Skip to content

oarriaga/neural_image_captioning

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

22 Commits
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

Neural Image Captioning (NIC)

Neural image captioning implementation with Keras based on Show and Tell.

alt tag

Instructions

To train from zero using the iapr2012 dataset:

  • Download IAPR2012 dataset from here
  • Move the downloaded file to the datasets/IAPR_2012/ directory
  • Untar the file:

tar xvf iaprtc12.tgz

Extract/download image features

To extract:

  • Edit the file train.py by changing the flag extract_image_features to True.

To download:

  • Download the image features:

  • Download the extracted image features from here

  • Move them do datasets/IAPR_2012/preprocessed_data/ directory

  • Start training by running the script

python3 train.py

Notes

  • Extracting the image features might take 1-2 hours in a GTX860M.
  • Training 50 epochs should give you reasonable results.
  • I will provide pre-trained models in COCO soon (hopefully)

About

Neural image captioning (NIC) implementation with Keras 2.

Resources

License

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published