About
Projects
Neural Style Transfer
Neural style transfer is an optimization technique used to take two images—a content image and a style reference image (such as an artwork by a famous painter)—and blend them together so the output image looks like the content image, but “painted” in the style of the style reference image.
This repository takes two images:
1. Content image -> The main image on which we need to apply the style.
2. Style image -> The image from which we want to extract the style which will be applied to the content image.
Finally we use a convolution neural network to extract style representations which will be applied to the content image representation.
Canadian Elections Sentiment Analysis
I am not very interested in politics, but Canadian elections were an event where I wanted to test how sentiments of people towards different political leaders change with each new controversy coming out.
This project uses very basic tools:
1. tweepy to pull tweets related to our two main candidates 'Justin Trudeau' and 'Andrew Scheer'.
2. Running nltk,textblob,spacy etc to get sentiments of people's tweets towards two candidate.