pytorch / pytorch/vision

Question about kernel size of class LastLevelMaxPool(ExtraFPNBlock) in feature_pyramid_network.py

Open
#3,632 2 comments 0 reactions 0 assignees View on GitHub

Nobody has claimed this yet.

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

Description

❓ Questions and Help

Why the pool kernel = 1? I think it should be 2 (my understanding is that kernel = 1 won't do max pooling correctly.
line 175: x.append(F.max_pool2d(x[-1], 1, 2, 0))

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 with feature_pyramid_network.py at line 175 and read the surrounding LastLevelMaxPool implementation. Verify the positional arguments passed to F.max_pool2d and the expected feature-pyramid output shape; done means providing an evidence-based explanation or correcting the call if the kernel size is wrong.

Written by the indexing model from the issue text.

Assessment

Tech stack
python
Domain
computer-vision
Issue type
Bug
Difficulty
3/5
Estimated time
1-2 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.