onnx / onnx/optimizer

[BUG] The pass "eliminate_nop_flatten" causes output mismatch

Open
#276 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

[BUG] The pass "eliminate_nop_flatten" causes output mismatch

Issue
Running the single pass eliminate_nop_flatten with onnxoptimizer 0.4.2 changes numerical outputs.

Environment

  • Ubuntu 20.04
  • Python 3.10
  • onnx==1.19.0
  • onnxruntime==1.23.2
  • onnxoptimizer==0.4.2(latest)

Repro steps (run from this folder)

eliminate_nop_flatten_repro.tar.gz

  1. Create a Python environment (Python 3.10) and install dependencies:
python3 -m venv .venv
source .venv/bin/activate
pip install -U pip
pip install -r requirements.txt
  1. Optimize a case with only eliminate_nop_flatten (writes model.opt.onnx next to model.onnx):
  • python optimize_model.py --case ./case_02084_seed36754215
  1. Differential test original and optimized models with same oracle inputs (ORT graph optimization disabled):
  • python diff_test.py --case ./case_02084_seed36754215

Expected
eliminate_nop_flatten should be semantics-preserving. Applying this pass alone should not change any output values.

Differential Test Output Details

  1. case_03140_seed45116679 — mismatch; output[14] max_abs=4.022e+04 max_rel=4.022e+12, output[15] max_abs=5.190e+02 max_rel=5.120e+10; overall mismatch.
  2. case_00324_seed22816775 — mismatch; output[3] max_abs=5.022e+18 max_rel=1.000e+00; overall mismatch.
  3. case_09334_seed94166965 — mismatch; outputs 3, 4, 8-12, 14, 15 have max_abs=inf max_rel=inf (NaN-equal comparison enabled), output[13] max_abs=1.000e+00 max_rel=1.000e+00; overall mismatch.
Case: case_03140_seed45116679 (ORT graph optimizations disabled)
  output[14]: max_abs=4.022e+04, max_rel=4.022e+12, shape=(1, 21, 24)
  output[15]: max_abs=5.190e+02, max_rel=5.120e+10, shape=(32, 21, 24)
Overall: max_abs=4.022e+04, max_rel=4.022e+12

Case: case_00324_seed22816775 (ORT graph optimizations disabled)
  output[3]: max_abs=5.022e+18, max_rel=1.000e+00, shape=(51, 1, 1, 1)
Overall: max_abs=5.022e+18, max_rel=1.000e+00

Case: case_09334_seed94166965 (ORT graph optimizations disabled)
  outputs 3, 4, 8, 9, 10, 11, 12, 14, 15: max_abs=inf, max_rel=inf
  output[13]: max_abs=1.000e+00, max_rel=1.000e+00, shape=(4, 62)
Overall: max_abs=inf, max_rel=inf

Attachments

  • requirements.txt
  • optimize_model.py
  • diff_test.py (runs original and optimized with same oracle inputs; ORT graph optimizations disabled)
  • run_optimized_model.py (executes optimized model with same oracle inputs)
  • case_03140_seed45116679/, case_04011_seed52014128/, case_00324_seed22816775/(original models, optimized models, and oracle inputs)

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

Start with the attached optimize_model.py and diff_test.py, using the listed case directories and the provided Python environment to reproduce the mismatch. Compare the original and optimized model outputs with ORT graph optimizations disabled; done means eliminate_nop_flatten preserves all reported outputs.

Written by the indexing model from the issue text.

Assessment

Tech stack
cpp, python
Domain
tooling
Issue type
Bug
Difficulty
4/5
Estimated time
3-5 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.