onnx / onnx/models

Grad-Cam from ONNX model

Open
#668 0 comments 2 reactions 0 assignees View on GitHub

Nobody has claimed this yet.

enhancement
Dominant language
Jupyter Notebook
Stars
9.8k
Forks
1.6k
PR merge metrics
No merged PRs in 30d

Description

Feature Request

Ability to get subset of layers from a list of layers for a given model

What is the problem that this feature solves?

I'm interested in implementing Grad-CAM starting with an ONNX model and from my understanding, importing onnx saves each layer as an attribute of the model struct but there's no way to get a subset of the model other than rebuilding it manually.

Describe the feature

Why is this feature necessary? What does it accomplish?

Relevant Model Zoo feature areas

Which area in the Model Zoo infrastructure does this impact?
explainable AI, computer vision, backbones

Notes

Fairly new to burn and I'm excited to use it!

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 by examining how ONNX imports expose layers as attributes on the model struct, then review the Grad-CAM and explainable-AI requirements described in the issue. Define and validate an approach for selecting a subset of layers from a model so Grad-CAM can use it without manual rebuilding.

Written by the indexing model from the issue text.

Assessment

Domain
computer-vision, machine-learning
Issue type
Feature
Difficulty
5/5
Estimated time
Over a week
Activity status
Stale
Clarity
Needs clarification
Newbie friendliness
30/100

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.