FabianFalck/unet-design

Official PyTorch implementation of "A Unified Framework for U-Net Design and Analysis" (NeurIPS 2023).

30
/ 100
Emerging

This project offers a unified framework for researchers and practitioners working with U-Net models to design, analyze, and compare different architectures. It takes various image datasets (like medical scans or general images) or scientific simulation data as input and produces insights into U-Net performance for tasks such as image segmentation, generative modeling, and physics simulations. Scientists, machine learning engineers, and medical imaging specialists can use this to optimize their U-Net designs.

No commits in the last 6 months.

Use this if you are a researcher or practitioner developing U-Net models for tasks like image segmentation, generative modeling, or solving partial differential equations, and you need a standardized way to evaluate and compare different U-Net configurations.

Not ideal if you are looking for a plug-and-play solution for general deep learning tasks unrelated to U-Net architectures or if you lack experience with experimental machine learning setups.

medical-imaging image-segmentation generative-modeling scientific-computing physics-simulation
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 6 / 25
Maturity 16 / 25
Community 8 / 25

How are scores calculated?

Stars

20

Forks

2

Language

Python

License

MIT

Last pushed

Sep 11, 2023

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/diffusion/FabianFalck/unet-design"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.