Neural Style Transfer

Neural Style Transfer is a technique that combines the style of one image with the content of another image, resulting in a new image that retains the content but adopts the style of the reference image. This repository provides an implementation of Neural Style Transfer using deep learning.

Prerequisites

• Python 3.7 or above
• TensorFlow 2.0 or above
• Keras 2.3.0 or above
• NumPy
• Matplotlib

Customization

• You can adjust the hyperparameters such as the number of iterations, content weight, style weight, etc., in the NeuralStyleTransfer.ipynb file to customize the style transfer process.
• Feel free to explore different style and content images to achieve your desired artistic effects.

For Streamlit Implementation consider NeuralStyleTransferWeb.ipynb

References

• Gatys, L.A., Ecker, A.S., & Bethge, M. (2016). Image Style Transfer Using Convolutional Neural Networks.
• TensorFlow Documentation

Authors

• Swarup Kanade @swarupkanade
• Omkar Kanade @omkarkanade