marksgraham/ddpm-ood

Official PyTorch code for "Out-of-distribution detection with denoising diffusion models"

37
/ 100
Emerging

This tool helps researchers and practitioners in fields like medical imaging and computer vision to automatically detect unusual or 'out-of-distribution' data within their image datasets. You input a collection of images that represent your 'normal' data, and the system learns its characteristics. It then processes new images and flags those that don't fit the established norm, helping you identify anomalies without manual inspection. This is useful for anyone working with image datasets where identifying unexpected inputs is critical.

No commits in the last 6 months.

Use this if you need to reliably identify images that deviate significantly from a known set of 'normal' or expected images, especially in computer vision or medical imaging applications.

Not ideal if your primary goal is image generation, image editing, or if you need to classify images into many specific categories rather than simply spotting anomalies.

medical-imaging image-analysis anomaly-detection computer-vision data-quality
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 8 / 25
Maturity 16 / 25
Community 13 / 25

How are scores calculated?

Stars

52

Forks

7

Language

Python

License

Last pushed

Jun 09, 2024

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/diffusion/marksgraham/ddpm-ood"

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