FutureXiang/soda
Unofficial implementation of "SODA: Bottleneck Diffusion Models for Representation Learning"
This is an experimental implementation of a specialized machine learning model designed to improve how computers learn to categorize images. It takes raw image datasets, like those used for object recognition, and trains a model that can then be used to classify these images more effectively. This tool is for machine learning researchers and practitioners who are exploring advanced representation learning techniques for image classification.
No commits in the last 6 months.
Use this if you are a machine learning researcher interested in experimenting with bottleneck diffusion models for image classification performance, especially on small to medium-scale datasets like CIFAR-10/100 or Tiny-ImageNet.
Not ideal if you need state-of-the-art classification accuracy out-of-the-box, require robust image generation capabilities, or plan to work with very large datasets like ImageNet-1k.
Stars
97
Forks
4
Language
Jupyter Notebook
License
—
Category
Last pushed
Mar 21, 2024
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/diffusion/FutureXiang/soda"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
quantgirluk/aleatory
📦 Python library for Stochastic Processes Simulation and Visualisation
blei-lab/treeffuser
Treeffuser is an easy-to-use package for probabilistic prediction and probabilistic regression...
TuftsBCB/RegDiffusion
Diffusion model for gene regulatory network inference.
yuanchenyang/smalldiffusion
Simple and readable code for training and sampling from diffusion models
chairc/Integrated-Design-Diffusion-Model
IDDM (Industrial, landscape, animate, latent diffusion), support LDM, DDPM, DDIM, PLMS, webui...