riiid/PPAP

Official pytorch implementation of "Towards Practical Plug-and-Play Diffusion Models" in CVPR2023

38
/ 100
Emerging

This project helps machine learning engineers and researchers improve how well their image classification models perform, especially when using diffusion models. It takes an existing image dataset and a pre-trained diffusion model as input. It then outputs a more accurate and robust image classifier, enhancing performance compared to standard fine-tuning or single-expert approaches.

No commits in the last 6 months.

Use this if you are developing or training image classification models and want to leverage advanced techniques to achieve higher accuracy and more stable performance, particularly with diffusion-generated data.

Not ideal if you are looking for an out-of-the-box solution for image generation or if you don't have access to substantial computational resources for model training.

image-classification deep-learning-research computer-vision-training model-optimization synthetic-data-training
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 6 / 25
Maturity 16 / 25
Community 16 / 25

How are scores calculated?

Stars

22

Forks

6

Language

Jupyter Notebook

License

Apache-2.0

Last pushed

Jul 22, 2023

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/diffusion/riiid/PPAP"

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