Age | Commit message (Collapse) | Author |
|
Signed-off-by: Kevin May <kevin.may@arm.com>
Change-Id: I4a82aca4a2c47b3c598b91bc0075c09397be728a
|
|
Signed-off-by: Teresa Charlin <teresa.charlinreyes@arm.com>
Change-Id: I8b27541ec11ee907b80f6e2b4ff9ce3d76320076
|
|
Signed-off-by: Narumol Prangnawarat <narumol.prangnawarat@arm.com>
Change-Id: I6b3321cf0d51c06b742432995ea486c987806afc
|
|
This patch addes ReduceSum operation support for reference backend,
which computes the sum of elements across dimensions of a tensor.
Changelog v1:
- Fix file header descriptions.
Chagelog v2:
- Fix line limit issue.
- Fix type conversion issue.
Changelog v3:
- Remove tabs.
- Modify newly added file headers.
Changelog v4:
- Symbol on header isn't allowed so drop it from newly added file headers.
Changelog v5:
- Remove tabs, fix the use of brackets and align lines correctly.
Changelog v6:
- Add serializer and deserializer support.
Changelog v7:
- Fix build error add missed code.
Changelog v8:
- Rename ReduceSumDecriptor to ReduceDescriptor
- Update m_KeepDims field data type to bool on ReduceDescriptor
- Add ReduceOperation field to ReduceDescriptor
- Rename ReduceSumLayer to ReduceLayer
- Update ReduceLayer to use ReduceDescriptor
- Update ReduceLayer::ValidateTensorShapesFromInputs() function
- Rename RefReduceSumWokload to RefReduceWorkload
- Update workload to use ReduceDescriptor
- Update workload to use Decoders and Encoders
- Remove ReduceSum.hpp and ReduceSum.cpp
- Added Reduce.hpp and Reduce.cpp
- Move Mean.cpp (which is implementing REDUCE_MEAN) functionality to Reduce.cpp
- Update RefMeanWorkload to call Reduce function with ReduceOperation::Mean argument
- Remove Mean.hpp and Mean.cpp
- Update the Serializer/Deserializer ArmnnSchema.fbs for ReduceLayer, ReduceDescriptor, and ReduceOperation
- Update Serializer and Deserializer for serializing/parsing ReduceLayer
- Added TfLiter parser Sum test for REDUCE_SUM operator
- Make corresponding changes on front-end and Ref backend to support REDUCE_SUM operator
Changelog v9:
- Fixed build errors.
Change-Id: I8c8e034f3df73f9565b3c18eff51ecca6c542195
Signed-off-by: Inki Dae <inki.dae@samsung.com>
Signed-off-by: Sadik Armagan <sadik.armagan@arm.com>
|
|
* Adds a page for contribution guidelines (Uses md guide)
* Adds a section for contribution guides (Uses md guide)
* Minor beautification
Signed-off-by: Jan Eilers <jan.eilers@arm.com>
Change-Id: Iafd7e3abf9da660ec21a215afada61a27ce928fc
|
|
* Moves TensorFlowLiteDelegateSupport.md to doxygen
* Renames a few .dox files to represent the structure of the documentation
* Adds sections for build and use guides
* Integrates markdown guides for the delegate into doxygen
Signed-off-by: Jan Eilers <jan.eilers@arm.com>
Change-Id: I68b7a29239be88c0617da9bdfce5323ebf26f5bc
|
|
* Add reduce-fp32-to-fp16, reduce-fp32-to-bf16, debug-data, memory-import
options to external delegate
* Simplify DelegateOptions
* Add test mock models
* Unit tests
* Configure lfs to manage tflite files
Signed-off-by: Narumol Prangnawarat <narumol.prangnawarat@arm.com>
Change-Id: I1e4db468862ba03d4cb031347bc307cf940b3cb1
|
|
Signed-off-by: Nikhil Raj <nikhil.raj@arm.com>
Change-Id: Id43ff3eb59f8c93cfe9fc4bcd76b8496512e2859
|
|
Signed-off-by: Jan Eilers <jan.eilers@arm.com>
Change-Id: I43082950c55375f62ecd30236d1c475e4ca89faf
|
|
* Uses README.md files to reduce duplications
Signed-off-by: Jan Eilers <jan.eilers@arm.com>
Change-Id: I2cfcb6cf02ac712656cb8c782c70d002df642b97
|
|
* Using README.md files directly to reduce duplications
Signed-off-by: Jan Eilers <jan.eilers@arm.com>
Change-Id: I6bd6f6326e608939ac244cc32b329e32bb4802f7
|
|
* Not using the README.md files directly because it doesn't seem to
be possible to get the content of readme.md combined with the content
of the support.md files in one page
Signed-off-by: Jan Eilers <jan.eilers@arm.com>
Change-Id: I1e5073761f3af8a8d498385f3f7586334e7b29ec
|
|
* Creates new section in doxygen called "Software Tools"
* Moves the Parser page into Software Tools
Signed-off-by: Jan Eilers <jan.eilers@arm.com>
Change-Id: I19643074226d7c2e73e560e3abb52f519af1a7b2
|
|
* Gives the readme file an update
* Removes introduction.dox
* Adds FAQ to doxygen
Signed-off-by: Jan Eilers <jan.eilers@arm.com>
Change-Id: Ibb67e7f2cac7e55556295eb7851c616561b17042
|
|
Signed-off-by: Finn Williams <Finn.Williams@arm.com>
Change-Id: I01c7bd314219e58f71505dcb787d606dbded914a
|
|
Signed-off-by: Keith Davis <keith.davis@arm.com>
Change-Id: Ie8c03153f82434d73572278eedb8a4b5b89ed837
|
|
* Added output log to capture time taken to load network into runtime.
