Track: research · Level: core · Effort: ~5h (2h GPU) · Depends on: #335 (T20)
Why this matters
Most real users fine-tune a pretrained backbone rather than train from scratch. Showing BNNR still helps in that regime makes the method relevant to how people actually work, not just to a research setup.
Steps
- Get maintainer sign-off.
- Run the Imagewoof matrix with the pretrained option (check run_grand_benchmark.py --help for the regime flag).
- Summarize with summarize_grand and write findings.md.
Done when
Pretrained Imagewoof JSON; table; findings.md.
How to take this: comment "taking this" and wait to be assigned. Branch t34-short-desc from upstream/main, and put Closes #<this issue number> in your PR. Full workflow: the Cohort Handbook (pinned in Discord).
Track: research · Level: core · Effort: ~5h (2h GPU) · Depends on: #335 (T20)
Why this matters
Most real users fine-tune a pretrained backbone rather than train from scratch. Showing BNNR still helps in that regime makes the method relevant to how people actually work, not just to a research setup.
Steps
Done when
Pretrained Imagewoof JSON; table; findings.md.
How to take this: comment "taking this" and wait to be assigned. Branch
t34-short-descfromupstream/main, and putCloses #<this issue number>in your PR. Full workflow: the Cohort Handbook (pinned in Discord).