Skip to content

Seminar project in Bio-inspired Artificial Intelligence.

Notifications You must be signed in to change notification settings

Leo-Lem/image-captioning

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

45 Commits
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

Different decoder architectures for Image Captioning

flickr8k dataset is used.

Image features are encoded using EfficientNet B0.

Evaluate different decoder architectures:

  • LSTM
  • GRU
  • Transformer

Models are evaluated using:

  • BLEU
  • METEOR
  • NIST

Running the project

python image-captioning -h