Tarun Gupta's repositories
HAR
Classify human actions into six different categories from smartphone sensor data. Initially used pre-processed data from a smartphone accelerometer and implemented Support Vector Machine (SVM) to classify the actions. As an improvement in the next phase, train a deep convolutional neural network with long-short-term memory cells, which produced more accurate results.
Simulate-linux-files-and-directory-commands
A python program that can simulate linux files and directory commands such as list(ls) ,copy(cp) ,move(mv) ,rename(mv) ,delete(rm),file details(ls l), dirstr(directory structure) (without using any system command).
Conversations
Conversations is an open source XMPP/Jabber client for Android 4.0+ smart phones.
MobileSecurity
Mobile Security Solution on Cloud.
Orchestration
Built a framework that can coordinate the provisioning of compute resources by negotiating with a set of hypervisors running across physical servers in the datacenter.
swift
Swift XMPP client and Swiften XMPP library
Carrom-Game-2D
This is a 2D game for Carrom using OpenGL.
CLIP
Contrastive Language-Image Pretraining
crowdsource-platform
The main repository for Crowdsource Platform
ls-command
Our own ls program using ONLY system calls with different options (-l, -a, -h).
MARL-Papers
Paper list of multi-agent reinforcement learning (MARL)
MDPWithOptions
This is an implementation of MDP with Options paper. http://www-anw.cs.umass.edu/~barto/courses/cs687/Sutton-Precup-Singh-AIJ99.pdf
MiniSQLEngine
A mini sql engine which will run a subset of SQL Queries using command line interface .
PyTorch-Encoding
Part Segmentation for EANet
REFIL
Code for "Randomized Entity-wise Factorization for Multi-Agent Reinforcement Learning" ICML 2021
Spam-Mail-Filtering
Feature Extraction from emails, generating vocabulary through lemmatization and stemming and converting them to feature vectors and classifying them as spam or non-spam. Analyzing and comparing the performance of various classification algorithms.
taming-transformers
Taming Transformers for High-Resolution Image Synthesis