aboutsummaryrefslogtreecommitdiff
path: root/src
AgeCommit message (Expand)Author
2019-03-29COMPMID-1995: Fixed graph fusion mutator for float types.Georgios Pinitas
2019-03-29COMPMID-1958: Implements 1D FFT in OpenCL.Georgios Pinitas
2019-03-29COMPMID-1975: Update depthwise convolution.Georgios Pinitas
2019-03-28COMPMID-2008: Add support for "reflect" padding mode in CLPadManuel Bottini
2019-03-28COMPMID-1318: Implementing Winograd 7x7 NHWC on OpenCL -- Part IMichele Di Giorgio
2019-03-27COMPMID-1995: Minor code fixes.Georgios Pinitas
2019-03-27COMPMID-1944 Add support for "reflect" padding mode in NEPadUsama Arif
2019-03-26COMPMID-2077 Optimise CLL2NormalizeLayerKernelUsama Arif
2019-03-25COMPMID-2076: Add StackLayer to the graph APIMichele Di Giorgio
2019-03-25COMPMID-2075 Segfault in NELSTMMichalis Spyrou
2019-03-22COMPMID-2056: Remove data layout check in NECopyLayerKernel and CLCopyLayerKe...Gian Marco Iodice
2019-03-20COMPMID-1932: Implement CLHeightConcatenateLayer.Pablo Tello
2019-03-20COMPMID-1995: Prepare Graph to support different input/output quantization infoIsabella Gottardi
2019-03-20COMPMID-2043: Add support for "dummy threads" in CLGEMMReshapedGian Marco Iodice
2019-03-19COMPMID-2065: Fix validation issue in NEGEMMLowpMMCoreGeorgios Pinitas
2019-03-19COMPMID-1995: Update RSH GEMM assembly kernels.Georgios Pinitas
2019-03-19COMPMID-1933: Implement NEHeightConcatenateLayer.Pablo Tello
2019-03-18Optimize CLDeconvolution-PART I: bug fixing CLGEMMLowpMatrixMultiplyCoregiuros01
2019-03-18COMPMID-1995: Fix compiler issues for invalid min,max arguments.Georgios Pinitas
2019-03-15COMPMID-1995: Fix NEActivation LogisticIsabella Gottardi
2019-03-15COMPMID-1694: Fuse offset contribution with the output stage when we use NEGE...George Wort
2019-03-14COMPMID-1995: Revert fusing convolution to batch norm due to performance regr...giuros01
2019-03-14COMPMID-1936: Add support for QASYMM8 in CLQuantizeLayer.Usama Arif
2019-03-14COMPMID-1281 Investigate concatenation for RNN/LSTM NEONJohn Kesapides
2019-03-13COMPMID-1844: Implement CLCropGeorge Wort
2019-03-13COMPMID-1935 Add support for QASYMM8 in NEQuantizeLayerJohn Kesapides
2019-03-13COMPMID-1995: Allow calculations being performed in pixels borders in conv.Georgios Pinitas
2019-03-13COMPMID-1995: Allow weights and bias to be passed as SubStream in FullyConnec...Michele Di Giorgio
2019-03-13COMPMID-1740: Fuse batch normalization with Convolution Layer at graph levelgiuros01
2019-03-12COMPMID-1964: Implement CLGEMMMatrixMultiplyReshapedOnlyRHS - Not transposedGian Marco Iodice
2019-03-12COMPMID-1995: Fix call_all_input_node_accessorsMichele Di Giorgio
2019-03-11COMPMID-1882: Improve memory coalescence when reshaping the weights for CLDep...Pablo Tello
2019-03-08COMPMID-1882: Improve memory coalescence when reshaping the weights for CLDep...Pablo Tello
2019-03-08COMPMID-2000: Implement CLGEMMMatrixMultiplyReshapedOnlyRHS - TransposedGian Marco Iodice
2019-03-05COMPMID-2034 Compilation error in bare metal buildManuel Bottini
2019-03-05COMPMID-1937: Adds support for DequantizationLayer for NEON/CL.Georgios Pinitas
2019-03-05COMPMID-2009: Add support for QASYMM8 in NEPixelWiseMultiplicationKernelManuel Bottini
2019-03-05COMPMID-1843: Implement NECropGeorge Wort
2019-03-05COMPMID-2010: Add support for QASYMM8 in NEArithmeticSubtractionKernelManuel Bottini
2019-03-04COMPMID-1946: Implement NEBatchToSpacegiuros01
2019-03-04COMPMID-1490 Create graph_convolution.cppJohn Kesapides
2019-03-01COMPMID-1947: Implement NESpaceToBatchgiuros01
2019-02-27COMPMID-1995: Fix output quantization CLDeptwiseConv3x3 when activation is fusedIsabella Gottardi
2019-02-22COMPMID-1601: Graph examples segfaulting on some platform when gles=1Georgios Pinitas
2019-02-22COMPMID-1710: Add FP16 support checks.Georgios Pinitas
2019-02-21COMPMID-1710: Fix NEReductionOperation border values for QASYMM8.Georgios Pinitas
2019-02-20COMPMID-1710: Quantization information missmatching issues.Georgios Pinitas
2019-02-20COMPMID-2007: Compilation failures with ndk16b.Georgios Pinitas
2019-02-19COMPMID-2006: NEON GEMMLowp assertion failure.Georgios Pinitas
2019-02-18COMPMID-2005: Tensors have different quantization information.Georgios Pinitas
generated by cgit v1.2.1 (git 2.23.0) at 2024-04-29 11:40:24 +0000