aboutsummaryrefslogtreecommitdiff
path: root/src/armnn/layers
AgeCommit message (Collapse)Author
2019-05-13MLCE-101: Adding dilation support in conv and dconvPablo Tello
Added support for dilation in DepthwiseConvolution2d in the Neon and CL backends. Change-Id: Ie1522b498c07f80d6efcf9dc79e926c8cfa06ca5 Signed-off-by: Pablo Tello <pablo.tello@arm.com>
2019-04-30IVGCVSW-3021 Add end-to-end flow control integration testMatthew Bentham
Currently asserts that the net fails to optimise as that is the expected behaviour, but it's complete enough to exercise most of the code in SwitchLayer.cpp and MergeLayer.cpp Also, fix a bug in SwitchLayer::ValidateTensorShapesFromInputs found by the new test. Also, make topological sort slightly more robust to missing connections as it should not be the job of the sorter to validate the graph. Change-Id: I30b9e2d4769ab14a6820284871a79a5bb3eef1ef Signed-off-by: Matthew Bentham <matthew.bentham@arm.com>
2019-04-30IVGCVSW-2405 Rename SubGraph to SubgraphViewDerek Lamberti
Change-Id: Ie50aeccf053c20c3a01a75042bbc3acd824375af Signed-off-by: Derek Lamberti <derek.lamberti@arm.com> Signed-off-by: Matteo Martincigh <matteo.martincigh@arm.com>
2019-04-18IVGCVSW-2980 Build ArmNN with the latest version of the driver stack libraryMatteo Martincigh
* Changed the pre-compiled object held by the pre-compiled layer into a unique pointer, so that now the layer has the ownership of it * Changed the pre-compiled object held by the descriptor and the workload into a naked pointer, to leave the ownership to the layer Change-Id: I4a582e45ca0aa3978e8e40b786c743a6eddce852 Signed-off-by: Matteo Martincigh <matteo.martincigh@arm.com>
2019-04-16IVGCVSW-2957 MergerLayer subtensor optimization now backend agnosticDerek Lamberti
+ Update clframework pin + Cl and Neon Merger workloads updated to use MemoryLayout agnostic API + Workloads only use sub-tensor optimization if ALL input tensors are sub-tensors + Refactor LayerSupportCommon code to be a bit more succinct Change-Id: Ib61ad4ccbd767e924dff07e61022e0cda4069828 Signed-off-by: Derek Lamberti <derek.lamberti@arm.com>
2019-04-05IVGCVSW-2914 Add Switch Layer and no-op factory methodSadik Armagan
Change-Id: I6a6ece708a49e8a97c83a3e7fec11c88af1e1cfa Signed-off-by: Sadik Armagan <sadik.armagan@arm.com> Signed-off-by: Aron Virginas-Tar <Aron.Virginas-Tar@arm.com>
2019-04-05IVGCVSW-2915 Add Merge Layer and no-op factory methodNattapat Chaimanowong
Change-Id: I54549671e0d3b207904cf9796a843eb2b0a631f7 Signed-off-by: Nattapat Chaimanowong <nattapat.chaimanowong@arm.com>
2019-04-01IVGCVSW-2871 Ref QuantizeLayer workloadDerek Lamberti
Change-Id: If048b2a053c542b31ae344fe0af04d9b4f40eb6d Signed-off-by: Derek Lamberti <derek.lamberti@arm.com>
2019-03-28IVGCVSW-2874 Add DequantizeLayer and no-op factory methodNattapat Chaimanowong
*Add Dequantize layer to the frontend *Add Serializer and Deserializer for Dequantize Change-Id: Ide2647b9e0348d599deb97e61ca4bf66e2f17fc0 Signed-off-by: Nattapat Chaimanowong <nattapat.chaimanowong@arm.com>
2019-03-27IVGCVSW-2870 Support QuantizeLayer on frontendDerek Lamberti
Change-Id: I2014a8d801f1f222d27a80dddf4f188ddcb3a5c9 Signed-off-by: Derek Lamberti <derek.lamberti@arm.com>
2019-03-26IVGCVSW-2881 Remove DebugDescriptorNattapat Chaimanowong
* Also update Debug layer to use layer guid information Change-Id: I9ec1f639299c3f855b670ff031a0e88d685cfc6b Signed-off-by: Nattapat Chaimanowong <nattapat.chaimanowong@arm.com>
