Age | Commit message (Collapse) | Author |
|
subgraph #0 error: Operator not supported"
This reverts commit 9fc259682c8b85af58bda42e87703bbec5ae57ce.
Fixes: IVGCVSW-6644 ExecuteNetwork tests failing with invalid input shape in Reshape layer
Signed-off-by: Teresa Charlin <teresa.charlinreyes@arm.com>
Change-Id: I561e0bd9ed1b92491cb8a08635042e199dd661d8
|
|
* This Dockerfile was donated by an open source
contributor to ArmNN.
* Fixed issues whilst building Arm Compute Library (ACL)
and removed Boost which is no longer used by ArmNN.
Signed-off-by: James Conroy <james.conroy@arm.com>
Change-Id: Ie3588dec510d7310a36699e135d67580dde30676
|
|
* Headers were updated in https://review.mlplatform.org/c/ml/ComputeLibrary/+/6751
* Update ACL pin to dc2282f40b40c0d85b113c792f90d1faa2759f46
Signed-off-by: Nikhil Raj <nikhil.raj@arm.com>
Change-Id: I1ff5d017e1921e5acbf7a5a54abc57d165fa5269
|
|
Deep_speech models
* Fixed output bindings in ExecuteNetwork when using delegate
* Added extra comments (for my own comprehension)
Change-Id: Ia1330903a2b724be7d637f6c5b6e4349e7d33e2e
Signed-off-by: Tamas Nyiri <tamas.nyiri@arm.com>
|
|
error: Operator not supported
* Added missing support for reshape operator in tflite parser when the target shape is dynamic and batch size is unknown
* Added corresponding unit test
Change-Id: I78f4b386f2e5e0d08ecacde17e33e304f6afbb70
Signed-off-by: Tamas Nyiri <tamas.nyiri@arm.com>
|
|
Signed-off-by: Nikhil Raj <nikhil.raj@arm.com>
Change-Id: Ifc06946de257c000fda364670fe4c3809953273e
|
|
* AddReduceLayer to PyArmNN armnn_network.i
* AddReduceDescriptor to PyArmNN armnn_descriptors.i
* Add layer to test_network.py
* Add descriptor unit tests to test_descriptors.py
Signed-off-by: Ryan OShea <ryan.oshea3@arm.com>
Change-Id: I2a8706052baf8f9c0038a5ea327d73b8f3ea1961
|
|
Signed-off-by: Nikhil Raj <nikhil.raj@arm.com>
Change-Id: Ia027c067343fc664e4e6f890e37cdc7fd0d36e8e
|
|
* These deprecated warnings have been there for more than two releases
Signed-off-by: Nikhil Raj <nikhil.raj@arm.com>
Change-Id: I1c816d80f6e74933cf5e4e8cc0dbad9a7a144562
|
|
Signed-off-by: Nikhil Raj <nikhil.raj@arm.com>
Change-Id: Ia7eb158dcc42cabde3b60806110b6e5c38c5d689
|
|
elements.
* Added out of bounds index error checking to PermutationVector operator[] method
in Types.hpp.
* Added armnn unit tests to UnitsTests.cpp to check error when using
PermutationVector alone and with TransposeDescriptor and PermuteDescriptor.
* Added pyarmnn unit test to check error when using PermutationVector.
Signed-off-by: Cathal Corbett <cathal.corbett@arm.com>
Change-Id: Ie5a8090f07b571a6bdf79a8cad621c31cc1891b7
|
|
Signed-off-by: Teresa Charlin <teresa.charlinreyes@arm.com>
Change-Id: I2bfc54ea9aae78c60a66d7a5c39a33ca8a238e62
|
|
Signed-off-by: Teresa Charlin <teresa.charlinreyes@arm.com>
Change-Id: I6d09abb75db1875d4d4075b1801fdc46a0f4ae7b
|
|
Signed-off-by: Teresa Charlin <teresa.charlinreyes@arm.com>
Change-Id: Ie54d2deff3059978a55667fe8a1d91418ef785dd
|
|
Signed-off-by: Teresa Charlin <teresa.charlinreyes@arm.com>
Change-Id: If9c6902396b9f3cec3b38b70ccfa12fcbb3fd5a7
|
|
* Add layer to armnn.network.i
* Add layer to test_network.py
Signed-off-by: Ryan OShea <ryan.oshea3@arm.com>
Change-Id: I7554a0ff62d81fcc99aa68204ae5f1cc3965c44b
|
|
* AddTransposeLayer to PyArmNN armnn_network.i
* AddTranposeDescriptor to PyArmNN armnn_descriptors.i
* Add layer to test_network_method_exists() in test_network.py
* Add descriptor unit tests to test_descriptors.py
Signed-off-by: Cathal Corbett <cathal.corbett@arm.com>
Change-Id: Ic198448ad11d10701b6b263656285bb75d3656cd
