Megvii-BaseDetection / Megvii-BaseDetection/DisAlign

the code question in semantic_seg

Open
#20 8 comments 0 reactions 0 assignees View on GitHub

Nobody has claimed this yet.

Dominant language
Python
Stars
118
Forks
10
PR merge metrics
No merged PRs in 30d

Description

Hi, I have a questation about the logit_scale and logit_bias in semantic_seg. The shape of the above parameter is (1, num_classes, 1, 1), why not is (1, num_classes, 512, 512) which is matched the input image size for semantic segmenation.

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

Locate the semantic_seg implementation and the definitions or uses of logit_scale and logit_bias. Read how these parameters are broadcast during semantic segmentation and review the related model path; done means documenting why their shape is intentional and how it relates to the input image dimensions.

Written by the indexing model from the issue text.

Assessment

Tech stack
python
Domain
computer-vision, machine-learning
Issue type
Documentation
Difficulty
4/5
Estimated time
3-5 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.