- b75d624 Graph Fusion With Post Ops Fix by ramelg01 · 2 years, 9 months ago
- 1d4a320 Fix node fusion mutator ordering by SiCongLi · 2 years, 10 months ago
- f2c022e Enable fast_math in CpuFullyConnected by cfRod · 2 years, 10 months ago
- c65023e Refine code for graph level fusion by Sheri Zhang · 2 years, 10 months ago
- fb22803 Add graph level convolution fusion with post operator by Sheri Zhang · 2 years, 10 months ago
- cc171f9 Provide tests for fusing pad layer in graph API by Gunes Bayir · 3 years ago
- 814bddf Fuse pad layer with subsequent convolution layer by Gunes Bayir · 3 years ago
- a46c9c9 Sync backend only if allocated rather than supported by Giorgio Arena · 3 years ago
- 9c67d38 Remove map/unmap overhead for input/output accessor when using DummyAccessor by Giorgio Arena · 3 years ago
- 59fd7a7 Add layer data to JSON output by Freddie Liardet · 3 years, 2 months ago
- 2b147ee Avoid multiple Rhs matrix transformation on ClGemm by Georgios Pinitas · 3 years, 2 months ago
- a387e27 Add in-place calculation support for CL elementwise arithmetic kernels by Sheri Zhang · 3 years, 2 months ago
- dd23f2a Add LayerData to all nodes by Freddie Liardet · 3 years, 2 months ago
- bc4e311 Implement FP GPU depthwise convolution 1x1 kernel for in-place computation by SiCongLi · 3 years, 2 months ago
- 1d35927 Add in-place computation for elementwise operations by Sheri Zhang · 3 years, 3 months ago
- bc91297 Fix node fusion mutator by SiCongLi · 3 years, 3 months ago
- 11d8415 Port DepthConvert to new Api by Georgios Pinitas · 3 years, 4 months ago
- 856f66e Port CLGEMM to memory injecting interface by Georgios Pinitas · 3 years, 4 months ago
- 2cd5b31 Remove unused CLCoreRuntimeContext by Georgios Pinitas · 3 years, 4 months ago
- 78e7691 Remove TODOs by Sheri Zhang · 3 years, 4 months ago
- 223aba9 Remove stale/solved TODOs by Michele Di Giorgio · 3 years, 4 months ago
- 402740d Add support for CLVK by Michalis Spyrou · 3 years, 4 months ago
- 562bee5 Port CpuConvertFullyConnectedWeights to new API by Teresa Charlin · 3 years, 4 months ago
- 33f41fa Fix trademarks throughout the codebase by Michele Di Giorgio · 3 years, 6 months ago
- 40efd53 Remove GLES-related code by Michele Di Giorgio · 3 years, 5 months ago
- f466d75 Add QASYMM8_SIGNED support to graph examples via graph mutator by SiCongLi · 3 years, 6 months ago
- 2ae0860 Fix redundant ternary operator in yolo node graph builder by Georgios Pinitas · 3 years, 6 months ago
- ceaa0bf Remove OpenGL ES support by Manuel Bottini · 3 years, 6 months ago
- b0cd5d8 Use polymorphic_downcast instead of dynamic_cast by Georgios Pinitas · 3 years, 6 months ago
- ac6499a Comply with Trademark rules for use of Neon, Arm and Mali by Sheri Zhang · 3 years, 7 months ago
- 6413e49 Add DIV to Elementwise layer support at graph level by Alessandro Navone · 3 years, 7 months ago
- 4841c97 Add mlgo to graph examples by SiCong Li · 3 years, 7 months ago
- 0f7ef8a Make memset/copy functions state-less by Georgios Pinitas · 3 years, 8 months ago
- b56c175 Generalization of CLTuner by Manuel Bottini · 3 years, 9 months ago
- 4d9687e Address RVO issue on some compilers by Georgios Pinitas · 3 years, 10 months ago
- c53266e Remove (CL/NE)UpsampleLayer in favor to (NE/CL)Scale by Georgios Pinitas · 3 years, 9 months ago
- 0b1c2db Remove (NE/CL)YoloLayer support by Georgios Pinitas · 3 years, 9 months ago
- 40f51a6 Update default C++ standard to C++14 by Georgios Pinitas · 3 years, 9 months ago
