Age | Commit message (Collapse) | Author |
|
* The abort is caused during destruction of flatbuffers::ClassicLocale
* Set FLATBUFFERS_LOCALE_INDEPENDENT=0 in delegates and parser so that
ClassicLocale is not included
Signed-off-by: Kevin May <kevin.may@arm.com>
Change-Id: I34584b05998a62bae2263a2281414fcf8c12d668
Signed-off-by: Colm Donelan <colm.donelan@arm.com>
|
|
Signed-off-by: Teresa Charlin <teresa.charlinreyes@arm.com>
Change-Id: I5b87304319f5e83e8eba9cb2d934fc4a6aebe85b
|
|
Signed-off-by: Colm Donelan <colm.donelan@arm.com>
Change-Id: If156b975d37868db77d7c6bb75d884652278e02a
|
|
Signed-off-by: Teresa Charlin <teresa.charlinreyes@arm.com>
Change-Id: Ic3c42db6fd87b379b42d610e0d0f56f55580268d
|
|
Signed-off-by: Teresa Charlin <teresa.charlinreyes@arm.com>
Change-Id: Ib49795e44ea7e4674a3b8e0df46e80c82f9a4132
|
|
This reverts commit 008270f8c1359a7d62c2f881326b4d3f0d8b7b56.
Signed-off-by: Mike Kelly <mike.kelly@arm.com>
Change-Id: If8f5151aa349ff3834f03391e813669e5c51ed66
|
|
* Updated Opaque Delegate, TfliteParser, OnnxParser, and Deserializer to handle the Zero In Shape edge case
Signed-off-by: Tianle Cheng <tianle.cheng@arm.com>
Change-Id: I4a0d1e72a66de1fa56de99af9b6730a84e0ff596
|
|
* Add support to CpuRef, CpuAcc and GpuAcc
* Add support to tflite parser, classic and opaque tflite delegates
* Add support to serializer and deserializer
* Add Unit tests
Signed-off-by: Teresa Charlin <teresa.charlinreyes@arm.com>
Change-Id: Ibc60ef2ef2a051e6d9af6e15d24c46316ec19de4
|
|
* Changing the optimizer
* Changing EndToEnd Tests
Signed-off-by: Idriss Chaouch <idriss.chaouch@arm.com>
Signed-off-by: Narumol Prangnawarat <narumol.prangnawarat@arm.com>
Change-Id: Ib581794280322a39cfc5ea3c4e6a6398cf723d5e
|
|
* Fix incorrect batch size and time size
* Fix incorrect time major when max time =1
* Fix incorrect permutation
* Fix incorrect scratch buffer
* Unit tests
Signed-off-by: Narumol Prangnawarat <narumol.prangnawarat@arm.com>
Change-Id: I510fae55528be412a58d020e82bd283852e7800b
|
|
This reverts commit 4980e21193f0a14fef084a7f4b4197392f3c0845.
Reason for revert: Android Build for v82a failed due to schema not re-generating
Change-Id: Ic19cf471b487f321c97ff837d36526512fb12fa4
|
|
!android-nn-driver:10089
* Disabled SubTensors on CL and Neon Backends.
* Added Axis to ViewsDescriptor to store the value where ever possible.
* Updated Splitter tests to provide all the information needed in the
Descriptor.
* Updated Serializer and Deserializer to handle axis.
Signed-off-by: Mike Kelly <mike.kelly@arm.com>
Change-Id: I6a22d4750e04003689495b5e9e3c33deb37162bd
|
|
* ILayerSupport interface - removed unstable virtual functions.
* User instead uses IsLayerSupported accepting LayerType enum argument.
* Backend developers should implement the ILayerSupport::IsLayerSupported
method accepting LayerType as a switch statement with case being
LayerType and each case calling their implementation of IsXXXSupported()
Signed-off-by: Francis Murtagh <francis.murtagh@arm.com>
Change-Id: Iaaead8320bb1b2f1bdab6b5be2e1e69d0eb482d5
|
|
* Replace most ARMNN_ASSERT's from tflite parser
* Replace most ARMNN_ASSERT's from onnx parser
* Replace some ARMNN_ASSERT's from tflite delegate
* Replace some ARMNN_ASSERT;s from include files
Signed-off-by: Ryan OShea <ryan.oshea3@arm.com>
Change-Id: Ie052e0180060203f28f64ebf54acad298f431caf
|
|
* Added boilerplate checks around the ParseStridedSlice memcpy's
Signed-off-by: David Monahan <david.monahan@arm.com>
Change-Id: Ied85c709dee230eb2984d3e339ed711d62ab36bd
|
|
Signed-off-by: Teresa Charlin <teresa.charlinreyes@arm.com>
Change-Id: Ic2c3a89b89f44f111e5a184c83db89ea1cb52976
|
|
Layer with 2 inputs
* Changing ReverseV2 to use two inputs
* This is required by the backends
* The ReverseV2Descriptor was removed
* Tests updated
* Added a Run<> templatefor inputs with different data types
Signed-off-by: Tracy Narine <tracy.narine@arm.com>
Change-Id: I22f947de829b4b3da6bda3a74f4ffdef4052cc25
|
|
Signed-off-by: Teresa Charlin <teresa.charlinreyes@arm.com>
Change-Id: I5760da9be2ed63fdfbdd5d3d7b771c310592798d
|
|
* Added ReverseV2 support to TFLite Parser
* Added ReverseV2 TFLite Parser unit tests
* Updated Parser Docs
Signed-off-by: Tianle Cheng <tianle.cheng@arm.com>
Change-Id: Idb9a9213f75cd6cf01509a5d06ea5772cf56ac5b
|
|
* Implement the "-C" command line option of executenetwork.
