Name: Venkata Sai Krishna Vanama
Type: User
Company: IIT Bombay
Bio: I am a PhD research scholar at Centre for Urban Science and Engineering (CUSE), Indian Institute of Technology, Bombay (IITB) from January 2016.
Location: Mumbai, India
Blog: https://sites.google.com/view/venkata-sai-krishna/home
Venkata Sai Krishna Vanama's Projects
Basic script to order data on Google Earth Engine using Python API
Generalized Radar Vegetation Index (GRVI) Matlab Toolbox Standalone
HistThresh toolbox - authored by Antti Niemistö
The code for the following papers: https://arxiv.org/pdf/1812.00786.pdf and https://arxiv.org/abs/1901.00861 see the website for more details:
This tutorial includes introduction to fundamentals of Google Earth Engine (GEE) with Python and Applications (Case Studies) of GEE.
Agent Based Modelling of Land use change
This repository contains the codes me and my collegues (Ms Rekha Khot M. and Ms Ruma Rani M) created as a part of teachers enrichment workshop on linear algebra and data analysis conducted at IIT Bombay. The codes elementary and well suited for beginners in GNU Octave. They span across eigenvalues, eigenvectors, systems of ordinary differential equations, QR decomposition, polynomial fitting etc.
Google Earth Engine implementation of the LandTrendr spectral-temporal segmentation algorithm. For documentation see:
Machine Learning and Python for Beginners. This repo will contain all the materials for 6-7 week course I shall teach to non-ML experts at Harris Manchester College, University of Oxford.
Deep Learning based audiovisual data analysis
Minimal and clean examples of machine learning algorithms implementations
Models and examples built with TensorFlow
Monk is a low code Deep Learning tool and a unified wrapper for Computer Vision.
Python implementation of NedborAfstromnings Model (NAM) lumped rainfall–runoff model
An ANFIS system to generate fuzzy flood maps from SAR
Material for distance learning course on "Geoprocessing using Python"
👩🏻🏫 Slides for OpenIntro Statistics
Code for the book Open source geoprocessing with Python
Jupyter Notebook-based workflows for programmatically accessing, processing, and visualizing 3D Elevation Program (3DEP) lidar data
Tutorial demonstrating how to create a semantic segmentation (pixel-level classification) model to predict land cover from aerial imagery. This model can be used to identify newly developed or flooded land. Uses ground-truth labels and processed NAIP imagery provided by the Chesapeake Conservancy.
The Places365-CNNs for Scene Classification
Portfolio webpage
TensorFlow implementation of original paper : https://github.com/hszhao/PSPNet