2019-03-21IVGCVSW-2694: serialize/deserialize LSTMJim Flynn
* added serialize/deserialize methods for LSTM and tests Change-Id: Ic59557f03001c496008c4bef92c2e0406e1fbc6c Signed-off-by: Nina Drozd <nina.drozd@arm.com> Signed-off-by: Jim Flynn <jim.flynn@arm.com>
2019-02-28IVGCVSW-2763 Fix bug in BatchToSpaceNdLayer::InferOutputShapesNattapat Chaimanowong
*Also added test case for non-zero crop and moved BatchToSpaceNd test functions together Change-Id: I142ba356165618b2811a4ab650ca6ced35220d9c Signed-off-by: Nattapat Chaimanowong <nattapat.chaimanowong@arm.com>
2019-02-14IVGCVSW-2620 Support static quantization of ConstantMatteo Martincigh
* Added VisitConstantLayer to QuantizerVisitor * Added unit tests and refactored QuantizerTest.cpp * Code cleanup Change-Id: I118fd2be085fc98879c5cfaa09698a7c98ba13f0 Signed-off-by: Matteo Martincigh <matteo.martincigh@arm.com>
2019-02-11IVGCVSW-2676 Make biases optional in ILayerVisitor for Convolution2D, ↵Aron Virginas-Tar
DepthwiseConvolution2D and FullyConnected Change-Id: I3048504ff699fdb266488e7c07b7262e5843d4b0 Signed-off-by: Aron Virginas-Tar <Aron.Virginas-Tar@arm.com>
2019-02-08IVGCVSW-2559 End to end tests for Detection PostProcessNarumol Prangnawarat
* end to end tests for Detection PostProcess float and uint8 * add anchors to AddDetectionPostProcessLayer * add anchors to VisitDetectionPostProcessLayer * refactor code Change-Id: I3c5a9a4a60b74c2246b4a27692bbf3c235163f90 Signed-off-by: Narumol Prangnawarat <narumol.prangnawarat@arm.com>
2019-02-07IVGCVSW-2553 Add Unit Test for ConstTensor layer visitorsjimfly01
Change-Id: I20a67135e4af7aa1f28f5000d73122f4e5e3acd5 Signed-off-by: Jim Flynn <jim.flynn@arm.com>
2019-02-07IVGCVSW-2609 Quantize BatchNormalizationLayerDerek Lamberti
Change-Id: I7b847112a0322ffc8b88a0708d8439bfb97cfe2c Signed-off-by: Derek Lamberti <derek.lamberti@arm.com>
2019-01-29IVGCVSW-2569 Add implementation of ConstTensor Accept functionsjimfly01
* Create the required ConstTensors and pass them to the appropriate visit method. Back fill of dummies added during IVGCVSW-2547 * Moved the VisitDetectionPostProcessLayer function declaration in ILayerVistor to its correct location after the VisitDepthwiseConvolution2dLayer functions. Change-Id: I0bd2f8c3603cbdb933b1216ead96dd8273eb5013
2019-01-25IVGCVSW-2556 Add Layer implementation for Detection PostProcessNarumol Prangnawarat
* Add DetectionPostProcessDescriptor. * Add implementation for DetectionPostProcessLayer. * Unit test to validate output. Change-Id: If63e83eb2a2978c549071c7aeb272906e7c35fe9
2019-01-25IVGCVSW-2547 Add Accept function to IConnectableLayerjimfly01
* Layers which callback VisitXXXLayer with ConstTensor have been implemented with dummies to speed up implementation and unblock IVGCVSW-2531 Change-Id: I49b8035f12ec72d6bd6cee95075692f98c48e193
2019-01-24IVGCVSW-2555 Add no-op implementation for Detection PostProcessNarumol Prangnawarat
* Added DetectionPostProcessQueueDescriptor to WorkloadData * Added CreateDetectionPostProcess function in WorkloadFactory.hpp * Added stub implementation of the CreateDetectionPostProcess in workload factories * Added DetectionPostProcessLayer stub implementation * Added AddDetectionPostProcessLayer to Network * Added IsDetectionPostProcessSupported to LayerSupportBase Change-Id: Ifc071b3b6b12877c997bdcc43d769c8f891d5c6c
2019-01-22IVGCVSW-2509 Add GatherLayer implementationnarpra01
* implementation of ValidateTensorShapesFromInputs * unit tests Change-Id: I1ed88f8ba0ea20329a259c5f36caea4b1fbeb013
2019-01-16IVGCVSW-2508 Add no-op factory implementations and layer for Gather operatornarpra01
* Added GatherQueueDescriptor to WorkloadData * Added CreateGather function in WorkloadFactory.hpp * Added stub implementation of the CreateGreater function in workload factories * Added GatherLayer stub implementation * Added AddGatherLayer to Network * Added IsGatherSupported to LayerSupportBase Change-Id: I0408fd54e88a7d4e3d9e1c2811a9323f0da52a04
2019-01-15IVGCVSW-2454 Merge together the pluggable backends work (was in aMatteo Martincigh
separate branch) and master * Brings in all the changes done for the pluggable backends * Added sub-graph support and tests * Added precompiled layer support and tests * Moved BackendSettings to a separate file * Removed the backend-specific code * Ported DebugLayer and associated functionality * Included fixes to make those changes work with master Change-Id: Id7028fa7917527b844628d5aff5732e3d94c0488
2019-01-07IVGCVSW-2371 Add Rsqrt Ref implementationMohamed Nour Abouelseoud
*Added Unit Tests Change-Id: I6cceb8e6dcda35ce08415f8e5ca86019a64d26e3
2019-01-04MLCE-77 Depthwise Convolution with depth multiplier > 1 doesn't workMatteo Martincigh
* Unified ArmNN's weight format to [ M, I, H, W ] for the depthwise convolution * Added conversion utilities to permute/reshape the weights as appropriate when using CL and Neon backends * Updated the reference implementation of the convolution * Updated the relevant unit tests accordingly !android-nn-driver:459 Change-Id: I07d0818efa9d1ca1e5dad82983aac1fe78eadb18
2018-12-24IVGCVSW-59 Add documentation to the public APIConor Kennedy
* Add documentation to the Descriptors * Add documentation to the layers Change-Id: I5e0849753903565227fd47d329a600fd90b2feb9
2018-12-17IVGCVSW-2398 Add no-op factory implementations for all backends for theFrancisMurtagh
Equal operation * Add QueueDescriptor in WorkloadData.hpp * Add CreateEqual function in WorkloadFactory.hpp * Added stub implementation of the CreateEqual function in RefWorkloadFactory, NeonWorkloadFactory and ClWorkloadFactory Change-Id: Iec6dc2f989c67fa6f0c32cfb93508995c8580783
2018-12-14IVGCVSW-2377 Add no-op factory implementations for all backends for theMatteo Martincigh
Greater operation * Added QueueDescriptor in WorkloadData.hpp * Added CreateGreater function in WorkloadFactory.hpp * Added stub implementation of the CreateGreater function in RefWorkloadFactory, NeonWorkloadFactory and ClWorkloadFactory * Added GreaterLayer stub implementation * Renamed ArithmeticBaseLayer to ElementwiseBaseLayer Change-Id: I7e38c2936de905da921a92ba3f918478169ec7f5
2018-12-06IVGCVSW-2315 Add descriptor for DebugNattapat Chaimanowong
Change-Id: I6b26c681989ef815752186f027a245ef8da7aea2
2018-12-05IVGCVSW-2264 Move DataLayoutIndexed to armnnUtilsMatteo Martincigh
* Since DataLayoutIndexed is now required in the TF parser, this changes move it to the armnnUtils library so that it'll be accessible by the armnnTfParser * Modified CMake files and Android.mk files accordingly Change-Id: Ie2620359ef288aeff64cb9e9bec068a466eee0e9
2018-12-03IVGCVSW-2315 Add DebugLayer and no-op factory methodNattapat Chaimanowong
Change-Id: I5455b720565248ff94278e76887d63f8434a7b58
2018-11-29IVGCVSW-2245 Add Minimum Layer and no-op Factory implementationkevmay01
Change-Id: I03fa374fd9692d98257de709f8c3ad0a49c88b95
