csinva/gan-vae-pretrained-pytorch

Pretrained GANs + VAEs + classifiers for MNIST/CIFAR in pytorch.

40
/ 100
Emerging

This project provides pre-trained models for generating new images and classifying existing ones, specifically for common datasets like MNIST and CIFAR. It takes numerical image data as input and can either produce novel, synthetic images resembling the original dataset or classify input images into categories. This is useful for researchers and machine learning practitioners who need to quickly experiment with generative models or image classifiers without extensive training from scratch.

207 stars. No commits in the last 6 months.

Use this if you are a machine learning researcher or practitioner working with image generation or classification and need pre-trained models for common datasets like MNIST or CIFAR to jumpstart your experiments or comparisons.

Not ideal if you need to generate highly complex, realistic images beyond simple datasets or require models trained on custom, domain-specific image data.

generative-modeling image-synthesis image-classification machine-learning-research computer-vision
No License Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 10 / 25
Maturity 8 / 25
Community 22 / 25

How are scores calculated?

Stars

207

Forks

49

Language

Jupyter Notebook

License

Last pushed

Feb 02, 2025

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/csinva/gan-vae-pretrained-pytorch"

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