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.

GitHub
376 stars
25 watching
133 forks
Language: Lua
last commit: over 5 years ago
Linked from 1 awesome list


Backlinks from these awesome lists: