aboutsummaryrefslogtreecommitdiff
AgeCommit message (Collapse)Author
2019-02-28IVGCVSW-2598 Update attribute to use num_splitv19.02branches/armnn_19_02Saoirse Stewart
Change-Id: I5de0e0a2de9241498213d274a6bf2a62ba7da7cc Signed-off-by: Saoirse Stewart <saoirse.stewart@arm.com>
2019-02-27IVGCVSW-2598 Fix for constant axis issue for Tensorflow ParserSaoirse Stewart
Change-Id: I8b081012529aed8e434273259c5a5ef7dc3afff7 Signed-off-by: Finn Williams <finn.williams@arm.com> Signed-off-by: Saoirse Stewart <saoirse.stewart@arm.com>
2019-02-27IVGCVSW-2764 Strengthen test for thread-safety in ProfilerMatthew Bentham
Replace assert with explicit conditions so that the checks are correctly performed in release builds. Change-Id: Id69ab3cc0aa8c61021642b7250e30c255f144a3a Signed-off-by: Matthew Bentham <matthew.bentham@arm.com>
2019-02-27IVGCVSW-2632 Fix RefMerger from QAsymm8 types with different quantization ↵Ferran Balaguer
parameters Change-Id: Ie67ce4966c5e5fef618876b027292da429de1485 Signed-off-by: Ferran Balaguer <ferran.balaguer@arm.com>
2019-02-26IVGCVSW-2560 Add support of SSD MobileNet to TensorFlowLiteSupport.mdNarumol Prangnawarat
* Add support for Custom operator - TFLite_Detection_PostProcess * Add Quantized SSD MobileNet to tested networks Change-Id: Id7e729ed02dbc401638b9832c8b9b5d71a6d31b7 Signed-off-by: Narumol Prangnawarat <narumol.prangnawarat@arm.com>
2019-02-26IVGCVSW-2560 Verify Inference test for TensorFlow Lite MobileNet SSDNarumol Prangnawarat
* Assign output shape of MobileNet SSD to ArmNN network * Add m_OverridenOutputShapes to TfLiteParser to set shape in GetNetworkOutputBindingInfo * Use input quantization instead of output quantization params * Correct data and datatype in Inference test Change-Id: I01ac2e07ed08e8928ba0df33a4847399e1dd8394 Signed-off-by: Narumol Prangnawarat <narumol.prangnawarat@arm.com> Signed-off-by: Aron Virginas-Tar <Aron.Virginas-Tar@arm.com>
2019-02-26IVGCVSW-2708 Add Serializer and Deserializer SpaceToBatchNdNattapat Chaimanowong
Change-Id: I14f2a660654dc87939fe413fafa9384f09594f68 Signed-off-by: Nattapat Chaimanowong <nattapat.chaimanowong@arm.com>
2019-02-26IVGCVSW-2429 Add Detection PostProcess Parser to TensorFlow Lite Parserkeidav01
* Added additional custom option use_regular_nms to JSON string * Renamed use_regular_non_max_suppression to use_regular_nms in parser Change-Id: I5431eabade6337f6f8c3372670862e32e9cda63c Signed-off-by: keidav01 <keith.davis@arm.com>
2019-02-26IVGCVSW-2683 Add Serializer & Deserializer for ConstantConor Kennedy
Change-Id: Iad7d89dfa963d9015cbe044f67aecc8bf6634b10 Signed-off-by: Conor Kennedy <conor.kennedy@arm.com>
2019-02-26IVGCVSW-2629 Adding support for uint8 in ExecuteNetwork to fix issues with ↵Éanna Ó Catháin
output tensor being all zero Change-Id: I4da1ffd684672fff0853fb053c3340d06a3bc165 Signed-off-by: Éanna Ó Catháin <eanna.ocathain@arm.com>
2019-02-26IVGCVSW-2756 Fix bug in ClSpaceToBatchNdWorkloadNattapat Chaimanowong
*Padding was not in format expected by Cl Change-Id: Id0de3fd2b306e31d555e2d67bc4406e5302dcd3b Signed-off-by: Nattapat Chaimanowong <nattapat.chaimanowong@arm.com>
