Arun Das's Projects
WIP: Personal Website
Course Lectures and Code for IS7033 Topics in Advanced AI/ML Research, Fall 2020, UT San Antonio.
A repository to host papers, reviews and code for adversarial machine learning research.
A beautiful, simple, clean, and responsive Jekyll theme for academics
Academic website based on adacemicpages template
š¼ļø Attend to You: Personalized Image Captioning with Context Sequence Memory Networks. In CVPR, 2017. Expanded : Towards Personalized Image Captioning via Multimodal Memory Networks. In IEEE TPAMI, 2018.
Course materials/Homework materials for the FREE MOOC course on "Creative Applications of Deep Learning w/ Tensorflow" #CADL
Caffe: a fast open framework for deep learning.
:beers: :rocket: :city_sunset: face recognition training project(pytorch)
Code for generating the Chameleon CC-Ubuntu16.04 image
ClassifyME is an Automatic Image Classification Engine being developed for low power (Raspberry Pi like) computing devices. A master-slave configuration testbed is in active development.
An adversarial example library for constructing attacks, building defenses, and benchmarking both
Mini Project, Programming Techniques for Cloud, Spring 2016, UTSA.
Projects on Computer Architecture which I did as a part of my Graduate coursework.
My tests and experiments on Caffe, the deep learning framework by Berkeley Vision and Learning Center (BVLC) and its contributors.
Benchmarking Deep Learning operations on different hardware
Compiling a list of all the helper functions I've written for Pytorch
TFLearn Implementation of DeXpression architecture. Batch normalization is used instead of LRN. Gives a precision of 99.3 percent, recall of 99.2 percent and f1-score of 99.2 percent on CKPlus Dataset for human emotion recognition from frontal facial images.
Keras implementation of DeXpression architecture mentioned in this paper: https://arxiv.org/abs/1509.05371
A Deep Learning Approach To Screen Diabetic Retinopathy from Retinal Fundus Images.
Instructions for setting up the software on your deep learning machine
Dockerfile collection
Real-time face detection and emotion/gender classification using fer2013/imdb datasets with a keras CNN model and openCV.
Platform to process DNA and RNA sequenced data and provide relevant analysis on the data.