Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

[Bug] onnx shape inference result in an infinite loop #19870

Closed
inisis opened this issue Mar 12, 2024 · 4 comments
Closed

[Bug] onnx shape inference result in an infinite loop #19870

inisis opened this issue Mar 12, 2024 · 4 comments
Labels
stale issues that have not been addressed in a while; categorized by a bot

Comments

@inisis
Copy link
Contributor

inisis commented Mar 12, 2024

Describe the issue

described as title

To reproduce

model is provided here

import onnxruntime.tools.symbolic_shape_infer as onnxrt_symbolic_shape_inference

model = onnx.load('pnasnet5large.onnx')
model = (onnxrt_symbolic_shape_inference.SymbolicShapeInference.infer_shapes(model, auto_merge=True))

Urgency

No response

Platform

Linux

OS Version

ubuntu 1804

ONNX Runtime Installation

Released Package

ONNX Runtime Version or Commit ID

1.17.1

ONNX Runtime API

Python

Architecture

X64

Execution Provider

Default CPU

Execution Provider Library Version

No response

@tianleiwu
Copy link
Contributor

tianleiwu commented Mar 12, 2024

@inisis the model you uploaded does not have symbolic inputs.
There is no issue in onnx shape inference:

import onnx
onnx.shape_inference.infer_shapes_path('pnasnet5large.onnx', 'pnasnet5large_shape.onnx')

I can also run symbolic shape inference successfully (using a build from the main branch):

python -m onnxruntime.tools.symbolic_shape_infer --input pnasnet5large.onnx --output pnasnet5large_sym_shape.onnx --auto_merge

@inisis
Copy link
Contributor Author

inisis commented Mar 13, 2024

@inisis the model you uploaded does not have symbolic inputs. There is no issue in onnx shape inference:

import onnx
onnx.shape_inference.infer_shapes_path('pnasnet5large.onnx', 'pnasnet5large_shape.onnx')

I can also run symbolic shape inference successfully (using a build from the main branch):

python -m onnxruntime.tools.symbolic_shape_infer --input pnasnet5large.onnx --output pnasnet5large_sym_shape.onnx --auto_merge

Hi, the uploaded model is incorrect, could you please redownload it, I have checked it myself. Thanks

Copy link
Contributor

This issue has been automatically marked as stale due to inactivity and will be closed in 30 days if no further activity occurs. If further support is needed, please provide an update and/or more details.

@github-actions github-actions bot added the stale issues that have not been addressed in a while; categorized by a bot label Apr 12, 2024
@inisis
Copy link
Contributor Author

inisis commented Apr 13, 2024

close as merged

@inisis inisis closed this as completed Apr 13, 2024
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
stale issues that have not been addressed in a while; categorized by a bot
Projects
None yet
Development

No branches or pull requests

2 participants