2018-11-28IVGCVSW-2253 Add maximum layer and corresponding no-op factory implementationNattapat Chaimanowong
Change-Id: I8964f5e8978c2d2a07734a381e3f7c656c22456a
2018-11-26IVGCVSW-2087 Reference implementation and unit tests for StridedSliceNattapat Chaimanowong
Change-Id: Ifeacc0adb4547c72537b9ea7a61bf3c4ec3673fa
2018-11-21IVGCVSW-2086 Update StridedSliceLayer and StridedSliceDescriptorNattapat Chaimanowong
Change-Id: Ifa88a879dd239f60ab27330d6b73859393828ef0
2018-11-20IVGCVSW-2043 Merger using ACL for innermost concat axisMatteo Martincigh
* Fixed unsigned to signed conversion error that was breaking master Change-Id: I08d79d9bf131eb46ea0495371160698ab59c1721
2018-11-19IVGCVSW-2169 Remove DataLayoutIndexed from public APIMatthew Bentham
Change-Id: If8d8087d9d365e467d3ca9bf9c40d7219cb75cfd
2018-11-19IVGCVSW-2168: Remove DataLayout from LayerAron Virginas-Tar
Change-Id: Iab6ad04e5c786e4e639578f7b1d1537dd1196e2f
2018-11-19IVGCVSW-2043 - Merger using ACL for innermost concat axisNikhil Raj
* Add ClMergerWorkload and NeonMergerWorkload to call ACL for innermost concat axis * Modify layer support to call ClMergerWorkloadValidate and NeonMergerWorkloadValidate when concat axis is inner most * Add m_ConcatAxis to MergerDescriptor * Modify MergerQueueDescriptor::Validate to check sub tensor only when using subtensor !android-nn-driver:166 Change-Id: I56676b43964c8d6d726387b41b3cc34a512c0f0a
2018-11-16IVGCVSW-2092 Port LSTMCell::Eval to ArmNNMatteo Martincigh
* Ported Google's LSTM implementation to RefLstmFloat32Workload * Fixed the code throughout because of an error in the docs around the scratch buffer size * Updated IsLstmSupported * Added the unit tests !android-nn-driver:127 Change-Id: I5577b7e39ca52df1a7f102a9b437df6aa99520b6
2018-11-15IVGCVSW-2086: Add StridedSlice layer & corresponding no-op factory ↵Conor Kennedy
implementations Change-Id: I906dcb8b4c9b491bf3a661f208c09d0ea1c0fa35
2018-11-14IVGCVSW-2054: Fixing issue with InferOutputShape implementation in ↵Éanna Ó Catháin
BatchToSpaceNdLayer. * added Unit test Change-Id: I80f55e8c7afb39d96006c8dd027fc9683ea8182e
2018-11-12Tidying up multiple issuesÉanna Ó Catháin
* Fixed error in InferOutputShape implementation * Added better error checking to the BatchToSpace implementation. * Added defaults to the batchToSpace descriptors. * Changed crops to be a vector of pairs to align with the SpaceToBatch implementation Change-Id: Ib1c16d871f0898a1caeb6629c1fee6380a773e14
2018-11-12IVGCVSW-2054: BATCH_TO_SPACE_ND Reference implementation and Unit tests.Éanna Ó Catháin
Change-Id: I13c6728dbb60643d0e086d171225c5d802987f92
2018-11-02IVGCVSW-1946: Remove armnn/src from the include pathsAron Virginas-Tar
Change-Id: I663a0a0fccb43ee960ec070121a59df9db0bb04e
2018-11-02IVGCVSW-2093 Add SpaceToBatchNd layer and corresponding no-op factory ↵Nattapat Chaimanowong
implementations Change-Id: Ibd457f3a2d4342c4d6335bd3c471282a14ab6b14
2018-10-27IVGCVSW-2083 - Add DataLayout parameter to calculate the expected output ↵narpra01
shape in ValidateTensorShapesFromInputs * Convolution2dLayer * DepthwiseConvolution2dLayer * Pooling2dLayer * ResizeBilinearLayer * Unittests for ValidateTensorShapesFromInputs Change-Id: I057caf8a90d822175a7dd7271f960b65c6154bb4
2018-10-25IVGCVSW-2051 Fixed the dynamic allocation of the dimSizes array in MeanLayerMatteo Martincigh
Change-Id: I6e39f1e1bc32c0c2c1953da00016edd68c48d4e0
generated by cgit v1.2.1 (git 2.23.0) at 2024-06-29 15:06:09 +0000