aboutsummaryrefslogtreecommitdiff
path: root/ethosu
AgeCommit message (Expand)Author
2020-09-23MLBEDSW-3018 Change to check for avoiding NHCWB16Patrik Gustavsson
2020-09-23MLBEDSW-3070: Fix addressing of weightsLouis Verhaard
2020-09-22MLBEDSW-2813: Handle non-const weights and check shapesAndreas Nevalainen
2020-09-21Fix int8/uint8 softmax mul shapeFredrik Svedberg
2020-09-21MLBEDSW-1693 Convert batched FC to ConvPatrik Gustavsson
2020-09-21MLBEDSW-2816: Fix assert in schedulerDiqing Zhong
2020-09-18MLBEDSW-2734: TensorFlow 2.3 compatibilityJacob Bohlin
2020-09-17[MLBEDSW-2638] Do not use 40bit ACC for softmax int16Fredrik Svedberg
2020-09-17MLBEDSW-2809: Redo the Tensor addressingJacob Bohlin
2020-09-17MLBEDSW-2377: Greedy allocator improvementLouis Verhaard
2020-09-17MLBEDSW-3008: Replace Split ops with IdentityDwight Lidman
2020-09-14[MLBEDSW-2845] Improve unit test coverage of fp_mathFredrik Svedberg
2020-09-14MLBEDSW-2816: remove constant array from SRAMDiqing Zhong
2020-09-11MLBEDSW-2745 Support relus with differing scalesMichael McGeagh
2020-09-11MLBEDSW-2994 Remove undesired reshape OPsPatrik Gustavsson
2020-09-11MLBEDSW-2813: Handle None tensor when parsing operatorsAndreas Nevalainen
2020-09-09vela: SHRAM alloc too big for some elementwise opsTim Hall
2020-09-08vela: Refactor op sets in graph_optimiserMichael McGeagh
2020-09-08optim: Fix issue with IFM streaming of LUTMichael McGeagh
2020-09-08MLBEDSW-2935: LUT fusing with preceding operatorLouis Verhaard
2020-09-07MLBEDSW-2874 Fix writing out empty tflite filesMichael McGeagh
2020-09-07[MLBEDSW-2928] Add batching to softmaxFredrik Svedberg
2020-09-04MLBEDSW-2819 Removed CLI-option permanent-storagePatrik Gustavsson
2020-09-03MLBEDSW-2814 Add support for inferred size in SplitVPatrik Gustavsson
2020-09-03MLBEDSW-2567: CLI option to specify allocation alignmentJacob Bohlin
2020-09-03[MLBEDSW-2905] Fix int16 multiplier saturationFredrik Svedberg
2020-09-03MLBEDSW-2906: Only add padding fields to Npu opsJacob Bohlin
2020-09-01MLBEDSW-2903 Split mapping to tensor1.2.0.rc31.2.0Patrik Gustavsson
2020-08-31MLBEDSW-2804: Removed invalid assert for shift rangeJacob Bohlin
2020-08-31MLBEDSW-2915: Added None check for bias before checking restrictionsJacob Bohlin
2020-08-30MLBEDSW-2919: bringup: int16 avgpool diff on FPGATim Hall
2020-08-29MLBEDSW-2804: Bias data type check wrongTim Hall
2020-08-28MLBEDSW-2900: softmax output diff on FPGATim Hall
2020-08-28[MLBEDSW-2900] zero point fix for int32 ifmFredrik Svedberg
2020-08-28MLBEDSW-2688: LUT calculation with different in/out scaleLouis Verhaard
2020-08-28MLBEDSW-2889: NHCWB16 format issue at end of subgraphTim Hall
2020-08-28MLBEDSW-2804: Added bias data type checkJacob Bohlin
2020-08-27[MLBEDSW-2857] Fix serialisation of non byte tensorsFredrik Svedberg
2020-08-27[MLBEDSW-2846] Do not use NHCWB16 for reduce_sum int32Fredrik Svedberg
2020-08-27Small fix for Softmax regressionJacob Bohlin
2020-08-27MLBEDSW-2786: Fix IFM order in binary operationDiqing Zhong
2020-08-27MLBEDSW-2719: Update kernel size checkAndreas Nevalainen
2020-08-26MLBEDSW-2686: Use NPU tensor format for noop reshapes.1.2.0.rc2Tim Hall
2020-08-26Update to HI 1.0.6Stefan Nannesson
2020-08-26MLBEDSW-2688: use LeakyRelu for int16Louis Verhaard
2020-08-26MLBED-2822 Added CLI-opt for weight size est.Patrik Gustavsson
2020-08-26MLBEDSW-2847: Fix for TransposeConv crash and u8 output diffJacob Bohlin
2020-08-26MLBEDSW-2688: LUT DMA may require kernel waitLouis Verhaard
2020-08-25MLBEDSW-2867: Split operators get placed on CPUDwight Lidman
2020-08-24MLBEDSW-2654: Convert Resizebilinear to a number of 2x2 poolsCharles Xu
generated by cgit v1.2.1 (git 2.23.0) at 2024-06-27 07:13:03 +0000