aboutsummaryrefslogtreecommitdiff
path: root/ethosu/vela/graph_optimiser.py
AgeCommit message (Expand)Author
2020-11-20Revert "MLMBED-3450: Do not convert batched fully connected to conv"2.0.0.rc2Patrik Gustavsson
2020-11-20vela: Tanh and Sigmoid broken in fixup_act_reorderTim Hall
2020-11-20vela: Improve the scaling is equal checkTim Hall
2020-11-17MLMBED-3450: Do not convert batched fully connected to convAndreas Nevalainen
2020-11-13MLBEDSW-839: Code generation using external API2.0.0.rc1Louis Verhaard
2020-11-11MLBEDSW-3463: StridedSlice fixup function causes infinite recursionDwight Lidman
2020-11-11MLBEDSW-3019: Add profiling debug databaseTim Hall
2020-11-10MLBEDSW-3377: fixup_stridedslice_output may silently change CPU opsDwight Lidman
2020-10-26MLBEDSW-3283: Bug fix: StridedSlice Op is placed on CPUDiqing Zhong
2020-10-21vela: Improve the scaling is equal checkTim Hall
2020-10-16MLBEDSW-3004: UnpackReshaped can't be serialisedDwight Lidman
2020-10-12MLBEDSW-3154 Bug fix for LUT ops with IFM from SplitSliceReadLouis Verhaard
2020-10-08MLBEDSW-3148: Refactor OperationLouis Verhaard
2020-10-02MLBEDSW-3060 Adjust check if weights fit in sramPatrik Gustavsson
2020-09-30MLBEDSW-3153: Fix overflow in sigmoid LUTLouis Verhaard
2020-09-30[MLBEDSW-2802] Fix 5D tensor crashFredrik Svedberg
2020-09-29MLBEDSW-3032 Fixed issue in removal of reshapesPatrik Gustavsson
2020-09-29MLBEDSW-2031: LUT support tanh/sigmoidLouis Verhaard
2020-09-25MLBEDSW-2811: Add rescaling to ReLus with different scalingAndreas Nevalainen
2020-09-23MLBEDSW-3018 Change to check for avoiding NHCWB16Patrik Gustavsson
2020-09-21MLBEDSW-1693 Convert batched FC to ConvPatrik Gustavsson
2020-09-17MLBEDSW-3008: Replace Split ops with IdentityDwight Lidman
2020-09-11MLBEDSW-2745 Support relus with differing scalesMichael McGeagh
2020-09-11MLBEDSW-2994 Remove undesired reshape OPsPatrik Gustavsson
2020-09-08vela: Refactor op sets in graph_optimiserMichael McGeagh
2020-09-08MLBEDSW-2935: LUT fusing with preceding operatorLouis Verhaard
2020-09-03MLBEDSW-2906: Only add padding fields to Npu opsJacob Bohlin
2020-08-28MLBEDSW-2688: LUT calculation with different in/out scaleLouis Verhaard
2020-08-27Small fix for Softmax regressionJacob Bohlin
2020-08-26MLBEDSW-2688: use LeakyRelu for int16Louis Verhaard
2020-08-26MLBEDSW-2847: Fix for TransposeConv crash and u8 output diffJacob Bohlin
2020-08-24MLBEDSW-2654: Convert Resizebilinear to a number of 2x2 poolsCharles Xu
2020-08-24MLBEDSW-2688: LeakyRelu rewrite to LUT or MUL/MAXLouis Verhaard
2020-08-21MLBEDSW-2663: Handle optional tensorsJacob Bohlin
2020-08-19MLBEDSW-2779 Avoid NHCWB16 in some SplitSliceRead casesPatrik Gustavsson
2020-08-18MLBEDSW-2779 Consider num dimensions, in check for NHCWB16Patrik Gustavsson
2020-08-14MLBEDSW-2570 Avoid usage of NHCWB16 for some casesPatrik Gustavsson
2020-08-12MLBEDSW-2637 Utilise new tensor and operator funcsMichael McGeagh
2020-08-06Skip the NOP resizebilinear opCharles Xu
2020-08-05[MLBEDSW-2335] SoftMax int16Fredrik Svedberg
2020-08-05MLBEDSW-2569:Support 1x1 IFM ResizeBilinearCharles Xu
2020-07-30MLBEDSW-2660 Convert FC-like convs to FCMichael McGeagh
2020-07-30vela: Move common functionalityMichael McGeagh
2020-07-13MLBEDSW-2584: Support cascading of Transpose ConvolutionJacob Bohlin
2020-07-07MLBEDSW-2548: Fix for Double Buffer size estimateJacob Bohlin
2020-06-18Code clean-up using black and flake8Tim Hall
2020-06-18MLBEDSW-2379: Fix 1-element tensors that were marked as scalarsLouis Verhaard
2020-06-18MLBEDSW-1716: Transpose Convolution supportJacob Bohlin
2020-06-18MLBEDSW-2420: Improved support for dilated convolutionLouis Verhaard
2020-06-18MLBEDSW-2372: Failing assert for ResizeBilinear with upscale != 2xDwight Lidman
generated by cgit v1.2.1 (git 2.23.0) at 2024-05-23 04:17:40 +0000