- bef7fa2 COMPMID-3639: (3RDPARTY_UPDATE) Move CL kernels to src by Sang-Hoon Park · 3 years, 10 months ago
- ebcebf1 COMPMID-3638: Move NEON kernels by Michalis Spyrou · 3 years, 10 months ago
- da4b1b2 COMPMID-3851: Fix output quantization info for SoftmaxLayerNode by Sheri Zhang · 3 years, 10 months ago
- 68dd25f COMPMID-3637: Move utility headers from arm_compute to src by Sang-Hoon Park · 3 years, 10 months ago
- 047c6fc COMPMID-3791: Add support for all activation types in NodeFusionMutator by Gian Marco Iodice · 4 years ago
- d64444b Add Reduction operation layer node to graph API by thecha01 · 4 years ago
- 3603aff Add L2Normalize layer node to Graph API by thecha01 · 4 years ago
- e8f05da Add ArgMinMax layer node to Graph API by thecha01 · 4 years ago
- 8a14b2c COMPMID-3748: Compiler issue with Bfloat16 on gcc8 by Georgios Pinitas · 4 years ago
- 2bfadd9 Add StridedSliceLayerNode to graph API by thecha01 · 4 years ago
- 0a05e6a Add DepthToSpace layer node to Graph API by thecha01 · 4 years ago
- 96a1400 Fix EltwiseLayerNode and QuantizationLayerNode by thecha01 · 4 years, 1 month ago
- 747a2c6 COMPMID-3698: Fix segfault running inception_v3, inception_v4, resnet50, resnet_v2_50 when running as qasymm8 on mate20 GPU by Sheri Zhang · 4 years ago
- f8e3584 Add support ElementwiseMax operator in graph API by thecha01 · 4 years, 1 month ago
- e357a25 COMPMID-3454 Patch1: Relocate data_type_from_name to core/Utils by SiCong Li · 4 years, 1 month ago
- f932d2c COMPMID-3386: Support memory injection in CLConcatenate functions/kernels by Michele Di Giorgio · 4 years, 2 months ago
- 4667ddd COMPMID-3374: Remove memory state from NEConcatenateLayer kernels by Georgios Pinitas · 4 years, 1 month ago
- d9eaf61 COMPMID-3324: Adjusting capitalization of Arm copyright claim to reflect Arm preferred presentation by Michele Di Giorgio · 4 years, 2 months ago
- 294f6ff COMPMID-3324: Allow in-place mutation on nodes with separate multiple inputs by Michele Di Giorgio · 4 years, 2 months ago
- 80feed5 COMPMID-3479: Perform in-place computations in NEElementwiseUnaryKernel by Manuel Bottini · 4 years, 3 months ago
- 3be0b8c COMPMID-3480: Enable in-place elementwise operations in graph API by Michele Di Giorgio · 4 years, 2 months ago
- 1902383 Revert "COMPMID-3480: Perform in-place computations in NEArithmeticAdditionKernel" by Michele Di Giorgio · 4 years, 2 months ago
- 16dddd2 COMPMID-3381: Implement graph example for YoLo v3 output detector by Sheri Zhang · 4 years, 3 months ago
- 4a61653 COMPMID-3480: Perform in-place computations in NEArithmeticAdditionKernel by Michele Di Giorgio · 4 years, 3 months ago
- 0905028 COMPMID-3069: Align graph convolution implementation for CL and NEON. by Georgios Pinitas · 4 years, 3 months ago
- 8b2a7d3 COMPMID-3101 Fuse activation with floating point elementwise operation layers in CL by Giorgio Arena · 4 years, 7 months ago
- 2e5fd63 COMPMID-3098 Fuse Relu and Bounded Relu with FullyConnected NEON by SiCongLi · 4 years, 6 months ago
- 104fbd7 COMPMID-3221: Add DeconvolutionLayerDescriptor by Sang-Hoon Park · 4 years, 6 months ago
- 797b76b COMPMID-3221: Add EltwiseLayerDescriptor by Sang-Hoon Park · 4 years, 6 months ago
- 6800117 COMPMID-3221: (DATA_UPDATE) add graph example for EDSR by Sang-Hoon Park · 4 years, 6 months ago
- 758b5ba COMPMID-3069: Improve build time by splitting up ToolchainSupport.h by Matthew Bentham · 4 years, 6 months ago
