microsoft / microsoft/onnxruntime
CumSum operator corner case causing an overflow
Open
@skottmckay is already working on this.
Since Sep 29, 2022.
core runtime
- Dominant language
- C++
- Stars
- 21.9k
- Forks
- 4.2k
- Avg merge
- 4d 8h
- Merged PRs (30d)
- 179
Description
Describe the issue
I've encountered a SafeIntOnOverflow exception when trying to execute the following model:
With an example input: [[1.0, 2.0]] I think the output should be equal to [[0.0, 0.0]]. The same happens when the axis is set to zero instead of -2. The model works fine with axis == 1.
To reproduce
Run the model from the description with any input tensor matching the input shape.
Urgency
No response
Platform
Linux
OS Version
Ubuntu 20
ONNX Runtime Installation
Released Package
ONNX Runtime Version or Commit ID
v1.12.1
ONNX Runtime API
Python
Architecture
X64
Execution Provider
Default CPU
Execution Provider Library Version
No response
Contributor guide
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.
Assessment
This issue has not been assessed yet.