|
|
* AddLogicalBinaryLayer to PyArmNN armnn_network.i
* LogicalBinaryDescriptor to PyArmNN armnn_descriptors.i
* Add layer to test_network_method_exists() in test_network.py
* Add descriptor unit tests to test_descriptors.py
Signed-off-by: Cathal Corbett <cathal.corbett@arm.com>
Change-Id: I2f6288987332e1556235a9c16582e96b3a0fb641
|
|
* Improve start-up timer for GeMM (floating-point)
Signed-off-by: Teresa Charlin <teresa.charlinreyes@arm.com>
Change-Id: I065dc7feb79aa0acf7e7ff9d86b296d134f2f97f
|
|
* Moved CompatibleTypes.hpp to include folder
* Added implementation file to source CompatibleTypes.cpp
Signed-off-by: Sadik Armagan <sadik.armagan@arm.com>
Change-Id: I94d2bffdb82a0592943f497d4f57972151d9f2db
|
|
* Add UnitTest for CpuAcc
!ComputeLibrary: 6641
Signed-off-by: Teresa Charlin <teresa.charlinreyes@arm.com>
Change-Id: Ic96b9e28d133cef73312b4ac793325f5e69b3d4d
|
|
Signed-off-by: Nikhil Raj <nikhil.raj@arm.com>
Change-Id: Ic66f4576fcba9983c0a4586d003654a098b6ee36
|
|
to comply with inclusive language guidelines.
Signed-off-by: Teresa Charlin <teresa.charlinreyes@arm.com>
Change-Id: Iff3c9fd1107ddd97b1547f676e6aec06d7e2d28a
|
|
Subtask of story: IVGCVSW-6164 Add a Pooling3d FrontEnd and Ref Implementation
* Add serialization support
* Add deserialization support
* Add corresponding unit tests
Change-Id: I7cce5421f0a9b7c47a03524e733f3315131ba125
Signed-off-by: Tamas Nyiri <tamas.nyiri@arm.com>
|
|
Subtask of story: IVGCVSW-6164 Add a Pooling3d FrontEnd and Ref Implementation
* Add front end
* Add reference workload
* Add corresponding unit tests
Change-Id: Icce4146dd0a06a1da46a2def00a82d343e171750
Signed-off-by: Tamas Nyiri <tamas.nyiri@arm.com>
|
|
Signed-off-by: Nikhil Raj <nikhil.raj@arm.com>
Change-Id: Ic352c48dfe04c6cc5a2b201bf71950866be6b2fe
|
|
Signed-off-by: Nikhil Raj <nikhil.raj@arm.com>
Change-Id: Ifb5600771e49ac75d4d53bf281bcb87c7bdd99f9
|
|
* Add UnitTest for GpuAcc
Signed-off-by: Teresa Charlin <teresa.charlinreyes@arm.com>
Change-Id: I235900dc62fb043c5ce9c8cd4f63dcc4e5393233
|
|
* Detected to be missing after adding validation to PadWorkload
Signed-off-by: Tamas Nyiri <tamas.nyiri@arm.com>
Change-Id: I3b2c58f414456008543db299a8461dad5b4d2a96
|
|
Signed-off-by: Francis Murtagh <francis.murtagh@arm.com>
Change-Id: I53f884d2b534b6b009c0717172d977af8b75a7e3
|
|
* Move all the image files used in doxygen to docs/
* Have a single path for all images in Doxyfile
* Update project number to 21.11 in Doxyfile
Signed-off-by: Nikhil Raj <nikhil.raj@arm.com>
Change-Id: Ic9102d36b69a8261caf8e55da645463540e0b9f3
|
|
* Added new test for AddConstantLayer to FullyConnectedLayer with
actual data in test_network.py
* Added support for m_ConstantWeights in FullyConnectedDescriptor in
file armnn_descriptors.i
* Amended AddFullyConnectedLayer methods in armnn_netowrk.i to
add support for ConstTensorsAsInputs to FullyConnected.
* Fixed indentation in test_network.py
Signed-off-by: Cathal Corbett <cathal.corbett@arm.com>
Change-Id: Id25c7ef6ed2cd3de3285416d90588ccb345aa9bc
|
|
* This guide has now been moved to the Quick Start section in doxygen
Signed-off-by: Nikhil Raj <nikhil.raj@arm.com>
Change-Id: I758915c43f0e9e116f7308482db34d560d7ba0d9
|
|
Signed-off-by: Nikhil Raj <nikhil.raj@arm.com>
Change-Id: Iea0afcb69230a22181629424a3f801f3128990d1
|
|
* Fix overlap detection with strategy validator
Signed-off-by: Finn Williams <finn.williams@arm.com>
Change-Id: If9d9d9586864cef7d109aad24bdb0f682fefb1bd
|
|
* Typo errors from ticket 'Constant flag in tensor info is not set correctly'.
