aboutsummaryrefslogtreecommitdiff
path: root/src
AgeCommit message (Expand)Author
2018-11-02COMPMID-617: Add validation to NEON functions.Georgios Pinitas
2018-11-02COMPMID-556: Fix CLDepthwiseConvolution3x3 Kernel.Georgios Pinitas
2018-11-02COMPMID-632: Integrated Assembly kernel GEMM U8 for Arm Cortex-A53.Michalis Spyrou
2018-11-02COMPMID-617 Add validation window to CLNormalizationLayerGiorgio Arena
2018-11-02COMPMID-617 Add validation window to CLPoolingLayerGiorgio Arena
2018-11-02COMPMID-661 Add optimal lws heuristics for the Bifrost direct_convolution ker...Anthony Barbier
2018-11-02COMPMID-697 - Rework GEMMLowp interface on OpenCLGian Marco
2018-11-02COMPMID-556 - Add QASYMM8 support for missing OpenCL kernelsGian Marco
2018-11-02COMPMID-699 - Add NEON functions for im2col and col2imGian Marco
2018-11-02COMPMID-556: Fix lws_hint CLSoftmaxLayerGeorgios Pinitas
2018-11-02COMPMID-632: Integrated Assembly kernel GEMM S8 for Arm Cortex-A53.Pablo Tello
2018-11-02COMPMID-464 Implement Depthwise separable convolution on NEONMichalis Spyrou
2018-11-02COMPMID-554 Add NodesMichalis Spyrou
2018-11-02COMPMID-632 Assembly: Integrate gemmlowp assembly versionMichalis Spyrou
2018-11-02COMPMID-556 Improved indentation and error handling in format_doxygen.pyAnthony Barbier
2018-11-02COMPMID-556 Add saturation to 8-bit activation. This prevents undefined overflowRob Hughes
2018-11-02COMPMID-464 Implement Depthwise separable convolution on NEONMichalis Spyrou
2018-11-02COMPMID-661: Fix scale border issue (#38)Daniil Efremov
2018-11-02COMPMID-556 - Passed _lws_hint in the run() method where was missingGian Marco
2018-11-02COMPMID-556: Set CLSoftmaxLayer temp buffers to resizable.Georgios Pinitas
2018-11-02COMPMID-677: Integrate HGEMM assembly kernel (generic CPUs)Pablo Tello
2018-11-02COMPMID-652 - Graph examples shouldn't need to link against OpenCLIsabella Gottardi
2018-11-02COMPMID-667: Add validation static method to NEON GEMMlowpGeorgios Pinitas
2018-11-02COMPMID-580 - Implement reference and CL/NEON validation for RemapSanghoon Lee
2018-11-02COMPMID-560 - Validation mismatches Gaussian Pyramid Half ScaleGian Marco
2018-11-02COMPMID-665 - NEON: Add QASYMM8 in place Activation layerGian Marco
2018-11-02COMPMID-617: Add validation methods to ML CL functions.Georgios Pinitas
2018-11-02COMPMID-661: Optimize FC layer with 2 new Bifrost kernels and LWS tuning (#33)Anton Lokhmotov
2018-11-02COMPMID-661: Add QASYMM8 support (and basic tests) to CLDepthwiseConvolution3...Dmitry Savenko
2018-11-02COMPMID-556 - Fixed static window in NEGEMMMatrixAccumulateBiasesKernelGian Marco
2018-11-02COMPMID-556: Fixes bias in CLDirectConvolutionLayer to be int32.Georgios Pinitas
2018-11-02COMPMID-670 - Extend Sobel testsIsabella Gottardi
2018-11-02COMPMID-683: Normalization layer API clarification.Georgios Pinitas
2018-11-02COMPMID-675: NEGEMMLowp Assembly IntegrationPablo Tello
2018-11-02APPBROWSER-298: Workaround Bifrost shader compiler issueJoel Liang
2018-11-02COMPMID-685 Extend CLTuner support to other DL functionsGiorgio Arena
2018-11-02COMPMID-661: issue# 23 Scale border fix (#26)Daniil Efremov
2018-11-02APPBROWSER-298, APPBROWSER-306: Reimplement the common code of compute shaderJoel Liang
2018-11-02COMPMID-676: Rework TensorInfo buildingGeorgios Pinitas
2018-11-02COMPMID-556: Fix CLNormalization issues.Georgios Pinitas
2018-11-02COMPMID-556 - Fix BatchNormalizationLayer (set weights target)Isabella Gottardi
2018-11-02COMPMID-678 Align Convolution InterfacesGiorgio Arena
2018-11-02COMPMID-583 - Implemented reference implementation and validation tests (NEON...Isabella Gottardi
2018-11-02COMPMID-675 - Fixed mismatches in GEMMLowpMatrixMultiplyKernel dotproduct pathPablo Tello
2018-11-02COMPMID-671: Add global pooling layer support.Georgios Pinitas
2018-11-02COMPMID-675 - Reworked NEGEMMLowp interface/functionGian Marco
2018-11-02COMPMID-556: Add support to build arm64-v8.2-a for Android platform (clang co...Ioan-Cristian Szabo
2018-11-02COMPMID-666: Adds the ability to import backing memory in a Tensor(CPU).Georgios Pinitas
2018-11-02COMPMID-661: Fix rounding in average pooling for uint8.Georgios Pinitas
2018-11-02COMPMID-661: softmax-uint8 implementation (#16)Chunosov
generated by cgit v1.2.1 (git 2.23.0) at 2024-06-01 01:17:41 +0000