GAN-Based Image Generation with CIFAR-10 Dataset

[Kaibalya27]

Related Issues or bug

• This pull request adds the GAN-based image generation model using the CIFAR-10 dataset. It includes the architecture for the generator, discriminator, and the GAN model itself. The GAN model is trained on CIFAR-10 to generate images that resemble real images from the dataset.

Fixes: #505

Proposed Changes

• Added a GAN model that uses the CIFAR-10 dataset to generate images.
• Integrated functionality for saving intermediate model checkpoints every 10 epochs.
• Implemented image saving functionality for generated images during training.

Additional Info

• The model is trained with a batch size of 128 and a latent dimension of 100.
• Models (generator, discriminator, and combined GAN) are saved as .h5 files every 10 epochs for future use.
• Generated images are saved in the JPG format.

Results

[github-actions]

👋 Thank you for opening this pull request! We appreciate your contribution to improving this project. Your PR is under review, and we'll get back to you shortly.
Don't forget to mention the issue you solved!.

To help move the process along, please tag @UppuluriKalyani, @Neilblaze, and @SaiNivedh26 for a faster review!

[github-actions]

🎉🎉 Thank you for your contribution! Your PR #516 has been merged! 🎉🎉