Viraj Prabhu's repositories
premise-emnlp17
Code for The Promise of Premise: Harnessing Question Premises in Visual Question Answering (EMNLP 2017)
read-timer
A browser extension that provides an estimate of the time it will take to read an article
adaclue-web
Webpage for Active DA via Clustering Uncertainty-weighted Embeddings
GuessWhich
Evaluating Visual Conversational Agents via Cooperative Human-AI Games
pytorchviz
A small package to create visualizations of PyTorch execution graphs
sentry-web
Project page for SENTRY
torch-hdf5
Torch interface to HDF5 library
visdial-rl
PyTorch code for Learning Cooperative Visual Dialog Agents using Deep Reinforcement Learning
VQA-Chatbot
A Chatbot based on VQA(Visual Question Answering)
VQA_LSTM_CNN
Train a deeper LSTM and normalized CNN Visual Question Answering model. This current code can get 58.16 on OpenEnded and 63.09 on Multiple-Choice on test-standard.