avisingh599 / visual-qa

[Reimplementation Antol et al 2015] Keras-based LSTM/CNN models for Visual Question Answering
https://avisingh599.github.io/deeplearning/visual-qa/
MIT License
480 stars 186 forks source link

Added the arg parser to change the word vectors to glove #22

Open iamaaditya opened 8 years ago

iamaaditya commented 8 years ago

Major: As mentioned by honnibal in #17, I have added the parser argument to chance the word vectors to Glove. I have tested the working of all the three training files. Minor: Added the missing arg parser variables on trainLSTM_language.py file, only those which were found in train_LSTM_1.py