Jcs Kadupitiya's repositories
ROS-TurtleBot-PID
This project demonstrates the simulation of ROS Turtlebot3 path tracking with PID. I have generalized the pid controller to track circular or linear trajectories; Please check the video till end.
bnsl
Simualtes the assembly of binary nanoparticle superlattices (BNSL)
connexion
Swagger/OpenAPI First framework for Python on top of Flask with automatic endpoint validation & OAuth2 support
Convolutional_neural_network
This is the code for "Convolutional Neural Networks - The Math of Intelligence (Week 4)" By Siraj Raval on Youtube
data4ML
contains datasets for training and testing ML models
hamiltonian-nn
Code for our paper "Hamiltonian Neural Networks"
Hardware_Neural_Net
Artificial Neural Network in hardware
hid-sample
Gregor von Laszewski
hid-sp18-416
Sabra, Ossen
kadupitiya.github.io
My Portfolio for APPs
markdown-cheatsheet
Markdown Cheatsheet for Github Readme.md
nanobind
polyvalent nanoparticle binding simulator
nanoconfinement-md
This code allows users to simulate ions confined between material surfaces that are nanometers apart, and extract the associated ionic structure.
np-assembly-lab
Simulates assembly of nanoparticles and oppositely-charged linkers under different physiological conditions. Outputs are structural information such as pair distribution functions.
np-electrostatics-lab
This code computes the density distribution of ions near a spherical nanoparticle in biological environments
np-shape-lab-1
The shape of nanoparticles determines their ability to interact with biological systems in nanomedicine applications. This framework simulates the shape deformation of deformable patchy nanoparticles for a broad variety of nanoparticle material properties and solution conditions. Molecular dynamics based simulated annealing is used to minimize the energy of the nanoparticle for a given set of material and solution parameters. Users can input control parameters such as the maximum surface charge, surface patch size, stretching modulus, and bending modulus, as well as control the solution ionic strength (salt concentration) changing the electrostatic drive to deform. Changing patch size parameter tunes the surface charge from a small value close to 0 to the maximum surface charge selected by the user. Suggested values of patch size are 0.25, 0.5, 0.75, 0.9 to observe a wide range of shape transitions. After running the simulation, in various output tabs, users can view the snapshots of the nanoparticle shape at various stages of the energy minimization process. Plots of the minimization of the electrostatic energy and increase in the area of the nanoparticle are also available (both these quantities are normalized by the associated values of the initial spherical conformation). Volume of the nanoparticle is conserved, representative of a finite amount of cargo. The range of charge, elasticities, and salt concentrations enable users to observe deformation into varios equilibrium shapes including bowls, hemispheres, discs, and rods, and egg-like conformations. The app is ran using hybrid MPI/OMP parallelized C++ codes and Python post-processing and app deployment. After the simulation, the following data files can be downloaded: final image of the shape of the container (PNG), movie of the entire deformation process (LAMMPS output format for viewing in Ovito or VMD), raw area data (in units of the radius of the sphere), and raw energy data including electrostatic energy variation with time (in kB T).
openpilot
openpilot is an open source driver assistance system. openpilot performs the functions of Automated Lane Centering and Adaptive Cruise Control for over 150 supported car makes and models.
speedchallenge
The comma.ai Speed Prediction Challenge!
tb3_rescue_bot
tb3_rescue_bot for USAR
TensorFlow-Examples
TensorFlow Tutorial and Examples for Beginners with Latest APIs
TensorFlow-Tutorials
TensorFlow Tutorials with YouTube Videos
Twister2SVM
MPI Based SVM
XNOR-Net
ImageNet classification using binary Convolutional Neural Networks