Downloads · 30 days
0
ae-vae-fashionmnist
krishika28/ae-vae-fashionmnist
ae-vae-fashionmnist is a machine learning model from krishika28. Use it for the machine learning task on the model card, and read the license before you ship it in a product.
This project implements: - Autoencoder (AE) - Variational Autoencoder (VAE)
Access
Public
Updated Apr 14, 2026
Repo size
3.3 MB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.pth3.3 MB · 100%
At a glance
- Access
- Public
- Created
- Apr 14, 2026
- Updated
- Apr 14, 2026
- SHA
- 37702a81
Model card
From the Hugging Face model README
Autoencoder & Variational Autoencoder (VAE) on Fashion-MNIST
This project implements:
- Autoencoder (AE)
- Variational Autoencoder (VAE)
to learn latent representations and generate images from the Fashion-MNIST dataset.
Dataset
- Fashion-MNIST
- Grayscale images of clothing items (28x28)
Models
Autoencoder
- Deterministic model
- Better reconstruction quality
Variational Autoencoder (VAE)
- Probabilistic model
- Smooth latent space
- Can generate new images
Results
- AE: Sharper reconstruction
- VAE: Better generation & smooth transitions
Latent Dimensions Tested
- 2
- 8
- 16
- 32
Files
autoencoder.pth→ trained Autoencoder modelvae.pth→ trained VAE model
Usage
Load model in PyTorch:
model.load_state_dict(torch.load("model.pth"))
- Created
- Apr 14, 2026
- Updated
- Apr 14, 2026