* Add a FileComparisonExecutorFile which will read tensors from
a previously written text file and compare them to the execution
output.
Signed-off-by: Colm Donelan <colm.donelan@arm.com>
Change-Id: I8380fd263028af13d65a67fb6afd89626d1b07b8
|
|
* this line is used earlier to initialize subgraphPtr
Signed-off-by: Francis Murtagh <francis.murtagh@arm.com>
Change-Id: Iff24da2acab33e59460455977e221066973532a2
|
|
* This commit fixes partially the ticket.
In ToTensorInfo() we assume batch is 1 when it is unknown.
We call OutputTensorInfoFromInputs() to amend this assumption/
However, this does not work for reshape layer.
Therefore, we have to calculate the output shape in the ParseExpandDims().
Signed-off-by: Teresa Charlin <teresa.charlinreyes@arm.com>
Change-Id: Iedc32a44b4ec0d8b7d2cc0b08f38f0776402f7bd
|
|
Signed-off-by: Teresa Charlin <teresa.charlinreyes@arm.com>
Change-Id: I96fd26559450690fbe99a0e8fbe193ddf5d3a34b
|
|
* Added 2 new operators as ElementWiseBinary ops
* Ref End to End and unit tests
* Serialize and Deserialize tests
* Delegate and Opaque Delegate tests
* TfLite Parser tests
Signed-off-by: John Mcloughlin <john.mcloughlin@arm.com>
Change-Id: I537158127f602f0c41ca0402aa31655cd3bd4281
|
|
* If the output shape is given in Transpose convolution, use it to calculate the padding
Signed-off-by: Teresa Charlin <teresa.charlinreyes@arm.com>
Change-Id: I0bf3dee94c2ce606ed67fb385018b220188c3017
|
|
* Reference workload
* TfLite Delegate
* TfLite Parser
* Serializer and Deserializer
* Changed fallback tests in delegate to use COS instead of CEIL
Signed-off-by: Teresa Charlin <teresa.charlinreyes@arm.com>
Signed-off-by: Mike Kelly <mike.kelly@arm.com>
Change-Id: I36e0dbff33694182d1dba0c95d463506428e2f04
|
|
* Arm NN does not account for int8 or uint8 not quantized types, Tensorflow does.
Not quantized int8 and uint8 is the same as quantized int8 and uint8 with scale = 1.0 and offset= 0
Default offset/zero_point was already 0, this review sets the default scale to 1.0.
Signed-off-by: Teresa Charlin <teresa.charlinreyes@arm.com>
Change-Id: Ibc3eecc281de516c2cc706e17bde01c64ff9556e
|
|
Signed-off-by: Teresa Charlin <teresa.charlinreyes@arm.com>
Change-Id: I3ccfc2a4c95c57743927fb276faa756740f5c55a
|
|
!android-nn-driver:9329
* Added ElementwiseBinaryLayer that can represent all ElementwiseBinary
operations including Add, Div, Sub, Maximum, Mul and Minimum.
* Updated Delegate to use ElementwiseBinaryLayer instead of the Add,
Div, Sub, Maximum, Mul and Minimum layers.
* Updated Deserializer to use ElementwiseBinaryLayer instead of the Add,
Div, Sub, Maximum, Mul and Minimum layers.
* Updated OnnxParser to use ElementwiseBinaryLayer instead of the Add
layer.
* Updated TfLiteParser to use ElementwiseBinaryLayer instead of the Add,
Div, Sub, Maximum, Mul and Minimum layers.
* Updated CL and Neon tests to use ElementwiseBinaryLayer.
* Updated CL and Neon Backend Specific Optimizations to accept
ElementBinaryLayers as well as Add, Div, Mul, Sub, Maximum and Minimum
layers.
Signed-off-by: Teresa Charlin <teresa.charlinreyes@arm.com>
Signed-off-by: Mike Kelly <mike.kelly@arm.com>
Change-Id: I7cbb96b60eb01f0e2b57b0541016d48a08b86c75
|
|
Signed-off-by: Teresa Charlin <teresa.charlinreyes@arm.com>
Change-Id: I4f5016841c31b183440f31c1e177bc41d2b8dbb7
|
|
We currently check that output_shape is an input for transpose conv2d.
If that is an input, we assume that it is constant and attempt to copy
the data into the descriptor. When this data is not constant and instead
comes from the output of another layer we segfault. When not constant
we will use infer output shapes.