Not fixed due to code freeze deadline.
Signed-off-by: Cathal Corbett <cathal.corbett@arm.com>
Change-Id: Id80ba60647d1970115a8cf200f0d71e4fada9b30
|
|
* py35 unit tests require more-itertools 8.10.0 as latest version 8.11.0
breaks with py35
Signed-off-by: Kevin May <kevin.may@arm.com>
Change-Id: I21654fc73a3e3e9d00b14119eb840df750c81b12
|
|
* The TfLiteparser was returning non const TensorInfo's for input tensor
BindingPointInfo.
Signed-off-by: Colm Donelan <colm.donelan@arm.com>
Change-Id: I20942aaef3afe7c91cf19fc3c007bec35828e69e
|
|
* With the new Memory Management updates input tensors should now match the backend of the layer they are attached to. Updated the test to reflect this.
Signed-off-by: David Monahan <David.Monahan@arm.com>
Change-Id: I4e7fbd3f2f40d349c39cdf0d7bfef1262144181b
|
|
Signed-off-by: David Monahan <David.Monahan@arm.com>
Change-Id: I115a28049eadd6101c507fb15a2e84bedb022189
|
|
Signed-off-by: Teresa Charlin <teresa.charlinreyes@arm.com>
Change-Id: I476608976c52df97677a64af94767d3945dd9475
|
|
* Serialize/Deserialize axis parameter on Softmax Descriptor.
Signed-off-by: Sadik Armagan <sadik.armagan@arm.com>
Change-Id: I1bba0dd7d78f9f211f77115dcefccf24a4a61b39
|
|
!android-nn-driver:6532
!armnn-internal-tests:372451
* Made fix to 2 out of 3 ConstTensor() constructors in Tensor.hpp to
throw InvalidArgumentException when TensorInfo isConstant parameter
is false.
* Added new ConstTensor() constructor in Tensor.cpp to accept vector<>.data()
using template<typename MemoryType>.
* Fixed runtime->GetOutputTensorInfo()/GetInputTensorInfo() methods and
called submethods to return TensorInfo& rather than TensorInfo.
* Fixed all failing unit tests for CpuRef/CpuAcc/GpuAcc to ensure any
ConstTensor created has it's TensorInfo isConstant set to true.
* Added unit tests in TensorTest.cpp to ensure ConstTensor constructors
throw InvalidArgumentException when TensorInfo isConstat parameter is
false.
* Added unit test to ensure an empty ConstTensor constructor will set
TensorInfo isConatant to true.
* Indentation fixes.
* Fix to arm_tensor.i to add isConstant parameter to TensorInfo
constructor. Added methods IsConstant() and SetConstant().
* Fix to const_tensor.py to throw ValueError when TensorInfo
isConstant is set to false when constructing a ConstTensor.
* Fixed PyArmnn unit tests to set TensorInfo isConstant to
True when ConstTensor is used.
* Added unit tests in test_const_tensor.py to ensure ConstTensor
constructors throw ValueError when TensorInfo isConstat parameter
is false.
Signed-off-by: Cathal Corbett <cathal.corbett@arm.com>
Change-Id: I44e440dd0422c366d31bbdbc77ad2b4db0bde148
|
|
Signed-off-by: Teresa Charlin <teresa.charlinreyes@arm.com>
Change-Id: If567bdc1ced5d4bbe524375e2566a19677533c98
|
|
Signed-off-by: Finn Williams <finn.williams@arm.com>
Change-Id: I4ca8d9196abd0e116d420a36c780e39edbca0eb3
|
|
Signed-off-by: Nikhil Raj <nikhil.raj@arm.com>
Change-Id: I9b5407a2d6fc27df2c448a4f6a6b862d2175022c
|
|
* adds missing dependencies to fix errors when building the
armnn delegate on its own
Signed-off-by: Jan Eilers <jan.eilers@arm.com>
Change-Id: I9bb676febc80eba277f981f5536a9add48e7f6dd
|
|
* enable external memory management for neon and ref backends
* change m_TensorMemoryVector to hold shared pointers
* change input layer backend Id to match backend id of connected layer
Signed-off-by: Finn Williams <finn.williams@arm.com>
Change-Id: I2216a724028312eb101b290df3f224177826b1a0
|
|
Signed-off-by: Nikhil Raj <nikhil.raj@arm.com>
Change-Id: Ia765d335ef998e7e47a1c0c81a375645972f4e1d
|
|
Change-Id: I474e5e40550d61f873fd930fe33b0e1e9f9992cc
Signed-off-by: Rob Hughes <robert.hughes@arm.com>
|