* This time is cut down when loading a cached network.
Signed-off-by: Matthew Sloyan <matthew.sloyan@arm.com>
Change-Id: I043c177f17d01df35fbe0752ec5d77e350749164
|
|
* Add test for new IsBackendRegistered member function of Handle
* Move deprecated messages to new frontend API of LayerSupportHandle
* Update delegate to use dot operator for IsXXXLayerSupported
Signed-off-by: Francis Murtagh <francis.murtagh@arm.com>
Change-Id: I70d7166e207a10e4b3583a827ca0dda2169bcba1
!android-nn-driver:4940
|
|
* Remove double brackets for scalars
* Add in extra location in cmake for tf lite dynamic library
Signed-off-by: Keith Davis <keith.davis@arm.com>
Change-Id: I31ef9a955d4677faabedc0068ae2cfbfe570b58c
|
|
Signed-off-by: Nikhil Raj <nikhil.raj@arm.com>
Change-Id: Ica17c75dfab52d9b8fada56658b95794d4e58536
|
|
Change-Id: Ic45d4c837eaad8b9f19288d4f3b6e8caa3eaf319
Signed-off-by: Jim Flynn <jim.flynn@arm.com>
|
|
* Added DEPTH_TO_SPACE and SPACE_TO_DEPTH operators support
Signed-off-by: Sadik Armagan <sadik.armagan@arm.com>
Change-Id: I2595f759181bd7339127e7b114b850b534210dd5
|
|
* Added L2_NORMALIZATION and LOCAL_RESPONSE_NORMALIZATION opertor support
Signed-off-by: Sadik Armagan <sadik.armagan@arm.com>
Change-Id: Ic9e66879cf6469fa8761fb1c9dd5950771f629b0
|
|
* Add OptimizerOptions, NetworkProperties, DebugCallbackFunction
to DelegateOptions
* Enable OptimizerOptions when the network is being optimized
* Enable NetworkProperties when loading network
* Enable DebugCallbackFunction
* Add error message when loading network
* Log warning instead of error when operator is not supported but
could fallback to another backend
* Improve uint16_t CompareData
* Unit tests
Signed-off-by: Narumol Prangnawarat <narumol.prangnawarat@arm.com>
Change-Id: I353035afb442774bfeb1c62570a90755c2ceaf38
|
|
* Pass in new window parameter to the schedule_op function
Signed-off-by: Nikhil Raj <nikhil.raj@arm.com>
Change-Id: I8579d2d6e55ab9888471bd780628df0f73438498
|
|
* Add neon detection for linux using HWCAPs
* Add test to check for backend throwing BackendUnavailable exception
Signed-off-by: Francis Murtagh <francis.murtagh@arm.com>
Change-Id: Ib74aeb06abe5f88f21ecdd1edb2a1cd20ee2019d
|
|
* Added GATHER operator support to TfLiteParser
* Added DEPTH_TO_SPACE operator support to TfLiteParser
Signed-off-by: Sadik Armagan <sadik.armagan@arm.com>
Change-Id: Id5d3b54e2d850eb9f19417029efbeb73a3029e69
|
|
* Implemented external delegate adaptor interface for TfLite
* Activated armnn logging for delegate
* Added logging info to indicate if gpu tuning is turned on
* Added pytests to ensure functionality of the external delegate adaptor
* Included the delegate directory into doxygen
* Added documentation on how to use the external delegate in python
Signed-off-by: Finn Williams <Finn.Williams@arm.com>
Signed-off-by: Jan Eilers <jan.eilers@arm.com>
Change-Id: Id3b4588fb0b9ac7e3f47ba2c19feead7beb58e18
|
|
Signed-off-by: Teresa Charlin <teresa.charlinreyes@arm.com>
Change-Id: I6504e922113aa9e397f53e570ebcf47e1f133945
|
|
* Report the error thrown
Signed-off-by: Sadik Armagan <sadik.armagan@arm.com>
Change-Id: If5e5160f43c11a284b919d76b04d9c4d53e9c56c
|
|
* Added ARG_MIN and ARG_MAX support to armnn_delegate
Signed-off-by: Sadik Armagan <sadik.armagan@arm.com>
Change-Id: Ia000c4b64378e28320164edd4df2902ca13dcda6
|
|
* Added generated schema file to the source tree
* Updated the ANdroid.mk file to pick up the Serializer/Deserializer source
Signed-off-by: Sadik Armagan <sadik.armagan@arm.com>
Change-Id: I12c2bf2ae7aa12374c60e671ff3a97eac5b7f161
|
|
* Added ModelOptions documentation to CLBackendModelContext
* Improved options descriptions in ExecuteNetworkProgramOptions.cpp
Signed-off-by: Matthew Sloyan <matthew.sloyan@arm.com>
Change-Id: I14f0c8bb4f299809b89f49c616b691e2f7956d5b
|
|
Signed-off-by: Nikhil Raj <nikhil.raj@arm.com>
Change-Id: I33dc1127627b4b89c02a3bea246eaf7499e5a780
|
|
* Added support for bias vector in TransposeConv to TfLite parser
* Added UnitTest
Signed-off-by: David Monahan <david.monahan@arm.com>
Change-Id: I6483986a9da9216084b4b885b7fd980fc3580fa9
|
|
* ArmnnQuantizer incorrectly converts boolean or integer DataTypes to quantized
DataTypes. This breaks layers like ArgMinMax where the output contains the
index of an element along an axis.
