Gray2Color-CNN

This project builds a Convolutional Neural Network (CNN) to automatically colorize grayscale images using the CIFAR-10 dataset.

Features

• Converts grayscale 32x32 images into full-color RGB images
• Uses TensorFlow and Keras for model building and training
• Simple, fully convolutional network design
• Trained on CIFAR-10 sample images

Future Improvements

• Train on larger datasets like CelebA or ImageNet
• Improve loss function (e.g., perceptual loss)

📚 Technologies Used

• Python 3
• TensorFlow
• Matplotlib (for visualizations)

sample output