx::TensorProto::DataType
Change-Id: If8f1cef1d02a22cfecf24135a960923d3ad0e14c
|
|
All changes are the same:
//
// Copyright © 2017 ARM Ltd. All rights reserved.
-// See LICENSE file in the project root for full license information.
+// SPDX-License-Identifier: MIT
//
Change-Id: I37eae011411133663ca9d2b059714d92f8bf8e24
|
|
|