pytorch / pytorch/vision

DeformConv2d offset and mask backprop

Open
#5,989 5 comments 0 reactions 0 assignees View on GitHub

Nobody has claimed this yet.

enhancement module: ops
Dominant language
Python
Stars
17.9k
Forks
7.3k
Avg merge
1d 15h
Merged PRs (30d)
13

Description

🚀 The feature

I notice that the current vision of DeformConv2d module doesn’t treat offset and mask as parameters, so it seems that the standard backward routine cannot update the offset. Is there any possibility that you could add this feature in the future?

Motivation, pitch

I’m trying to build DNNs with above module, so it is not that convenient if I need to rewrite the backward process by myself

Alternatives

No response

Additional context

No response

Contributor guide

Open the contributing guide

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 locating the DeformConv2d module and tracing its current backward path. Check how offset and mask are represented and whether existing tests cover their gradients. Done means the standard backward routine can update both offset and mask, with tests demonstrating that behavior.

Written by the indexing model from the issue text.

Assessment

Tech stack
python
Domain
computer-vision, machine-learning
Issue type
Feature
Difficulty
5/5
Estimated time
Over a week
Activity status
Stale
Clarity
Needs clarification
Newbie friendliness
35/100

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.