aboutsummaryrefslogtreecommitdiff
path: root/src/runtime/CL/functions/CLConvolutionLayer.cpp
AgeCommit message (Expand)Author
2019-04-29COMPMID-2117 : Use FFT convolution if output feature map depth is less than i...Vidhya Sudhan Loganathan
2018-11-02COMPMID-1498 - Enable grouping in CLGEMMConvolutionLayerGian Marco Iodice
2018-11-02COMPMID-1188 - Fixed get_convolution_method in CLConvolutionLayerGian Marco Iodice
2018-11-02COMPMID-1160 Turn Graph hints into heuristicsGiorgio Arena
2018-11-02COMPMID-959 - Fix Validate in Convolution LayerIsabella Gottardi
2018-11-02COMPMID-792 - Re-enabled Winograd on NEON in all graph examples.Gian Marco Iodice
2018-11-02COMPMID-920: Introduce prepare() stageGeorgios Pinitas
2018-11-02COMPMID-1096 - Add fast_math flag to CLConvolutionLayerGian Marco Iodice
2018-11-02COMPMID-959: Sets memory manager to CLWinogradGeorgios Pinitas
2018-11-02COMPMID-1026 - Add support for 4x4 output tile in CLWinogradConvolutionLayerGian Marco Iodice
2018-11-02COMPMID-908 - Merge Activation layer with Convolution Layer (NEON. CL, GLES)Isabella Gottardi
2018-11-02COMPMID-1017: Implement dilated convolution in NEON, OpenCL, and GCAlex Gilday
2018-11-02COMPMID-754: Add validation to kernels.Georgios Pinitas
2018-11-02COMPMID-765 - Fix get_convolution_method in order to return the correct method.Isabella Gottardi
2018-11-02COMPMID-845: Create a ConvolutionLayer for CLIsabella Gottardi
2018-11-02COMPMID-790 - NEON: Add QASYMM8 support to ConvolutionIsabella Gottardi
2018-11-02COMPMID-816 - Enabled CLConvolutionLayer to use CLGEMM function insteadGian Marco
2018-11-02COMPMID-759 - CLGEMM optimization for McVail benchmarksGian Marco
2018-11-02COMPMID-556: Fix NEConvolutionLayer for fully connected convolution.Georgios Pinitas
2018-11-02COMPMID-556 - Fix examplesGian Marco
2018-11-02COMPMID-661: Convolution quantized (#32)Chunosov
2018-11-02COMPMID-661: Vectorize im2col and add lws heuristics for convolution kernels #46Anthony Barbier
2018-11-02IVGCVSW-601: support for asymetric padding in cl conv and depthwise convJaroslaw Rzepecki
2018-11-02COMPMID-485: Memory ManagerGeorgios Pinitas
2018-11-02COMPMID-477 - Optimized batched case in CLConvolutionLayerGian Marco Iodice
2018-11-02COMPMID-477 - Optimized Direct Convolution 3x3 and 5x5 (f32) for Bifrost.Gian Marco Iodice
2018-09-17COMPMID-417 - Fixed auto-config in NEConvolutionLayer and in CLConvolutionLayerGian Marco Iodice
2018-09-17COMPMID-440, COMPMID-441 - Port CLConvolutionLayer and CLFullyConnectedLayer ...Gian Marco Iodice
2018-09-17COMPMID-420, COMPMID-414 - Port CLConvolutionLayer and CLFullyConnectedLayer ...Gian Marco Iodice
2018-09-17COMPMID-432 - Extended Convolution Layer to support rectangular kernelsGian Marco Iodice
2018-09-17COMPMID-417 - Adding support for rectangular kernelsGian Marco Iodice
2018-09-17COMPMID-344 Updated doxygenAnthony Barbier