nv-generate-vae-finetune

Community

Fine-tune NV-Generate VAE for CT/MRI data

Authorsayalinvidia
Version1.0.0
Installs0

System Documentation

What problem does it solve?

Train and tailor the NV-Generate-CTMR MAISI VAE for CT/MRI datasets by wrapping upstream configs, validating datasets, and staging runs, enabling engineering teams to run finetuning without duplicating boilerplate.

Core Features & Use Cases

  • Stages upstream VAE finetuning workflows and datalist contracts, providing ready-to-run configuration scaffolding.
  • Validates MONAI-style datalists (training and validation), resolves absolute image paths, and prepares staged artifacts for training.
  • Use Case: researchers can quickly prototype finetuning on CT and MRI volumes and compare results across different settings using a single, repeatable wrapper.

Quick Start

Invoke this skill with a MONAI-style datalist and a data-base directory to stage the VAE finetuning workflow and run the training pipeline.

Dependency Matrix

Required Modules

nibabelnumpytorchmonaiscipyscikit-imageeinopshuggingface_hubtqdmfiretensorboardlpipsPyYAML

Components

scripts

💻 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-generate-vae-finetune
Download link: https://github.com/sayalinvidia/sayali-skills-test/archive/main.zip#nv-generate-vae-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.