onnx / onnx/optimizer

3 concatenations at the same time?

Open
#146 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

Most of the problems of edge devices is that onnx not simplifies concatenations. If we have 3 inputs at the same time, causes problems.
So solutions I think that can be
modify the original model at the position corresponding to 3 concatenations to
use two parallel Concat structures. For example, if the input nodes are A, B, C
and the output is Concat(A, B, C), modify it to Concat(Concat(A, B), C).
Specify the specific dimensions for the reshape operation in this process to
avoid abnormal precision caused by automatic inference.

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

No files, tests, or entry points are named. Start by locating the optimizer logic that handles ONNX Concat nodes and reproduce a case with three inputs. Done should mean the three-input concatenation is rewritten into nested two-input Concat structures, with reshape dimensions specified explicitly and edge-device behavior verified.

Written by the indexing model from the issue text.

Assessment

Tech stack
cpp
Domain
performance
Issue type
Feature
Difficulty
4/5
Estimated time
3-5 days
Activity status
Stale
Clarity
Needs clarification
Newbie friendliness
30/100

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.