aboutsummaryrefslogtreecommitdiff
AgeCommit message (Expand)Author
2018-11-02COMPMID-417: Fix valid regionMoritz Pflanzer
2018-11-02COMPMID-513 Choose maximum local workgroup size at run timesteniu01
2018-11-02COMPMID-417: Fix Yocto cross-compiles (Public pull request)Anthony Barbier
2018-11-02COMPMID-452 CL Depthwise Separable Convolution Layer kernel implementation, v...Giorgio Arena
2018-11-02COMPMID-417: Fix inclusion in QuantizationLayerGeorgios Pinitas
2018-11-02COMPMID-486 Add batch sizes 1, 4 and 8 to validation datasetsSiCong Li
2018-11-02COMPMID-345: Added support for 5x5 kernels in NEDirectConvolutionPablo Tello
2018-11-02COMPMID-477 - Optimized CLNormalizationLayerGian Marco Iodice
2018-11-02COMPMID-439: Implement NEON Quantization Layer.Michele Di Giorgio
2018-11-02COMPMID-345: Optimization for NEFillBorder kernel.Pablo Tello
2018-11-02COMPMID-417 - Optimizing reciprocal QS8/QS16Michalis Spyrou
2018-11-02COMPMID-431 Port OpenCL pooling layer to use fixed pointsteniu01
2018-11-02COMPMID-417 - Disabled DirectConvolutionLayer on AlexNet for NEONGian Marco Iodice
2018-11-02COMPMID-417 - Added DirectConvolution 5x5 in AlexNet system testGian Marco Iodice
2018-11-02COMPMID-477 - Optimizing Pooling 3x3 with stride_x <= 3 on OpenCLGian Marco Iodice
2018-11-02COMPMID-417: Cleanup NEON FullyConnectedLayerMoritz Pflanzer
2018-11-02COMPMID-417: Cleanup CL FullyConnectedLayerMoritz Pflanzer
2018-11-02COMPMID-415: Move FullyConnectedLayer to new validationMoritz Pflanzer
2018-11-02COMPMID-417 - Fixed call of direct convolution 1x1 for bifrostGian Marco Iodice
2018-11-02COMPMID-483 Add VGG16 benchmarksSiCong Li
2018-11-02COMPMID-477 - Optimized Direct Convolution 3x3 and 5x5 (f32) for Bifrost.Gian Marco Iodice
2018-11-02COMPMID-479 Add GoogleNetInceptionV4 benchmarksSiCong Li
2018-11-02COMPMID-417: Add in-place support for batch-normalization.Georgios Pinitas
2018-11-02COMPMID-479 Restructure system tests datasetsSiCong Li
2018-11-02COMPMID-450 Add YOLOV2 benchmark testsSiCong Li
2018-11-02Disabled CLANG assisted parsing as it's not supported by Jenkins and it is re...Anthony Barbier
2018-11-02COMPMID-415: Update test documentationMoritz Pflanzer
2018-11-02COMPMID-415: Improve SimpleTensor and RawTensorMoritz Pflanzer
2018-11-02COMPMID-415: Move BitwiseNot to new validationMoritz Pflanzer
2018-11-02COMPMID-415: Move BitwiseXor to new validationMoritz Pflanzer
2018-11-02COMPMID-478 Implemnt CL direct convolution 5x5steniu01
2018-11-02COMPMID-417: Fix missing includeMoritz Pflanzer
2018-11-02COMPMID-417 - BugFix Validate with valid_maskIsabella Gottardi
2018-11-02COMPMID-474 - Add support for QS8/QS16 DirectConvolution CLMichalis Spyrou
2018-11-02COMPMID-424 NEON/CL Harris Corners validation tests.Giorgio Arena
2018-11-02COMPMID-412: Port PoolingLayer to use fixed point 16.Michalis Spyrou
2018-11-02COMPMID-417 - Fixed bug in CLCol2ImKernek related to the stride passed during...Gian Marco Iodice
2018-11-02COMPMID-417 - Added clFinish to CLSymbolsGian Marco Iodice
2018-11-02COMPMID-417 - Added method to set the Local Workgroup size hintGian Marco Iodice
2018-11-02COMPMID-417 - Bug Fix WarpPerspective kernelIsabella Gottardi
2018-11-02COMPMID-417: Fix JSON printerMoritz Pflanzer
2018-11-02COMPMID-345: Added benchmarking tests for profiling Neon Direct Convolution.Pablo Tello
2018-11-02COMPMID-459 Collapse CL Im2col's higher dimensionssteniu01
2018-11-02COMPMID-477 - Optimizing CLDirectConvolution 3x3 on OpenCL and added the auto...Gian Marco Iodice
2018-11-02COMPMID-415 Fixed JSON printer to output errors as an array of single lines i...Anthony Barbier
2018-11-02COMPMID-417: Increase tolerance because of failuresMoritz Pflanzer
2018-09-17COMPMID-417 - Fixed auto-config in NEConvolutionLayer and in CLConvolutionLayerGian Marco Iodice
2018-09-17COMPMID-424 Implemented reference implementation and validation tests (NEON a...Isabella Gottardi
2018-09-17COMPMID-417: Fix invalid read in GEMMMoritz Pflanzer
2018-09-17COMPMID-: Implement L2NormalizationLayer.Georgios Pinitas