hoffmannhof/swin-t-matching

Matching (Swin T)

Overview

This repository is a compact, custom PyTorch implementation of Swin T for Matching. The huge configuration is intended for code review, smoke tests, and small controlled experiments rather than as a production-ready pretrained release.

Limitations

The initialization checkpoint has not been trained or audited for robustness, fairness, or domain transfer. The implementation should be treated as an experimental starting point. Results from a future trained checkpoint must be documented separately from the defaults shipped here.

Default Experiment Recipe

The included configuration uses adamw with a onecycle schedule. These are starting values in the script, not evidence of a completed run. For a meaningful evaluation, train all baselines with the same data exposure, tuning budget, and random seeds.

Roadmap

Next steps, in no particular order: a cleaner entry point, input-shape docs, and a small evaluation script if time permits.

Repository Status

1. Single-file implementation; the __main__ block runs a smoke test.
2. config.json and training_args.json hold the generated settings.
3. model.safetensors is freshly initialized — plumbing, not results.
4. No benchmark numbers are reported on purpose.

Evaluation Guidance

A first evaluation could use a paired validation set. Report the metric across at least three seeds and include a matched-capacity baseline; keep logs and library versions with any published number.

Environment

Item	Value
Python	>= 3.9
torch	2.x
safetensors	any recent

Files

1. run.py — primary artifact
2. README.md — this documentation
3. config.json — architecture configuration
4. training_args.json — default experiment settings
5. model.safetensors — initialization checkpoint
6. NOTES.md — informal to-do notes

License

Distributed under the bsd-2-clause license. External datasets keep their own terms — check them separately.