onnx-mlir/test/mlir
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
..
conversion [NFC] Rename passes for stylistic consistency. (#232) 2020-07-31 21:37:35 +08:00
krnl Introduce krnl.shape operation and its lowering (#267) 2020-08-19 12:57:40 -04:00
onnx Add shape inference and names (#266) 2020-08-27 15:46:27 -04:00
transform Shape inference for some ops in RNN models (#207) 2020-07-22 10:15:56 -04:00
CMakeLists.txt Compiling Models with Large Constant Arrays (#146) 2020-06-12 10:27:05 +08:00
lit.cfg.py Compiling Models with Large Constant Arrays (#146) 2020-06-12 10:27:05 +08:00
lit.site.cfg.py.in Remove whole archive linkage (#173) 2020-06-19 00:21:27 +08:00