Cat Faces
A demonstration of GAN for generating cat faces
I created a Generative Adversarial Network (GAN) and trained it on a dataset of cat faces. This task provided hands-on experience in implementing and training GANs using PyTorch. I also implemented WGAN loss function and spectral normalization. What’s more I trained the model and visualized the output.
Key Features:
- Implemented a vanilla GAN and a Least Squares GAN (LSGAN).
- Trained the GAN on a dataset of cat faces.
- Visualized the output of the GAN every 1000 iterations and for the final model.
- Reported the discriminator and generator loss values every 1000 iterations.
Tools and Technologies:
- Python
- PyTorch
Source Code
The complete source code for this project is available on GitHub.