nv-segment-ct-finetune

Community

Auto-configured finetune workflow for NV-Segment-CT.

Authorsayalinvidia
Version1.0.0
Installs0

System Documentation

What problem does it solve?

NV Segment-CT Finetune provides an auto-configured wrapper around the upstream MONAI-based finetuning workflow for NV-Segment-CT, enabling researchers to reliably run smoke tests and MSD Task06 sanity runs without manually wiring the bundle.

Core Features & Use Cases

  • Auto-configured wrapper around NV-Segment-CT continual finetune entry, coordinating dataset inputs, patch sizes, and GPU/runtime settings.
  • Supports smoke (spleen_micro) and sanity (Task06_Lung) presets, with explicit label mappings (e.g., [[1, 23]]) and automatic class-prompt segmentation.
  • Exposes outputs finetuned_ckpt and result_json and relies on the upstream bundle for the heavy lifting.

Quick Start

Run the finetune script against a dataset to produce a finetuned model and an evaluation artifact.

Dependency Matrix

Required Modules

nibabelnumpyscipytyper

Components

scriptsreferences

💻 Claude Code Installation

Recommended: Let Claude install automatically. Simply copy and paste the text below to Claude Code.

Please help me install this Skill:
Name: nv-segment-ct-finetune
Download link: https://github.com/sayalinvidia/sayali-skills-test/archive/main.zip#nv-segment-ct-finetune

Please download this .zip file, extract it, and install it in the .claude/skills/ directory.
View Source Repository

Agent Skills Search Helper

Install a tiny helper to your Agent, search and equip skill from 510,000+ vetted skills library on demand.