ROCm / ROCm/AMDMIGraphX

PARSE_RESIZE: only nearest and linear modes are supported

Open
#2,764 1 comment 0 reactions 0 assignees View on GitHub

Nobody has claimed this yet.

Dominant language
C++
Stars
333
Forks
150
Avg merge
4d 19h
Merged PRs (30d)
54

Description

  • MIGraphX commit: 431e714
  • GPU: MI210 (gfx90a)
  • ROCm version: 6.0.1

Model(s) to reproduce:

Fails at: /code/AMDMIGraphX/src/onnx/parse_resize.cpp:166: get_mode: PARSE_RESIZE: only nearest and linear modes are supported!

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 at src/onnx/parse_resize.cpp:166, especially get_mode, and reproduce the failure with one of the linked CrossViT ONNX models. Identify the resize mode those models request and trace the parser's handling of it. Done means the affected models no longer fail at this unsupported-mode error and existing resize behavior remains covered.

Written by the indexing model from the issue text.

Assessment

Tech stack
cpp
Domain
machine-learning
Issue type
Bug
Difficulty
4/5
Estimated time
3-5 days
Activity status
Quiet
Clarity
Mostly clear
Newbie friendliness
45/100

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.