Projects Done

Project Duration: Aug 2019 - Nov 2019 (M.Tech mini project)

To overcome the disadvantages of the Blacklisting and Heuristic approach (ancient approach) and due to the increasing popularity of Machine Learning this problem was introduced as the problem to solve using Machine Learning techniques. The Machine Learning approach try to analyze the information of a URL and its corresponding websites or web pages, by extracting good feature representations of URLs and training a prediction model on training data of both malicious and benign URLs.

URL

Crowd size estimator with PyTorch

This project aims for estimating crowd size in the given image frame, the model used in this project is CERNet.The proposed CSRNet is composed of two major components: a convolutional neural network (CNN) as the front-end for 2D feature extraction and a dilated CNN for the back-end, which uses dilated kernels to deliver larger reception fields and to replace pooling operations.

Lastly, this was deployed using FLASK and can run locally, still working on the heroku implementation as facing error on increased slug size of the project.

TLDR(Too Long Didn’t Read) Text Summerizer

This project is based on the concept of “sentence similarity”, where summary is generated based on the rank of sentences from the input text given.
Project is then deployed on HEROKU using FLASK.
Check the project in action here : Click here