onnx-mlir/test/mlir/onnx
albertomagni-ms e1386b0689
Add shape inference for Ops used by BERT (#249)
* Add shape inference for Ops used by BERT

* Erf
* Pow
* ReduceMean
* Dropout
* Expand
  https://github.com/onnx/onnx/blob/master/docs/Operators.md#expand
  Deduce the value of the shape operand by looking at the producer
  of the operand.
  Currently supported producers are: onnx.Constant and onnx.Shape.

* Add corresponding tests for each op.

* Sort the list of ops with shape inference in gen_onnx_mlir.py
in alphabetic order for clarity.

* Restart CI

Co-authored-by: Tian Jin <tjingrant@gmail.com>
2020-08-07 13:08:00 +08:00
..
onnx_bundle_memory_pool.mlir [NFC] Rename passes for stylistic consistency. (#232) 2020-07-31 21:37:35 +08:00
onnx_canonicalization.mlir Add Rewrite rule to eliminate CastOp when input element type is the same as expected output element type (#237) 2020-07-27 12:49:14 -04:00
onnx_constprop.mlir constant folding for transpose of constant tensors (#171) 2020-06-17 10:42:06 -04:00
onnx_decompose.mlir ScalerOp support non-float input using CastOp (#231) 2020-07-24 10:57:52 -04:00
onnx_elide_constants.mlir Rework output to improve readability of intermediate MLIR code. (#87) 2020-04-24 16:15:36 -04:00
onnx_enable_memory_pool.mlir [NFC] Rename passes for stylistic consistency. (#232) 2020-07-31 21:37:35 +08:00
onnx_krnl_global_elision.mlir Remove optimize_loops/return_loops op. (#200) 2020-07-08 12:49:15 +08:00
onnx_lowering.mlir [NFC] Rename passes for stylistic consistency. (#232) 2020-07-31 21:37:35 +08:00
onnx_lowering_with_dealloc.mlir [NFC] Rename passes for stylistic consistency. (#232) 2020-07-31 21:37:35 +08:00
onnx_shape_inference.mlir Add shape inference for Ops used by BERT (#249) 2020-08-07 13:08:00 +08:00
onnx_shape_inference_maxpool.mlir Add the split marker to test files (#90) 2020-04-16 15:17:27 +08:00
onnx_structure.mlir Seq type (#199) 2020-07-31 20:05:59 +08:00