Skip to content

Add offline scene tag inference - #125

Open
hualuoz wants to merge 1 commit into
mergeos-bounties:masterfrom
hualuoz:bounty/scene-tagger
Open

Add offline scene tag inference#125
hualuoz wants to merge 1 commit into
mergeos-bounties:masterfrom
hualuoz:bounty/scene-tagger

Conversation

@hualuoz

@hualuoz hualuoz commented Jul 23, 2026

Copy link
Copy Markdown

Summary

  • add a deterministic offline scene tagger for background descriptions and image filenames
  • optionally infer and merge scene tags in poseguide guide recommend
  • cover description, image-fixture, CLI integration, and no-match behavior
  • document the offline behavior and a future CLIP upgrade seam

Why

PoseGuide previously required a scene JSON file or manually supplied tags. It had no path from a background image name or natural-language description to the tags consumed by the ranker.

User impact

Users can now request recommendations with --description or --background. The implementation makes no network requests, reads no image pixels, and downloads no model; explicit --tags can still be combined with inferred tags.

Validation

  • pytest -q — 46 passed, 5 skipped
  • pytest -q --cov=src --cov-fail-under=30 — 70.73% coverage
  • ruff check src tests
  • ruff format --check src tests
  • python -m compileall -q src tests

Fixes #6

@hualuoz
hualuoz marked this pull request as ready for review July 23, 2026 15:55
@hualuoz

hualuoz commented Jul 26, 2026

Copy link
Copy Markdown
Author

Ready for review. I reran the full repository CI locally on 2026-07-26: Ruff check and format check passed, coverage was 70.73% (threshold 30%), 46 tests passed with 5 skipped, and compileall passed. GitHub Actions is currently marked action_required because this is a fork PR. Could a maintainer approve the CI run and review the PR when available?

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

[50 MRG] Scene tagger: simple CV/heuristics or CLIP-stub for background tags

1 participant