ModelAufgelistetExtern

Scalesurfer v6

This repository contains the ScaleSurfer 3D TransUNet volume segmentation checkpoint fine-tuned for FreeSurfer v6 labels.

Quellehuggingface.co/rphammonds/scalesurfer-v6/tree/94a4efe9dc46ca5b0daf3eaeb6189dcbde23237f

ArtOtherVersionRevision 94a4efeCBewertung

Modellquelle

Art: Other
Dateigröße: 10,0 MB
Version: vRevision 94a4efe
Aktualisiert: 1. Nov. 2026
Downloads: 2
Quelle: Hugging Face

Quellenbeschreibung

ScaleSurfer FreeSurfer v6 Volume Model

This repository contains the ScaleSurfer 3D TransUNet volume segmentation checkpoint fine-tuned for FreeSurfer v6 labels.

Files

transunet3d.safetensors: model weights in safetensors format.
config.json: architecture and checkpoint configuration.
metadata.json: conversion checksums and sanitized training/evaluation metadata.

Metrics

Split counts	Best validation CE	Final test CE
train=1592, val=202, test=202	0.021963781686407505	0.020560515551173157

Loading

ScaleSurfer resolves this model automatically when ScaleSurfer(..., fs_version=6) is used.

This model is intended for research workflows and is not a clinical diagnostic device.

Quellen

1 Quelle

Hugging FacePrimärVersion 94a4efe9dc46ca5b0daf3eaeb6189dcbde23237f

huggingface.co/rphammonds/scalesurfer-v6/tree/94a4efe9dc46ca5b0daf3eaeb6189dcbde23237f

Verifiziert 1. Nov.

Download files

Repository files

File inventory only; completeness is unverified.

Modellartefakte

1 Artefakt

transunet3d.safetensors

safetensors · FP32 (unverified) · 10,0 MB · SHA-256 e3fee0400256…fb8a · Hugging Face

Download file

Quellenauszüge

2 Auszüge

Readme18. Aug.huggingface.co/rphammonds/scalesurfer-v6

--- library_name: pytorch pipeline_tag: image-segmentation tags: - medical-imaging - freesurfer - segmentation - safetensors - scalesurfer --- # ScaleSurfer FreeSurfer v6 Volume Model This repository contains the ScaleSurfer 3D TransUNet volume segmentation checkpoint fine-tuned for FreeSurfer v6 labels. ## Files - `transunet3d.safetensors`: model weights in safetensors format. - `config.json`: architecture and checkpoint configuration. - `metadata.json`: conversion checksums and sanitized training/evaluation metadata. ## Metrics | Split counts | Best validation CE | Final test CE | | --- | ---: | ---: | | train=1592, val=202, test=202 | 0.021963781686407505 | 0.020560515551173157 | ## Loading ScaleSurfer resolves this model automatically when `ScaleSurfer(..., fs_version=6)` is used. This model is intended for research workflows and is not a clinical diagnostic device.

Note18. Aug.huggingface.co/rphammonds/scalesurfer-v6

Source context: 2 downloads · 0 likes · Pipeline image-segmentation · Library pytorch · Repo rphammonds/scalesurfer-v6