2019-02-26IVGCVSW-2525 *Update TfLite supported operator listDerek Lamberti
Change-Id: Ia349d71ec966b37feaffb971c7a77bf8cd44501c Signed-off-by: Derek Lamberti <derek.lamberti@arm.com>
2019-02-25IVGCVSW-2751 When layers are Deserialized the layer name is lostÉanna Ó Catháin
* Fixed defect * Added unit tests to check names Change-Id: I67211110b90aabff6e00bccdadd1145423b07523 Signed-off-by: Mike Kelly <mike.kelly@arm.com> Signed-off-by: Éanna Ó Catháin <eanna.ocathain@arm.com>
2019-02-25Rename ArmNN schema file to ArmnnSchema.fbsMatthew Bentham
This makes the header file change to ArmnnSchema_generated.h, which is then unambiguous with respect to other generated schema files. Change-Id: Id7785ed74cced4dcd4d6bcbab81e53c6aeba973c Signed-off-by: Matthew Bentham <matthew.bentham@arm.com>
2019-02-25IVGCVSW-2762 Fix missing layer name and output slot index in DebugLayer outputAron Virginas-Tar
Change-Id: Idda9c8ba244c74d931105ced90c38a12d48df48a Signed-off-by: Aron Virginas-Tar <Aron.Virginas-Tar@arm.com>
2019-02-25Add strided-slice parser to tf-liteBruno Goncalves
Change-Id: I1821d7e8123c76823562dd2e8822c5293fcb18c3 Signed-off-by: Bruno Goncalves <bruno.slackware@gmail.com>
2019-02-25IVGCVSW-2757 Add check for wrong number of components supplied to const tensorSaoirse Stewart
Change-Id: Ia9bc6c73ce246712c41496a1cfe0bb6a1d2eb8e9 Signed-off-by: Saoirse Stewart <saoirse.stewart@arm.com>
2019-02-25Add minimum parser to tf-liteBruno Goncalves
Change-Id: I617c2715e0fb8d01b96fa9d3d5d9a16a33477b66 Signed-off-by: Bruno Goncalves <bruno.slackware@gmail.com>
2019-02-25Add maximum parser to tf-liteBruno Goncalves
Change-Id: Idaf6dd3f4d96dad01e1dc1a0d3fd6c146780626d Signed-off-by: Bruno Goncalves <bruno.slackware@gmail.com>
2019-02-25IVGCVSW-2721 Quantize and Dequantize aren't quite rightFrancis Murtagh
* Add check for infinity and negative infinity in quantize() * Add assert for NaN value in quantize and dequantize() * Add unit tests for infinity and negative infinity Change-Id: Ie60e1e15b289ccbf99df4a3281f067b82cc9f9bf Signed-off-by: Francis Murtagh <francis.murtagh@arm.com>
2019-02-22IVGCVSW-2735 Fail build if TfLite parser or armnnSerializer can't be builtMatthew Bentham
Change-Id: I39a2fee99218a0a31d8ce6c46d7cc1c0ca5b75d2 Signed-off-by: Matthew Bentham <matthew.bentham@arm.com>
2019-02-22Add space-to-batch-nd parser to tf-liteBruno Goncalves
Change-Id: I3bf86d44f811380559ec35eed0bc43b3bd97da80 Signed-off-by: Bruno Goncalves <bruno.slackware@gmail.com>
2019-02-22Add batch-to-space-nd parser to tf-liteBruno Goncalves
Change-Id: I1e210f88f19f38ab719008e119c8fed153a3dd95 Signed-off-by: Bruno Goncalves <bruno.slackware@gmail.com>
2019-02-22Add resize-bilinear parser to tf-liteBruno Goncalves
Change-Id: Id35db981b38348e5a941cfbb4cbdfe8cd617a254 Signed-off-by: Bruno Goncalves <bruno.slackware@gmail.com>
2019-02-22Add sub parser to tf-liteBruno Goncalves
Change-Id: I0e63d81d95528e6c278dc5fa8b87ccc1f8798130 Signed-off-by: Bruno Goncalves <bruno.slackware@gmail.com>
2019-02-22IVGCVSW-2589 Fix for checking out CL release branchAron Virginas-Tar
