Some Models failed to pass onnxruntime_test_python_symbolic_shape_infer.py
Open
Nobody has claimed this yet.
bug
- Dominant language
- Jupyter Notebook
- Stars
- 9.8k
- Forks
- 1.6k
- PR merge metrics
- No merged PRs in 30d
Description
Bug Report
SSD-MobilenetV1 with opset10 and opset12
call stack
FAIL: test_symbolic_shape_infer (__main__.TestSymbolicShapeInference)
----------------------------------------------------------------------
Traceback (most recent call last):
File "c:\git\onnxruntime\build\Windows\RelWithDebInfo\RelWithDebInfo\onnxruntime_test_python_symbolic_shape_infer.py", line 47, in test_symbolic_shape_infer
SymbolicShapeInference.infer_shapes(
File "D:\programs\Continuum\anaconda3\envs\onnxruntime\lib\site-packages\onnxruntime\tools\symbolic_shape_infer.py", line 2080, in infer_shapes
all_shapes_inferred = symbolic_shape_inference._infer_impl()
File "D:\programs\Continuum\anaconda3\envs\onnxruntime\lib\site-packages\onnxruntime\tools\symbolic_shape_infer.py", line 1909, in _infer_impl
self.dispatcher_[node.op_type](node)
File "D:\programs\Continuum\anaconda3\envs\onnxruntime\lib\site-packages\onnxruntime\tools\symbolic_shape_infer.py", line 743, in _infer_Concat
assert 0 == get_attribute(node, 'axis')
AssertionError
cc @snnn
Contributor guide
No contributing guide indexed for this repository
First steps
- Read the whole issue, then the project's contributing guide.
- Comment on the issue to say you are picking it up — it saves two people doing the same work.
- Fork the repository and make your change on a branch.
- Open a pull request that references the issue number.
Research direction
Start with onnxruntime_test_python_symbolic_shape_infer.py and reproduce the SSD-MobilenetV1 failures for opset10 and opset12. Then inspect symbolic_shape_infer.py around _infer_Concat and the failing model inputs to determine the expected behavior. Done means the symbolic shape inference test passes for both reported opsets.
Written by the indexing model from the issue text.
Assessment
- Tech stack
- python
- Domain
- machine-learning, testing-qa
- Issue type
- Bug
- Difficulty
- 3/5
- Estimated time
- 1-2 days
- Activity status
- Stale
- Clarity
- Needs clarification
- Newbie friendliness
- 35/100