- 1856ff7 COMPMID-3097 Fuse activation with fully connected layer CL by Giorgio Arena · 4 years, 7 months ago
- 0b192e8 COMPMID-3067: Address gcc9 failures by Georgios Pinitas · 4 years, 6 months ago
- 102b0ce COMPMID-3105: Update pad layer to PadV2 by Georgios Pinitas · 4 years, 6 months ago
- 0082c36 Silence warnings related to "control reaches end of non-void function" by Matthew Bentham · 4 years, 7 months ago
- f8c4749 COMPMID-3083: Add graph support for PRelu by Georgios Pinitas · 4 years, 7 months ago
- 07fbe37 COMPMID-2819: Enable PadLayer on NEON graph backend. by Georgios Pinitas · 4 years, 7 months ago
- 0cb3da6 COMPMID-2985 change PoolingLayerInfo to struct by Sang-Hoon Park · 4 years, 7 months ago
- 6e9d0e0 COMPMID-2856 Add PrintLayer at graph level by Giorgio Arena · 4 years, 8 months ago
- f4261ad COMPMID-2779: Add support for generating synthetic int8 graphs. by Georgios Pinitas · 4 years, 9 months ago
- cd4e9ab COMPMID-2452: Add mnist example by Isabella Gottardi · 4 years, 10 months ago
- ee8cf32 COMPMID-2905: Fixed benchmark graph segfault. by Pablo Tello · 4 years, 10 months ago
- 5dea19e COMPMID-2579: Fuse batch normalization with convolution and depthwise convolution at graph level on NEON by Gian Marco Iodice · 4 years, 10 months ago
- d985378 COMPMID-2588: Optimize the output detection kernel required by MobileNet-SSD (~27% improvement) by Giuseppe Rossini · 4 years, 10 months ago
- 05069f0 COMPMID-2515: Merge optimized depthwise convolution to the generic depthwise convolution function by Manuel Bottini · 5 years ago
- 3f8cc58 COMPMID-2813: Update the heuristic in CLDepthWiseConvolutionLayer by Gian Marco Iodice · 4 years, 10 months ago
- db8485a COMPMID-2205: CL runtime context. by Pablo Tello · 5 years ago
- b27e13a COMPMID-2685: [CL] Use Weights manager by Michalis Spyrou · 5 years ago
- 04ea4e8 COMPMID-2581: Fuse batch normalization with convolution and depthwise convolution at graph level for OpenCL - FP16 by giuros01 · 5 years ago
- 879d131 COMPMID-2452: Fix compilation issues on armclang by Georgios Pinitas · 5 years ago
- 1a569a3 COMPMID-2161 [NEON] Create IWeightManager class by Michalis Spyrou · 5 years ago
- 26014cf COMPMID-2649: Generalize MemoryGroup. by Georgios Pinitas · 5 years ago
- 351bd13 compmid-2573: Investigate FP16 Winograd reference implementations by giuros01 · 5 years ago
- b9070a4 COMPMID-2605: Add asymmetric padding support for Deconvolution layer by Matthew Jackson · 5 years ago
- f948b10 COMPMID-2582: Disable fuse batch normalization on OpenCL for FP16 by Gian Marco Iodice · 5 years ago
- a7acb3c COMPMID-1849: Implement CPPDetectionPostProcessLayer by Isabella Gottardi · 6 years ago
- 169cda3 COMPMID-2055: Fusion of ConvolutionLayer with BatchNormalization at graph only for CL by Manuel Bottini · 5 years ago
- cf3abde COMPMID-2430: Adding FusedDepthwiseConvolutionBatchNormalizationLayer condition in NEON function factory by Manuel Bottini · 5 years ago
- 2ea3761 COMPMID-2336: Fix InPlaceMutator condition and add SaveNumpyAccessor by Isabella Gottardi · 5 years ago
- bffb41e COMPMID-2273: Fuse Batch Normalization with Depthwise Convolution layer at graph level (only for CL) by Manuel Bottini · 5 years ago
- c1b76fa COMPMID-2092: Refactoring interface for the deconvolution kernels (NEON/CL) by Manuel Bottini · 5 years ago
- 30271c7 COMPMID-2156: Optimized dilated convolution for NEON. by Georgios Pinitas · 5 years ago