yandex-research/tab-ddpm
[ICML 2023] The official implementation of the paper "TabDDPM: Modelling Tabular Data with Diffusion Models"
This project helps data scientists and machine learning engineers create realistic synthetic datasets from existing tabular data. You input your original structured data (like a spreadsheet or database table), and it outputs a new, artificially generated dataset that mirrors the statistical properties of your original data. This is useful for tasks like sharing data while protecting privacy, augmenting small datasets, or testing models without using sensitive real-world information.
533 stars. No commits in the last 6 months.
Use this if you need to generate high-quality synthetic versions of your structured, numerical, and categorical datasets while preserving their statistical characteristics and protecting privacy.
Not ideal if you are working with unstructured data like images, text, or audio, or if you need to generate entirely new data that doesn't resemble an existing dataset.
Stars
533
Forks
132
Language
Python
License
MIT
Category
Last pushed
Jul 13, 2024
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/diffusion/yandex-research/tab-ddpm"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Related models
huggingface/diffusers
🤗 Diffusers: State-of-the-art diffusion models for image, video, and audio generation in PyTorch.
bghira/SimpleTuner
A general fine-tuning kit geared toward image/video/audio diffusion models.
mcmonkeyprojects/SwarmUI
SwarmUI (formerly StableSwarmUI), A Modular Stable Diffusion Web-User-Interface, with an...
nateraw/stable-diffusion-videos
Create 🔥 videos with Stable Diffusion by exploring the latent space and morphing between text prompts
TheDesignFounder/DreamLayer
Benchmark diffusion models faster. Automate evals, seeds, and metrics for reproducible results.