1. 351bd13 compmid-2573: Investigate FP16 Winograd reference implementations by giuros01 · 4 years, 11 months ago
  2. f948b10 COMPMID-2582: Disable fuse batch normalization on OpenCL for FP16 by Gian Marco Iodice · 5 years ago
  3. 169cda3 COMPMID-2055: Fusion of ConvolutionLayer with BatchNormalization at graph only for CL by Manuel Bottini · 5 years ago
  4. bffb41e COMPMID-2273: Fuse Batch Normalization with Depthwise Convolution layer at graph level (only for CL) by Manuel Bottini · 5 years ago
  5. 299fdd3 COMPMID-2177 Fix clang warnings by Michalis Spyrou · 5 years ago
  6. cadb368 COMPMID-1995: Fixed graph fusion mutator for float types. by Georgios Pinitas · 5 years ago
  7. 0ae5de9 COMPMID-1995: Prepare Graph to support different input/output quantization info by Isabella Gottardi · 5 years ago
  8. 749021a COMPMID-1995: Revert fusing convolution to batch norm due to performance regressions by giuros01 · 5 years ago
  9. acce504 COMPMID-1740: Fuse batch normalization with Convolution Layer at graph level by giuros01 · 5 years ago
  10. 1c32bf396 COMPMID-1451: Perform fusion before GroupConvolution unrolling by Georgios Pinitas · 6 years ago
  11. 60e9825 COMPMID-1451: Fuse activation in DepthwiseConvolution. by Georgios Pinitas · 6 years ago
  12. 08346e9 COMPMID-1451:Fuse RELU,LU_BOUNDED_RELU with requantization in NEGEMMConvolutionLayer. by Georgios Pinitas · 6 years ago
  13. 2a2db59 COMPMID-1505: Add native grouping support at graph level by Georgios Pinitas · 6 years ago
  14. 6f109bd COMPMID-1409: Disable BN + Act fusion in the graph if activation is not supported by Georgios Pinitas · 6 years ago
  15. d3a78ab COMPMID-1283: (GitHub issue) after convolution output data is zero by Georgios Pinitas · 6 years ago
  16. d9eb275 COMPMID-797: Switch to new graph. by Georgios Pinitas · 6 years ago[Renamed (94%) from src/graph2/mutators/NodeFusionMutator.cpp]
  17. d8734b5 COMPMID-793 : Add graph intermediate representation by Georgios Pinitas · 7 years ago