aboutsummaryrefslogtreecommitdiff
path: root/src
AgeCommit message (Expand)Author
2021-04-20Port CpuConvertFullyConnectedWeights to new APITeresa Charlin
2021-04-20Remove OpenCL padding: CLPixelWiseMultiplicationKernelGiorgio Arena
2021-04-20[Nightly #1129] CL/Winograd/ConvolutionLayer/F16 mismatch on Mate9Manuel Bottini
2021-04-20Remove experimental tracing featurePablo Marquez Tello
2021-04-19Added S32 Integer support to DIV operator in CLElementWiseOperations with TestsSuhail Munshi
2021-04-19CLInstanceNormalizationLayer NHWC optimisationPablo Marquez Tello
2021-04-19Port DepthwiseConvolution to new APIMichalis Spyrou
2021-04-19Remove padding from CLNormalizePlanarYUVLayerKernelSheri Zhang
2021-04-19Add Tensor related utilities to the new APISang-Hoon Park
2021-04-19Add padding consideration to pooling index computationSang-Hoon Park
2021-04-16Fix bug on Implicit Padding for NEON FFT2DManuel Bottini
2021-04-16Remove unnecessary use AccessWindowsMichele Di Giorgio
2021-04-16Add GEMM heuristic for Mali-G78Gian Marco Iodice
2021-04-14Remove unused AccessWindow* includesMichele Di Giorgio
2021-04-14Add support for a global allocator for OpenCL tensorsGeorgios Pinitas
2021-04-14Port NEDirectConvolutionLayer to new APIManuel Bottini
2021-04-14Remove OpenCL padding: CLNormalizationLayerKernelManuel Bottini
2021-04-13Port CLConvertFullyConnectedWeights to new APITeresa Charlin
2021-04-13Fix TILE initialization in direct convolution and winograd transformsGian Marco Iodice
2021-04-13Check data type lower bound when creating a tensorGeorgios Pinitas
2021-04-13Fix T_LOAD too few parameters issueSheri Zhang
2021-04-12Fix CLDepthwiseConvolutionLayer QSYMM8_PER_CHANNEL mismatchesGiorgio Arena
2021-04-12Add support for cl_image in CLDirectConvolutionLayerGian Marco Iodice
2021-04-12Fix OpenCL kernel compiling failure with array initializerSheri Zhang
2021-04-12Fix validation in reshape kernel [cpu,gpu]Gian Marco Iodice
2021-04-09Fix bug on Implicit Padding for CL GEMMMatrixMultiplyInterleavedTransposedManuel Bottini
2021-04-09Winograd Output transform 7x7 reworkGiorgio Arena
2021-04-09Fix OpenCL kernel compiling failure with array initilizerSheri Zhang
2021-04-08Rewritten Winograd (4x4, 5x5) output transformationAleksandr Nikolaev
2021-04-08Fix incorrect return statement in gemm_uint8 heuristic selectionGeorgios Pinitas
2021-04-08Ensure OpenCL runtimes are initialized firstMarco Antognini
2021-04-08Fix convolution with bias segmentation fault issueSheri Zhang
2021-04-08Rework the OpenCL Winograd Input Transformations NHWCGian Marco Iodice
2021-04-08Substitute CLFullyConnectedLayerReshapeWeights by CLTransposeTeresa Charlin
2021-04-08Substitute NEFullyConnectedLayerReshapeWeights by NETransposeTeresa Charlin
2021-04-07Implement Fanout mode in CPPSchedulerSiCongLi
2021-04-07Add per channel quantization support for NEDeconvolutionLayerFreddie Liardet
2021-04-06Correct Copyright datesMichalis Spyrou
2021-04-06Add tensor related data structures for the new APIGeorgios Pinitas
2021-04-06Remove OpenCL padding: CLL2NormalizeLayerKernelManuel Bottini
2021-04-06Mixed data-layout testing on high priority operatorsManuel Bottini
2021-04-01Added Qasymm8 datatype support to CLROIPoolingLayer with TestsSuhail Munshi
2021-03-31Fix trademarks throughout the codebaseMichele Di Giorgio
2021-03-31Remove alignment FIXMEMichele Di Giorgio
2021-03-31Remove Computer Vision generic interfaces and typesGeorgios Pinitas
2021-03-29Port ClTranspose to new APITeresa Charlin
2021-03-29Update U8 mmla kernelMichalis Spyrou
2021-03-29Remove usage of valid window region CL - NHWCMichalis Spyrou
2021-03-29NEGEMMConvolution and NEGEMMConv2d produce different resultsManuel Bottini
2021-03-29New variant of OpenCL Winograd (4x4,5x5) input transformationAleksandr Nikolaev
generated by cgit v1.2.1 (git 2.23.0) at 2024-05-12 00:46:13 +0000