Ishan Bhatt's repositories
Vizualize-CONV-FeatureExtractors
Code described in blog post
HarryPotter-InvisiblityCloak
Building Harry Potter's invisibility cloak
BUG-on-a-wire
train an agent to play the game using random-forest
Income-Tax-Calculator
Income Tax Management tool in C++
KMeansClustering-Python
We implement KMeans clustering from scratch in python
Lane-Annotation-for-Self-Driving-Car
This notebook uses HoughLines Probabilistic to locate traffic-lanes as seen from a car driver's seat.
Program2-nDijkstra-vs-FloydWarshall
In this project, we aim to compare the performance of two popular algorithms for solving the all-pairs shortest path problem: N iterations of the Dijkstra’s algorithm (1 iteration per node); Floyd-Warshall Algorithm. We implement both these algorithms in C++ and analyze their performance on different graph structures using the values for runtime and number of comparisons. We make some hypotheses related to the performance of these algorithms and try to validate or invalidate them by designing experiments to test them. We explain how we executed the experiments and report our findings in this paper.
SinglePerson2DPoseEstimation
Single Person 2D Pose Estimation System (inspired from CPMs and SHMs); trained and evaluated on a subset of the MPII HumanPosedataset; achieves 81.5% PCKh@0.5
TerrainRecognition-Competition
Project made as part of ECE542: Deep Learning & Neural Networks; TerrainRecognition. This work finished first on the leaderboard with F1-score of 0.935 on the private-test set.
alpha-wordle
Taking the fun out of WORDLE! We use AI to solve wordle!
awesome-python-template
This repository is a base repository for python projects; we handle unit testing (with hooks), a template README and a .gitignore
dashboard_netload_forecasting
This repository will house code for the data and result visualization dashboard for net load forecasting
DSs-in-C-
This repository is intended to serve as a resource for error-free implementations of all data structures
GalaxyClassification
SDSS telescopes have captured over 40 TB worth of galaxy images and classification of these images is the first step towards obtaining a deeper understanding of physical processes within them, star formation, and the nature of the universe. Since we could not find an easily accessible dataset for galaxy classification, we compiled a dataset for Galaxy classification and provided benchmarks with some of the common learning algorithms that would help in automating the galaxy classification which until recently had to be performed by hand by expert astronomers. We classify the images of galaxies into four classes: spiral, elliptical, irregular, and invalid.
iphw5
hw_repo for iphw5
Lower-Earth-Orbit-Trajectory-Predictor
First Year Project written in C++
se-hw2
To store my work for Software Engineering Homework 2
se-hw3
repository to store my files for SE hw3
se21
Files for an SE graduate class
whack-a-mole-fork
Created with CodeSandbox