Artistic style transfer using convolution neural network
Deep neural networks have demonstrated a near-human performance in the areas of object detection and face recognition. However, these networks have never been used to create images which look and feel like artistic images. This research introduced by Leon A.Gatys et.al is a novel articial system based on a deep neural network that creates artistic images using neural representations to separate and recombine content and style of arbitrary images. It relies on the fact that when convolutional neural networks are trained on object recognition, they develop an abstract representation of image that makes object information increasingly explicit along the processing hierarchy. This repository contains re-implementaion of artistic style transfer with PyTorch on Google colab as stated by Leon A.Gatys et.al in their research.
- Programming Languages: Python 3
- Libraries: Numpy,OpenCV,Matplotlib
- Deep Learning Framework: PyTorch