pytorch / pytorch/vision

Motivation around setting beta to 1/9

Open
#8,075 1 comment 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

Hi everyone,
I was wondering what was the motivation around setting the beta parameter for the smooth L1 loss for faster RCNN to 1/9.

The line in question is here: https://github.com/pytorch/vision/blame/8a0b491e51197edd9ca9f9ad7f6d9147ac8a209d/torchvision/models/detection/roi_heads.py#L44

Is this based on some work / intution I could be able to track (but wasn't) or was it a "good guess"?

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 the beta definition at torchvision/models/detection/roi_heads.py#L44 and inspect the linked Git blame history. Trace any referenced Faster R-CNN or smooth L1 loss sources mentioned in that history. Done means identifying and recording the rationale or source for the 1/9 value, if one exists.

Written by the indexing model from the issue text.

Assessment

Tech stack
python
Domain
computer-vision, machine-learning
Issue type
Documentation
Difficulty
3/5
Estimated time
1-2 days
Activity status
Stale
Clarity
Needs clarification
Newbie friendliness
25/100

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.