lakmalnd
AI and Machine Learning Researcher. And Geo-spatial Data Analyst.
Geoinformatics Center (GIC) of AITThailand and Sri Lanka
Pinned Repositories
centroid-unet
Centroid-UNet is deep neural network model to detect centroids from satellite images.
DL-for-satellite-image-analysis
This includes short and minimalistic few examples covering fundamentals of Deep Learning for Satellite Image Analysis (Remote Sensing).
intro-to-gee-and-application
This tutorial includes introduction to fundamentals of Google Earth Engine (GEE) with Python and Applications (Case Studies) of GEE.
pLitter
pLitter is a standardized, deep learning friendly dataset and pre-trained model that can be used for detecting plastic litter in streets , road-sides, etc. Additionally, all supplementary codes related to this repository are also published here.
PyAEZ
PyAEZ is a python package consisted of many algorithms related to Agro-ecalogical zoning (AEZ) framework.
python-for-geospatial-data-analysis
This includes short and minimalistic few sessions covering fundamentals of Python programing language for geospatial data analysis.
deep-protein-structure-modeling
This repository is about prediction of tertiary structure of proteins from the primary structure of proteins (sequences of amino acids). So here, I'm trying to build a neural network that can input sequence of amino acids and output 3D structure of proteins (coordinates of major atoms in proteins that define the overall shape of the protein).
simple-vehicle-count-algorithm
This algorithm counts vehicles passing through a particular line on a stable video (Drone). Here I use simple background extracting techniques (just with simple statistics) to do that.
SimpleVAE
This repository provides implementation simplified Variational Autoencoder (VAE), producing smooth latent space completely unsupervised manner. And this can be used as generative model as well.
Vec2Instance
This repository provides an implementation of Vec2Instance over the SpaceNet challenge AOI 2 (Vegas) building footprint dataset. Vec2Instance provides a framework for parametrization of instances, allowing convolutional neural networks to efficiently estimate the complex shapes of instances around their centroids.
lakmalnd's Repositories
lakmalnd/Vec2Instance
This repository provides an implementation of Vec2Instance over the SpaceNet challenge AOI 2 (Vegas) building footprint dataset. Vec2Instance provides a framework for parametrization of instances, allowing convolutional neural networks to efficiently estimate the complex shapes of instances around their centroids.
lakmalnd/SimpleVAE
This repository provides implementation simplified Variational Autoencoder (VAE), producing smooth latent space completely unsupervised manner. And this can be used as generative model as well.
lakmalnd/simple-vehicle-count-algorithm
This algorithm counts vehicles passing through a particular line on a stable video (Drone). Here I use simple background extracting techniques (just with simple statistics) to do that.
lakmalnd/deep-protein-structure-modeling
This repository is about prediction of tertiary structure of proteins from the primary structure of proteins (sequences of amino acids). So here, I'm trying to build a neural network that can input sequence of amino acids and output 3D structure of proteins (coordinates of major atoms in proteins that define the overall shape of the protein).