* Adds a check into ParseTransposeConv2d that inputs[0] is constant
Signed-off-by: Ryan OShea <ryan.oshea3@arm.com>
Change-Id: I01176ae22974767a2306a3db749a029ed220d88b
|
|
the shape of the network
* Fixed bug where calculated output shape wasn't being recorded in ParseSqueeze.
Signed-off-by: Mike Kelly <mike.kelly@arm.com>
Change-Id: I8f03a0400323c865e7e8f924d257d6770f809502
|
|
* TFLite Parser:
* Fixed issue in ParseReshape where the targetShape wasn't always calculated correctly
* Fixed issue in ParseFullyConnected where the wrong name was used for the ReshapeLayer
* Added an ExpandDims to the FullyConnected to ensure that we reshape the output correctly
* TFLite Delegate:
* Added an ExpandDims to the FullyConnected to ensure that we reshape the output correctly
Signed-off-by: Mike Kelly <mike.kelly@arm.com>
Change-Id: I129dfcb8543f8a3a297c0589c841be20ef3b6407
|
|
* Added ability to calculate dynamic tensors and propagate
them through the model so that when those tensors are later
used as inputs they have the right shapes.
* Added InferOutputShapes to DetectionPostProcessLayer.
* Added InferOutputShapes to MeanLayer.
* Added InferOutputShapes to RankLayer.
* Added InferOutputShapes to ReduceLayer.
* Fixed typos in TfLiteParser.
Signed-off-by: Mike Kelly <mike.kelly@arm.com>
Change-Id: I880c0716938ef278f5dbf01a8a73a5cc99ce5ded
|
|
Signed-off-by: Cathal Corbett <cathal.corbett@arm.com>
Change-Id: Id765f6d766e623a157b614ca935113a9f32a5801
|
|
* Fixed bug when converting Constants with Per-Axis Quantization
Signed-off-by: Mike Kelly <mike.kelly@arm.com>
Change-Id: Ifbea23e60483746ec987da491dae96e74cb33af4
|
|
param contains a value of -1.
Signed-off-by: Cathal Corbett <cathal.corbett@arm.com>
Change-Id: I538347083e9f22b3f3b6c048aebc2cf5cf4dc786
|
|
Signed-off-by: Teresa Charlin <teresa.charlinreyes@arm.com>
Change-Id: I1bc3d50b8fa6e216d8b6b7e3421d2ff37a21712c
|
|
buffer data for Slice operator.
Signed-off-by: Cathal Corbett <cathal.corbett@arm.com>
Change-Id: I86735faf8d57168a63ca6657f281ec03b90f7235
|
|
* Added armnnTfLiteParser for BatchMatMul
* Added unit testing for parser
* Updated CMakeLists
Signed-off-by: Samuel Yap <samuel.yap@arm.com>
Change-Id: If6842aaf7cf08f688093b714e2ecea6e8cd87161
|
|
* Adding the check only if it's not a const layer which is needed to run ai_benchmark_v5_yolo_v4_tiny_quant.tflite model
* We still won't be able to run the model due to IVGCVSW-7158
Signed-off-by: Nikhil Raj <nikraj01@e126673.cambridge.arm.com>
Change-Id: Ib7e77a0b5a64be0c92a8e4eae45729f799770b37
|
|
Signed-off-by: Cathal Corbett <cathal.corbett@arm.com>
Change-Id: I5c68b81a67fc2b5a33cf62753351440564bb868e
|
|
Signed-off-by: Teresa Charlin <teresa.charlinreyes@arm.com>
Change-Id: I979a6f43c0d6ec49effb9a87339dbcd07678d2bd
|
|
Signed-off-by: Teresa Charlin <teresa.charlinreyes@arm.com>
Change-Id: I1fedfdf2cd8871d6b307fce8620f40adadf75f04
|
|
* Fixed Segfault when parsing Unidirectional Sequence LSTM
Signed-off-by: Mike Kelly <mike.kelly@arm.com>
Change-Id: Ic69a4190c60ef595be64bc2c356e540319381b7e
|
|
dimensions
* Added allow-expanded-dims to TFLite parser and ArmNN delegate
* If true ArmNN will disregard dimensions with a size of 1 when
validating tensor shapes. Tensor sizes must still match.
* This allows us to support models where tensors have expanded
dimensions (i.e. extra dimensions with a size of 1).
* Fixed bug in Network where it assumed that only the first option
could be ShapeInferenceMethod.
* Fixed bug where m_ShapeInferenceMethod was lost when copying or
moving Graphs.
* Changed Delegate to pass "infer-output-shape", "allow-expanded-dims"
and other BackendOptions through to the Network during construction.
Signed-off-by: Mike Kelly <mike.kelly@arm.com>
Change-Id: Ibe7c5ae6597796fc9164cb07bd372bd7f8f8cacf
|
|
* 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
|
|
Signed-off-by: Teresa Charlin <teresa.charlinreyes@arm.com>
Change-Id: I7ce633a66e2ecb72a9cdd1bff690c4195a9a449f
|
|
Signed-off-by: Teresa Charlin <teresa.charlinreyes@arm.com>
Change-Id: I3b1f44c10a3446cfe45a7757d8a98e9788ec5dc0
|