Downloads · 30 days
0
GAN_MNIST
hussamalafandi/GAN_MNIST
GAN_MNIST is a machine learning model from hussamalafandi. Use it for the machine learning task on the model card, and read the license before you ship it in a product. It is set up for pytorch. The card lists the license as mit.
This repository contains a Generative Adversarial Network (GAN) trained on the MNIST dataset to generate realistic handwritten digits. The model was trained as part of the Generative AI course.
Access
Public
Updated Mar 27, 2025
Repo size
9 MB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.pth4.5 MB · 100%
At a glance
- Library
- pytorch
- License
- mit
- Access
- Public
- Created
- Mar 27, 2025
- Updated
- Mar 27, 2025
- SHA
- 295eabf5
Datasets
Model card
From the Hugging Face model README
GAN for MNIST Digit Generation
This repository contains a Generative Adversarial Network (GAN) trained on the MNIST dataset to generate realistic handwritten digits. The model was trained as part of the Generative AI course.
Model Details
- Model Type: GAN
- Dataset: MNIST (handwritten digits)
- Generator Input: Latent vector of size 100
- Output: 28x28 grayscale images
- Framework: PyTorch
Training Details
- Optimizer: Adam
- Learning Rate: 0.0002
- Beta1: 0.5
- Epochs: 50
- Batch Size: 64
- Weight Decay: 0.0001
- Logging: Weights & Biases
Usage
Loading the Model
To load the trained model, use the following code snippet:
from gan import Generator
import torch
latent_dim = 100
generator = Generator(latent_dim)
generator.load_state_dict(torch.load("./gan_mnist.pth"))
generator.eval()
# Generate samples
z = torch.randn(16, latent_dim)
samples = generator(z)
Example Results
References
License
This project is licensed under the MIT License.
- Library
- pytorch
- License
- mit
- Created
- Mar 27, 2025
- Updated
- Mar 27, 2025