ModelListedExternal

Scalesurfer v7

This repository contains the ScaleSurfer 3D TransUNet volume segmentation checkpoint fine-tuned for FreeSurfer v7 labels.

Sourcehuggingface.co/rphammonds/scalesurfer-v7/tree/c9f7e092567fba60363a6d188ff4e9daec148f94

KindOtherVersionRevision c9f7e09Bgrade

Model source

Kind: Other
File size: 10.0 MB
Version: vRevision c9f7e09
Updated: Nov 1, 2026
Downloads: 2
Source: Hugging Face

Source description

ScaleSurfer FreeSurfer v7 Volume Model

This repository contains the ScaleSurfer 3D TransUNet volume segmentation checkpoint fine-tuned for FreeSurfer v7 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=1077, val=134, test=134	0.043248842053337774	0.047175739092557734

Loading

ScaleSurfer resolves this model automatically when ScaleSurfer(..., fs_version=7) is used.

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

Sources

1 source

Hugging FacePrimaryVersion c9f7e092567fba60363a6d188ff4e9daec148f94

huggingface.co/rphammonds/scalesurfer-v7/tree/c9f7e092567fba60363a6d188ff4e9daec148f94

Verified Nov 1

Download files

Repository files

File inventory only; completeness is unverified.

Model artifacts

1 artifact

transunet3d.safetensors

safetensors · FP32 (unverified) · 10.0 MB · SHA-256 150caa2ecc98…2fc9 · Hugging Face

Download file

Source excerpts

3 excerpts

ReadmeAug 18huggingface.co/rphammonds/scalesurfer-v7

--- library_name: pytorch pipeline_tag: image-segmentation tags: - medical-imaging - freesurfer - segmentation - safetensors - scalesurfer --- # ScaleSurfer FreeSurfer v7 Volume Model This repository contains the ScaleSurfer 3D TransUNet volume segmentation checkpoint fine-tuned for FreeSurfer v7 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=1077, val=134, test=134 | 0.043248842053337774 | 0.047175739092557734 | ## Loading ScaleSurfer resolves this model automatically when `ScaleSurfer(..., fs_version=7)` is used. This model is intended for research workflows and is not a clinical diagnostic device.

NoteNov 1huggingface.co/rphammonds/scalesurfer-v7

Source context: 2 downloads · 0 likes · Pipeline image-segmentation · Library pytorch · Repo rphammonds/scalesurfer-v7

NoteAug 18huggingface.co/rphammonds/scalesurfer-v7

Source context: 10 downloads · 0 likes · Pipeline image-segmentation · Library pytorch · Repo rphammonds/scalesurfer-v7