Change-Id: I3200cb7a88158ec3aabc6feaca452406d5408129 Signed-off-by: Aron Virginas-Tar <Aron.Virginas-Tar@arm.com>
2019-02-22IVGCVSW-2739 Updating the Readme.md and ContributorGuide.md files to add ↵Saoirse Stewart
references and links to the new MLPlatform.org website (the home for the machine learning platform Change-Id: I14819d71157ea32bb911f0a20ece3e5d2d59f64b Signed-off-by: Saoirse Stewart <saoirse.stewart@arm.com>
2019-02-22IVGCVSW-2749 Throw exception in TensorShape when requested index >= number ↵Aron Virginas-Tar
of dimensions Change-Id: I3589b1e901b0f81f6bb17848046a22829f91bb9e Signed-off-by: Aron Virginas-Tar <Aron.Virginas-Tar@arm.com>
2019-02-22IVGSVSW-2736 Fix dangling reference to temporary storageDerek Lamberti
Change-Id: Ie6c553798eac732f37148d81970366e5a4ede1be Signed-off-by: Derek Lamberti <derek.lamberti@arm.com>
2019-02-22IVGCVSW-2588 Update README files for 19.02Nattapat Chaimanowong
*Also update related Support.md files Change-Id: If832980fdebb136ab02333d99512fd39b9093b2b Signed-off-by: Nattapat Chaimanowong <nattapat.chaimanowong@arm.com>
2019-02-21IVGCVSW-2424 Add LOGISTIC Operator Support (CL)Finn Williams
* Added Logistic tests in ClLayerTests * Removed check for QuantisedAsymm8 in CLActivationWorkload Change-Id: I6950e18109504d8426b727cb6b7d19898c899024 Signed-off-by: Finn Williams <finn.williams@arm.com>
2019-02-21IVGCVSW-2748 Fix bug causing std::bad_alloc in MakeTensor()Aron Virginas-Tar
Change-Id: Iff6533396e594e2716e432223780d662d99d06ec Signed-off-by: Aron Virginas-Tar <Aron.Virginas-Tar@arm.com>
2019-02-21IVGCVSW-2589 Update CL pin to the 19.02 releaseFinn Williams
Change-Id: Ic3a0ab87ac1df94bd69a2b966b27f95a7ef47dc9 Signed-off-by: Finn Williams <finn.williams@arm.com>
2019-02-21IVGCVSW-2635 Update TensorFlowSupport.mdJim Flynn
* Also fixed a format issue in TfParser.hpp Change-Id: I5b0ae1d5909f03e166a40d3aca8859024cd5e5b6 Signed-off-by: Jim Flynn <jim.flynn@arm.com>
2019-02-21COMPMID-2007 Changing NDK version to 17b in the Build ArmNN with the Android ↵telsoa01
NDK guide. This is required by the Arm Compute Library for some of the v8 NEON intrinsics Change-Id: Icd4bfaf502c4ada55618b711603d5ff509674b55
2019-02-21IVGCVSW-2429 Add Detection PostProcess Parser to TensorFlow Lite Parserkeidav01
* Added parser function in TFLiteParser * Removed custom options gating * Added unit test * Removed template usage in VerifyTensorInfo for DeserializeParser Change-Id: If198654ed70060855a05f8aaed010293405bd103 Signed-off-by: keidav01 <keith.davis@arm.com>
2019-02-21IVGCVSW-2643 Add Activation to SerializerSupport.md and DeserializerSupport.mdAron Virginas-Tar
Change-Id: Id4a75051d8a93744346b91febcad0e62e7063495 Signed-off-by: Aron Virginas-Tar <Aron.Virginas-Tar@arm.com>
2019-02-21IVGCVSW-2639 Add Serializer & Deserializer for Fully ConnectedSadik Armagan
* Added FullyConnectedLayer to Serializer Schema Schema.fbs * Added FullyConnected serialization and deserialization support * Added FullyConnected serialization and deserialization unit tests Change-Id: I8ef14f9728158f849fa4d1a8d05a1a4170cd5b41 Signed-off-by: Sadik Armagan <sadik.armagan@arm.com> Signed-off-by: Aron Virginas-Tar <Aron.Virginas-Tar@arm.com>
