Pinned Repositories
Artificial-Neural-Network
Some of the most successful deep learning methods involve artificial neural networks. Artificial neural networks are inspired by the 1959 biological model proposed by Nobel laureates David H. Hubel & Torsten Wiesel, who found two types of cells in the primary visual cortex: simple cells and complex cells. Deep learning (deep structured learning or hierarchical learning) is a branch of machine learning based on a set of algorithms that attempt to model high-level abstractions in data by using model architectures. cs231n.github.io, theano tutorial and ufldl.stanford.edu has a reference.
backgrid
Finally, an easily stylable semantic HTML data grid widget with a Javascript API that doesn't suck.
caffe
Caffe: a fast open framework for deep learning.
cloudstorage
Unified cloud storage API for storage services.
code_and_command
it is temporary directory having code files and commands.
goal-oriented-action-planning
Goal oriented action planner(GOAP) is AI program which can be driven by max scoring, this algorithm works on exploring potential plans to maximize score and choses the action according to plan. check out the src directory for planner, this capability was tested on MIT-Battle code 2017. I would like to welcome others to try and collaborate, I am open for helping.
Image-segmentation-opencv
Implementation of the segmentation algorithm described in: Efficient Graph-Based Image Segmentation Pedro F. Felzenszwalb and Daniel P. Huttenlocher International Journal of Computer Vision, 59(2) September 2004.
Machine-Learning-Application
TwitMiner Are you a social media addict? Are you a follower of celebrity pages and accounts? Are you interested in what’s happening around you? Does challenging problems set adrenalin racing through your veins? Then this is the right place to be in. The Computer Science and Automation department of Indian Institute of Science, Bangalore presents the first of its kind Machine Learning contest in India: Develop a prediction algorithm by learning from a collection of texts(tweets) hosted by Twitter.com.
OCR-using-SWT
This project objective describes a device dedicated for blind or visually impaired people. The main aim of this system is to provide an automated image classifier to classify the languages. The challenge for such system is it should be a portable, low cost, able to recognize distorted images, multiple languages and efficient working in term of ability to recognize multiple size character. The two key technologies are necessary: text detection and language detection. A further improvement can also be done by integrating it with Google translator which can be used by visually impaired people . Even though several researches have been done in this area ,it has been observed that implementation of language detection is not yet done. So a multi language detector is required for India, Since India has several languages.
ssd_detectors
SSD-based object and text detection with Keras, SSD, DSOD, TextBoxes, SegLink, TextBoxes++, CRNN
madan-ram's Repositories
madan-ram/Artificial-Neural-Network
Some of the most successful deep learning methods involve artificial neural networks. Artificial neural networks are inspired by the 1959 biological model proposed by Nobel laureates David H. Hubel & Torsten Wiesel, who found two types of cells in the primary visual cortex: simple cells and complex cells. Deep learning (deep structured learning or hierarchical learning) is a branch of machine learning based on a set of algorithms that attempt to model high-level abstractions in data by using model architectures. cs231n.github.io, theano tutorial and ufldl.stanford.edu has a reference.
madan-ram/OCR-using-SWT
This project objective describes a device dedicated for blind or visually impaired people. The main aim of this system is to provide an automated image classifier to classify the languages. The challenge for such system is it should be a portable, low cost, able to recognize distorted images, multiple languages and efficient working in term of ability to recognize multiple size character. The two key technologies are necessary: text detection and language detection. A further improvement can also be done by integrating it with Google translator which can be used by visually impaired people . Even though several researches have been done in this area ,it has been observed that implementation of language detection is not yet done. So a multi language detector is required for India, Since India has several languages.
madan-ram/ssd_detectors
SSD-based object and text detection with Keras, SSD, DSOD, TextBoxes, SegLink, TextBoxes++, CRNN
madan-ram/backgrid
Finally, an easily stylable semantic HTML data grid widget with a Javascript API that doesn't suck.
madan-ram/caffe
Caffe: a fast open framework for deep learning.
madan-ram/cloudstorage
Unified cloud storage API for storage services.
madan-ram/code_and_command
it is temporary directory having code files and commands.
madan-ram/creating-a-pipeline-in-blue-ocean
For an introductory tutorial on how to use the Blue Ocean feature of Jenkins to create a Pipeline that builds an application.
madan-ram/CUTIE
Convolutional Universal Text Information Extrator
madan-ram/darknet
Convolutional Neural Networks
madan-ram/detr
End-to-End Object Detection with Transformers
madan-ram/detr-tensorflow
Tensorflow implementation of DETR : Object Detection with Transformers
madan-ram/Drawflow
Simple flow library 🖥️🖱️
madan-ram/fasttext-server
Flask web server to serve supervised models trained with FastText.
madan-ram/fasttext-serving
fastText model serving service
madan-ram/flowy
The minimal javascript library to create flowcharts ✨
madan-ram/label-studio-frontend
Data labeling react app that is backend agnostic and can be embedded into your applications — distributed as an NPM package
madan-ram/llama-recipes
Examples and recipes for Llama 2 model
madan-ram/madan-ram.github.io
madan-ram/models
Models and examples built with TensorFlow
madan-ram/opencv
Open Source Computer Vision Library
madan-ram/pdftabextract
A set of tools for extracting tables from PDF files helping to do data mining on (OCR-processed) scanned documents.
madan-ram/Problem
madan-ram/Reinforcement-learning
assignment in ‘Reinforcement Learning’ by Sutton and Barto
madan-ram/serve
Serve, optimize and scale PyTorch models in production
madan-ram/SSD-Tensorflow
Single Shot MultiBox Detector in TensorFlow
madan-ram/ssd_keras
A Keras port of Single Shot MultiBox Detector
madan-ram/tensorflow
An Open Source Machine Learning Framework for Everyone
madan-ram/tensorflow-serving-example
Examples to server tensorflow models with tensorflow serving
madan-ram/tf-slim