This is RNN+CNN Visual Question Answering Model. It uses VGG16 for image feature extraction. VQA Dataset is used for training the model.
- Keras version 2.0+
- Tensorflow 1.2+
- Spacy version 2.0+
- To upgrade & install Glove Vectors
- python -m spacy download en_vectors_web_lg
- To upgrade & install Glove Vectors
- OpenCV
Download my pretrained model from here
For running pretrained model in Google Colab Click Here
For training the model run:
$ python train.py
Currently in intitial stages. You have to rename the image with the question you want to ask. For running:
$ set FLASK_APP=hello_app.py
$ flask run
https://github.com/VT-vision-lab/VQA_LSTM_CNN