2019-02-21IVGCVSW-2613 Support static quantization of BatchToSpaceFerran Balaguer
Change-Id: I44b12c5c246b7aacc789420dbe55a16efaab6f98
2019-02-21Fix typos in IVGCVSW-2645 Add Serializer & Deserializer for Pooling2druoyan01
Change-Id: I63fdf3e7fb6ba42e879942ee9664d7c84678d4e8 Signed-off-by: ruoyan01 <ruomei.yan@arm.com>
2019-02-21IVGCVSW-2610 Add Quantization Tool ExecutableJim Flynn
* Also added TensorInfos to the output slots in the SerializerTests to create valid ArmNN networks for serialization Change-Id: I092b1ac889dd5e05cb1c10c9dfb573acaf1970d9 Signed-off-by: Jim Flynn <jim.flynn@arm.com>
2019-02-20IVGCVSW-2702 Add Serializer and Deserializer for PermuteNattapat Chaimanowong
Change-Id: I56322cb935de42cfa25bd1fbb0c09d00c7a5dd2b Signed-off-by: Nattapat Chaimanowong <nattapat.chaimanowong@arm.com>
2019-02-20IVGCVSW-2643 Add Serializer & Deserializer for ActivationMike Kelly
* Added ActivationLayer to Schema.fbs * Added Activation serialization and deserialization support * Added serialization and deserialization unit tests Change-Id: Ib5df45f123674988b994ffe3f111d3fb57864912 Signed-off-by: Mike Kelly <mike.kelly@arm.com>
2019-02-20IVGSVSW-2736 Rename DeserializeParser => Deserializer & fix namespacesDerek Lamberti
Change-Id: I4166c0bbb5ba7f8b8884e71134c21f43d1fc27b0 Signed-off-by: Derek Lamberti <derek.lamberti@arm.com>
2019-02-20IVGCVSW-2636 Update serializer and deserializer README with new layersAron Virginas-Tar
Change-Id: Icba4e6e65027c4ac2dd08bd5a2662c4289ade8f3 Signed-off-by: Aron Virginas-Tar <Aron.Virginas-Tar@arm.com>
2019-02-20IVGCVSW-2685 Serialize / de-serialize the DepthwiseConvolution2d layerAron Virginas-Tar
Change-Id: I37e360c824b30cb14cbef86f6ff7636bc9382109 Signed-off-by: Aron Virginas-Tar <Aron.Virginas-Tar@arm.com>
2019-02-20IVGCVSW-2583 Update verison number for 19.02Saoirse Stewart
Change-Id: I9c28b8986d10b092ddc8e9b609006b27858bf6be Signed-off-by: Saoirse Stewart <saoirse.stewart@arm.com>
2019-02-20IVGCVSW-2436 Modify MobileNet SSD inference testNarumol Prangnawarat
* change MobileNet SSD input to uint8 * get quantization scale and offset from the model * change data layout to NHWC as TensorFlow lite layout * update expected output as result from TfLite with quantized data Change-Id: I07104d56286893935779169356234de53f1c9492 Signed-off-by: Narumol Prangnawarat <narumol.prangnawarat@arm.com>
2019-02-20IVGCVSW-2730 Fix bug in TfParser setting incorrect output shape for Addition ↵Nattapat Chaimanowong
Layer *Output shape was incorrectly set for case when the 2 inputs have same number of dimensions and each dimension has different (but broadcast compatible) size Change-Id: Ia617442b2b7f962c33792b94035236d26de70558 Signed-off-by: Nattapat Chaimanowong <nattapat.chaimanowong@arm.com>
2019-02-20IVGCVSW-2725 Fix issue with ExecuteNetwork and Guid'sSaoirse Stewart
Change-Id: I499b2ac3b51390fd725ea8afa64efc7e007be199 Signed-off-by: Saoirse Stewart <saoirse.stewart@arm.com>
generated by cgit v1.2.1 (git 2.23.0) at 2024-05-03 12:39:14 +0000