README.md

Image Descriptions

We analyze whether the visual questions contain enough information to provide an accurate description of the image using the Seq2Seq model. See NeuralTalk2 and Seq2Seq models for image caption generation.

Replace the Seq2Seq datafiles in place of the placeholders present in the repository. Use these in place of the French and English dataset in the Seq2Seq models.

Datafiles:

1. Training_captions
2. Training_questions