rakshithshetty Goto Github PK

a4nt-author-masking

Repository for author masking

adversarial-object-removal

Code base for our paper " Adversarial Scene Editing: Automatic Object Removal from Weak Supervision" appearing in NIPS 2018.

captiongan

Source code for the paper "Speaking the Same Language: Matching Machine to Human Captions by Adversarial Training"

causalvqa

causalvqa-1

cg_assignments

Assignments from the Computer Graphics Course

dataaugmentation_context

dnn-speech

This ist the repository for the term project Speech Recognition using Deep Neural Networks for the course ELEC-E5510-Speech Recognition

functional-zoo

PyTorch and Tensorflow functional model definitions

halide

a language for image processing and computational photography

lte-cnn

markovchnbenchmark

Benchmarking simple markov chain performance with python, Numpy and Theano

mymastersthesisaalto

Latex Source and material for my masters thesis

neuraltalk

NeuralTalk is a Python+numpy project for learning Multimodal Recurrent Neural Networks that describe images with sentences.

py-faster-rcnn

Faster R-CNN (Python implementation) -- see https://github.com/ShaoqingRen/faster_rcnn for the official MATLAB version

py-faster-rcnn-featextract

This is a clone of py faster rcnn -- With additional scripts to extract features for image/video captioning

rakshithshetty.github.io

My Blog

semanticadversary

Code for our paper "Towards Automated Testing and Robustification by Semantic Adversarial Data Generation"

simsearch-text

This code implements fast cosine similarity search between text sentences. You have a database of sentences (can be tweets/ documents etc ) and a list of query sentences. This code searches the database and finds the nearest neighbhor to the given queries using cosine similarity. The code supports 1) brute force search 2) Fast exact search by building smart indexes 3) Fast approximate search (given the error tolerance) . It is written in C language and you just need basic c compiler to use the code. It has been tested on linux 64 bit machines