hanskrupakar Goto Github PK
Name: Hans Krupakar
Type: User
Bio: Data Science | Computer Vision
Twitter: HansKrupakar
Name: Hans Krupakar
Type: User
Bio: Data Science | Computer Vision
Twitter: HansKrupakar
An implementation of 3D U-Net CNN models for the task of voxel-wise semantic segmentation of 3D MR images for isolation of Low-Grade and High Grade Gliomas, the common types of brain tumour.
This is a collection of all the apps I created in order to familiarise myself with the use of Android Studio to build android apps.
Generate images, bounding boxes and segmentation masks for bags sitting on shelves by using HSV ranges over retail catalogue images.
This contains code for various curiosity-quenching models that were implemented because of wanting to understand the nature and behaviour of Neural Nets. Also are the models for AlexNet and ResNet architectures in TensorFlow.
A simple GUI-based COCO-style JSON Polygon masks' annotation tool to facilitate quick and efficient crowd-sourced generation of annotation masks and bounding boxes. Optionally, one could choose to use a pretrained Mask RCNN model to come up with initial segmentations.
This is part of a research project I am conducting on the effects of morphological segmentation on the embedding process using algorithms like Word2Vec.
English Tamil MT is part of a project carried out for ADD (Acoustic Dialect Decoder). It implements Moses based SMT and Neural MT in TensorFlow.
Deep Learning Fast & Easy
This repo consists of customized graph path traversal algorithms to display all ancestors of an input node and all possible descendants in a specific indented format. It is work done for a company and the JSON files in the project are removed. The algorithms are implemented in JavaScript.
These are few of the open APIs I implemented during my internship in Company XYZ.
Analysis of divergence between the weight parameters of a CNN model over several local minima for various standard datasets like MNIST, CIFAR etc.
Mask R-CNN for object detection and instance segmentation on Keras and TensorFlow
Fast, modular reference implementation of Instance Segmentation and Object Detection algorithms in PyTorch.
A Web App to label datasets for instance segmentation and dense object detection tasks.
This project uses the Agrimet 15-min Precipitation dataset (2014-2017) to train an RNN prediction network for precipitation using 25 15-min timesteps as input and 6 hour cumulative precipitation as forecast output. The baseline RNN system is then supplemented with the NEXRAD RADAR Images dataset from which the 3-hour precipitation accumulations radar map for 2 years (644 days) and using a CNN-RNN hybrid multimodally tries to predict precipitation.
Efficient PyTorch Hessian eigendecomposition using the Hessian-vector product and stochastic power iteration
This is a converging bottom up implementation of the Recurrent Neural Network architecture with 3 layers and a tanh activation function using only numpy in Python.
This repo consists of the very few models I built using Tensorflow that helped me learn the internal workings of TensorFlow, Google's Computation Tool.
Datasets, Transforms and Models specific to Computer Vision
A declarative, efficient, and flexible JavaScript library for building user interfaces.
🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
An Open Source Machine Learning Framework for Everyone
The Web framework for perfectionists with deadlines.
A PHP framework for web artisans
Bring data to life with SVG, Canvas and HTML. 📊📈🎉
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
Some thing interesting about web. New door for the world.
A server is a program made to process requests and deliver data to clients.
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
Some thing interesting about visualization, use data art
Some thing interesting about game, make everyone happy.
We are working to build community through open source technology. NB: members must have two-factor auth.
Open source projects and samples from Microsoft.
Google ❤️ Open Source for everyone.
Alibaba Open Source for everyone
Data-Driven Documents codes.
China tencent open source team.