Downloads · 30 days
0
aungmthein/oct-cell-layer-fold4-swin-umamba
oct-cell-layer-fold4-swin-umamba is a image segmentation model from aungmthein. Use it for the image segmentation task on the model card, and read the license before you ship it in a product. It is set up for pytorch. The card lists the license as mit.
Production checkpoint for the OCTFabiola cell-layer segmentation task. 3-class semantic segmentation (above / cell layer / below) on 2D OCT images of engineered cartilage constructs.
Downloads · 30 days
0
Access
Public
Updated May 22, 2026
Repo size
240 MB
Likes
0
Public
Click a slice to open those files.
.pth240 MB · 100%
From the Hugging Face model README
Production checkpoint for the OCT_Fabiola cell-layer segmentation task. 3-class semantic segmentation (above / cell layer / below) on 2D OCT images of engineered cartilage constructs.
phase4-1f3f21ce| slice | n | Dice | MAE (px) | ECE | Brier |
|---|---|---|---|---|---|
| val (fold 4) | 14 | 0.84 | 32 | 0.05 | 0.13 |
| OOD aggregate | 44 | 0.572 | 104.47 | 0.174 | 0.432 |
| OOD restricted (thin-bounded subset) | 29 | ~0.81 | ~48 | -- | -- |
| OOD no-bottom subset | 15 | ~0.10 | n/a | -- | -- |
Important caveat on the OOD numbers. The OOD slice is bimodal-by-regime: 15 of 44 OOD images are in the no-bottom regime (cell layer extends below the visible frame), which is completely absent from training (0/68 training images). The model has zero training signal for that regime, so the aggregate OOD Dice 0.572 is dominated by an extrapolation failure, not a generalization failure on the in-distribution regime. The honest metric is the restricted-OOD number on the thin-bounded subset.
from huggingface_hub import hf_hub_download
ckpt_path = hf_hub_download(
repo_id="aungmthein/oct-cell-layer-fold4-swin-umamba",
filename="phase4-1f3f21ce_softmax_B__swin_umamba_fold4.pth",
)
# Loader integration: see the demo Space at
# https://huggingface.co/spaces/aungmthein/oct-cartilage-cell-layer
MIT (matches the upstream Swin-UMamba reference).