onnx-mlir/src
Aman LaChapelle 24d0a2ac71
Add shape inference and names (#266)
* Add shape inference and names

 - Add shape inference for PRelu
 - Fix shape inference for group conv
   for ConvTranspose
 - Add input and output names for
   graphs (functions)
 - Add support for (u)int8 tensor
   attributes

* Fix format issues

* Revert formatting for gen_onnx_mlir.py

* Pads can have ArrayAttr and DenseElementsAttr so support both

* NumInputs is the number of graph inputs that don't have initializers

* Add test for 2D batchnorm

* Fix typo in define_loops in new 2d BN test

* Change 'name' to 'onnx_node_name'

* Fix Batchnorm for 2D I/O and add lowering test

Co-authored-by: Gheorghe-Teodor Bercea <gt.bercea@gmail.com>
2020-08-27 15:46:27 -04:00
..
Builder Add shape inference and names (#266) 2020-08-27 15:46:27 -04:00
Conversion Add shape inference and names (#266) 2020-08-27 15:46:27 -04:00
Dialect Add shape inference and names (#266) 2020-08-27 15:46:27 -04:00
Interface Error fix3 (#145) 2020-05-27 10:09:28 +08:00
Pass Introduce krnl.shape operation and its lowering (#267) 2020-08-19 12:57:40 -04:00
Runtime include stdlib.h on macOS (#236) 2020-07-30 16:48:31 +08:00
Tool Introduce krnl.shape operation and its lowering (#267) 2020-08-19 12:57:40 -04:00
Transform Introduce krnl.shape operation and its lowering (#267) 2020-08-19 12:57:40 -04:00
CMakeLists.txt Introduce krnl.shape operation and its lowering (#267) 2020-08-19 12:57:40 -04:00
ExternalUtil.hpp.in Call LLVM opt to optimize bitcode (#245) 2020-08-03 11:46:21 +08:00
InitMLIRPasses.hpp Add selected MLIR options (#213) 2020-07-09 18:12:57 -04:00
InitOMPasses.hpp Introduce krnl.shape operation and its lowering (#267) 2020-08-19 12:57:40 -04:00
MainUtils.cpp Introduce krnl.shape operation and its lowering (#267) 2020-08-19 12:57:40 -04:00
MainUtils.hpp Introduce krnl.shape operation and its lowering (#267) 2020-08-19 12:57:40 -04:00
main.cpp Add emitjni target (#204) 2020-07-11 13:23:13 +08:00