Signed-off-by: Mike Kelly <mike.kelly@arm.com>
Change-Id: I272c3d0f48bf884a2480bfa43eb14ec265fcda6b
|
|
* Fixed the ContributorGuide display issue
Signed-off-by: Sadik Armagan <sadik.armagan@arm.com>
Change-Id: I7be39cda5682a220dbd3708692230ab7421f80e0
|
|
Current we use 'A'rmNNQuantizer name for executable
and 'a'rmNNQuantizer as library name.
Since cmake does not allow same name for executable and library.
The old way is to use a captial letter for the executable name.
But it will create a problem on system (like macosx) that the file
system is case insensitive by default. Since it will create/overwritten
file on the same folder during the cmake build which makes build failed
when BUILD_ARMNN_QUANTIZER is enabled.
Fixed this by using ArmNNQuantizerMain as the executable
name during build, then rename it back to ArmNNQuantizer using
set_target_property OUTPUT_NAME function.
Signed-off-by: Keith Mok <ek9852@gmail.com>
Change-Id: I3e0779770c851c0eb6804e300a24836be955d07a
|
|
* Fixed issue where nightly job couldn't find flatbuffers import.
* Removed unnecessary commented code.
Signed-off-by: Matthew Sloyan <matthew.sloyan@arm.com>
Change-Id: If201f3fe54bf3bdd167aaf5d108154165d2a910d
|
|
* Float16 unit tests for Reshape
* Remove unsupported data type from Pad
Signed-off-by: Narumol Prangnawarat <narumol.prangnawarat@arm.com>
Change-Id: Ib1804bb6e708a0552fb40d05fe8a6511936f9793
|
|
* Remove need to update the guide for each release
by allowing user to check for newest version
Signed-off-by: Francis Murtagh <francis.murtagh@arm.com>
Change-Id: Ic6dda46524916762a06f24444bd7368ff1cde159
|
|
* Use ECONNREFUSED #define instead for connection refused error no.
* As error code on mips for example is 146
Change-Id: I2c725dc93ab8951d4f42a3ba51e747e01ced3a68
Signed-off-by: Francis Murtagh <francis.murtagh@arm.com>
|
|
* Enable ability to save/load ClContext in ExecuteNetwork.
Signed-off-by: Matthew Sloyan <matthew.sloyan@arm.com>
Change-Id: I58c61a53f6713853eb06520cc372ed47baf7f8c4
|
|
* Implemented Serialization and Deserialization of CLContext.
* Fixed flatbuffers android-nn-driver dependency.
!android-nn-driver:4772
Signed-off-by: Matthew Sloyan <matthew.sloyan@arm.com>
Signed-off-by: Sadik Armagan <sadik.armagan@arm.com>
Change-Id: If806f050535ffaa70922ba0f1ffe7bb10f902329
|
|
Signed-off-by: Keith Mok <ek9852@gmail.com>
Change-Id: I4b2926342bbf8621f7b7f5695cf1526dd7281bef
|
|
On macosx, the section rodata syntax is a
little bit different, add ifdef __MACH__
to fix that.
Signed-off-by: Keith Mok <ek9852@gmail.com>
Change-Id: Ic11d6faf8b8d3f3b521fd4305e6cdc3562a1c8ae
|
|
Signed-off-by: Nikhil Raj <nikhil.raj@arm.com>
Change-Id: I10e46b3c4b7d69bcb742014cb2633cfc061eb718
|
|
armnn support argmax and deconv , but caffe parser does not.
Add back this feature.
Signed-off-by: Keith Mok <ek9852@gmail.com>
Change-Id: I6b99cc4b58491204c41c6e1d11f583c65c628ee4
|
|
Signed-off-by: Keith Mok <ek9852@gmail.com>
Change-Id: I3a85de2d082d489fbf5a775c2ae551080d189294
|
|
Signed-off-by: Teresa Charlin <teresa.charlinreyes@arm.com>
Change-Id: I6a00045967fa48ec0913c8708ffc146a72ed2b87
|