Saltar al contenido
ModelPublicadoExterno
Descargar

VAE CelebA

This repository contains a trained Variational Autoencoder (VAE) model on the CelebA dataset. The model is designed to encode and decode facial images, enabling tasks such as image reconstruction, latent space...

Fuentehuggingface.co/hussamalafandi/VAE-CelebA/tree/9e5ed327c2d4dff8a702cff3a1b8e829969e42b8
TipoVAEVersiónvae_celeba_latent_200_epochs_10_batch_64_subset_80000Ccalidad

Fuente del modelo

Tipo
VAE
Tamaño del archivo
14,7 MB
Versión
vvae_celeba_latent_200_epochs_10_batch_64_subset_80000
Actualizado
20 oct 2026
Fuente
Hugging Face

Descripción de la fuente

Variational Autoencoder (VAE) - CelebA Dataset

This repository contains a trained Variational Autoencoder (VAE) model on the CelebA dataset. The model is designed to encode and decode facial images, enabling tasks such as image reconstruction, latent space interpolation, and attribute manipulation.

Model Details

  • Architecture: Variational Autoencoder (VAE)
  • Dataset: CelebA
  • Latent Dimension: 200
  • Training Subset Size: 80,000 images
  • Batch Size: 64
  • Learning Rate: 1e-3
  • Epochs: 10

Weights and Biases Run

The training process was tracked using Weights and Biases. You can view the full training logs and metrics here.

Usage

Loading the Model

To load the trained model, use the following code snippet:

import torch
from vae_model import VAE  # Ensure the VAE class is defined in vae_model.py

# Define the latent dimension
latent_dim = 200

# Initialize the model
model = VAE(latent_dim=latent_dim)

# Load the trained weights
model_path = "./vae_celeba_latent_200_epochs_10_batch_64_subset_80000.pth"
model.load_state_dict(torch.load(model_path))
model.eval()

Applications

  1. Image Reconstruction: Reconstruct input images using the encoder and decoder.
  2. Latent Space Interpolation: Generate smooth transitions between two images by interpolating in the latent space.
  3. Attribute Manipulation: Modify specific attributes (e.g., smiling, hair color) by moving along attribute directions in the latent space.

Example Results

Reconstruction

Below is a reconstruction example where the first row represents the original images, and the second row represents the reconstructed images:

Reconstruction

Latent Space Interpolation

Below is an example of interpolating between two images in the latent space:

Latent Space Interpolation

Attribute Manipulation

Manipulating the "Smiling" attribute in the latent space:

Attribute Manipulation

License

This project is licensed under the MIT License. See the LICENSE file for details.

Fuentes

1 fuente
Hugging FacePrincipalVersión 9e5ed327c2d4dff8a702cff3a1b8e829969e42b8
huggingface.co/hussamalafandi/VAE-CelebA/tree/9e5ed327c2d4dff8a702cff3a1b8e829969e42b8

Verificado 20 oct

Artefactos del modelo

1 artefacto

vae_celeba_latent_200_epochs_10_batch_64_subset_80000.pth

pth · 14,7 MB · SHA-256 3229ca548c16…593c · Hugging Face

Download file

Extractos de fuentes

2 extractos
Readme3 agohuggingface.co/hussamalafandi/VAE-CelebA

--- library_name: pytorch tags: - vae - celeba - generative-model - latent-space - image-reconstruction - attribute-manipulation datasets: - celeba metrics: - reconstruction-loss - kl-divergence license: mit --- # Variational Autoencoder (VAE) - CelebA Dataset This repository contains a trained Variational Autoencoder (VAE) model on the CelebA dataset. The model is designed to encode and decode facial images, enabling tasks such as image reconstruction, latent space interpolation, and attribute manipulation. ## Model Details - **Architecture**: Variational Autoencoder (VAE) - **Dataset**: CelebA - **Latent Dimension**: 200 - **Training Subset Size**: 80,000 images - **Batch Size**: 64 - **Learning Rate**: 1e-3 - **Epochs**: 10 ### Weights and Biases Run The training process was tracked using [Weights and Biases](https://wandb.ai). You can view the full training logs and metrics [here](https://wandb.ai/hussam-alafandi/vae-celeba/runs/cv01woz1?nw=nwuserhussamalafandi). ## Usage ### Loading the Model To load the trained model, use the following code snippet: ```python import torch from vae_model import VAE # Ensure the VAE class is defined in vae_model.py # Define the latent dimension latent_dim = 200 # Initialize the model model = VAE(latent_dim=latent_dim) # Load the trained weights model_path = "./vae_celeba_latent_200_epochs_10_batch_64_subset_80000.pth" model.load_state_dict(torch.load(model_path)) model.eval() ``` ### Applications 1. **Image Reconstruction**: Reconstruct input images using the encoder and decoder. 2. **Latent Space Interpolation**: Generate smooth transitions between two images by interpolating in the latent space. 3. **Attribute Manipulation**: Modify specific attributes (e.g., smiling, hair color) by moving along attribute directions in the latent space. ## Example Results ### Reconstruction Below is a reconstruction example where the first row represents the original images, and the second row represents the reconstructed images: ![Reconstruction](./reconstruction_images_13_9c2c9b76dee391efede2.png) ### Latent Space Interpolation Below is an example of interpolating between two images in the latent space: ![Latent Space Interpolation](./latent_space_interpolation.png) ### Attribute Manipulation Manipulating the "Smiling" attribute in the latent space: ![Attribute Manipulation](./attribute_manipulation.p...

Note3 agohuggingface.co/hussamalafandi/VAE-CelebA

Source context: 0 downloads · 0 likes · Library pytorch · Repo hussamalafandi/VAE-CelebA