ocean-gan

GAN Image Generator

This model was trained on a custom image dataset using a GAN architecture.

Training Information

• Epochs: 9000/10000
• Current Date: 2025-05-10 23:25:41
• Image Size: 64x64
• Latent Dimension: 100
• Batch Size: 64

Latest Training Metrics

• Generator Loss: 10.298025131225586
• Discriminator Loss: 0.0010482072830200195
• Discriminator Accuracy: 1.0

Sample Images

Usage

import torch
from torch import nn

# Define generator architecture
class Generator(nn.Module):
    # ... (architecture code)

# Load the model
generator = Generator(latent_dim=100, channels=3)
generator.load_state_dict(torch.load('model/generator_epoch_9000.pt'))
generator.eval()

# Generate images
z = torch.randn(1, 100)
with torch.no_grad():
    fake_image = generator(z)
    # Convert to range [0, 1] for display
    fake_image = (fake_image + 1) / 2.0

Training Progress

Training is currently 90.0% complete.