onnx / onnx/optimizer

Pass "fuse_bn_into_conv" introduces duplicate initializer.

Open
#174 0 comments 0 reactions 0 assignees View on GitHub

Nobody has claimed this yet.

Dominant language
C++
Stars
834
Forks
109
Avg merge
6h 55m
Merged PRs (30d)
2

Description

While fetching RetinaNet of opset=9 from ONNX Model Hub and optimizing it using fuse_bn_into_conv pass, I encounter the following error, related to the model initializer:

onnx.onnx_cpp2py_export.checker.ValidationError: 1133 initializer name is not unique.

Contributor guide

No contributing guide indexed for this repository

First steps

  1. Read the whole issue, then the project's contributing guide.
  2. Comment on the issue to say you are picking it up — it saves two people doing the same work.
  3. Fork the repository and make your change on a branch.
  4. Open a pull request that references the issue number.

Research direction

Reproduce the issue by fetching RetinaNet at opset=9 from ONNX Model Hub and running the fuse_bn_into_conv pass. Trace how the pass handles model initializers and verify that the optimized model no longer contains duplicate initializer names and passes ONNX validation.

Written by the indexing model from the issue text.

Assessment

Tech stack
cpp
Domain
tooling
Issue type
Bug
Difficulty
3/5
Estimated time
1-2 days
Activity status
Stale
Clarity
Mostly clear
Newbie friendliness
35/100

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.