Downloads · 30 days
0
dat-challenge-winner
paulonium/dat-challenge-winner
dat-challenge-winner is a machine learning model from paulonium. Use it for the machine learning task on the model card, and read the license before you ship it in a product. The card lists the license as mit.
prizesubmission.tar.gz (2.9 GB) — the complete prize package: code (github.com/paul-bd/DATchallenge @ main), pinned requirements, and the shipped weights (50 fusion10 TorchScript members + striatal ellipse localiser +…
Access
Public
Updated Sep 25, 2026
Repo size
3.1 GB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.gz3.1 GB · 100%
At a glance
- License
- mit
- Access
- Public
- Created
- Sep 24, 2026
- Updated
- Sep 25, 2026
- SHA
- 4c12a493
Model card
From the Hugging Face model README
DaT SPECT abnormality classification — DrivenData comp 311, 3rd place
prize_submission.tar.gz (2.9 GB) — the complete prize package: code
(github.com/paul-bd/DAT_challenge @ main), pinned requirements, and the
shipped weights (50 fusion10 TorchScript members + striatal ellipse
localiser + calibration).
sha256: 9752e5b3273841b343b73131cf55a038fcffa501899c1b915981802a05e1da65
Unpack, pip install -r requirements.txt, then
DATA_DIR=/path/with/niftis OUTPUT_PATH=out.csv python inference/main.py.
- License
- mit
- Created
- Sep 24, 2026
- Updated
- Sep 25, 2026