Skip to content

Commit

Permalink
splits + comments + save_per_epoch
Browse files Browse the repository at this point in the history
  • Loading branch information
Kelvin Xu authored and Kelvin Xu committed May 17, 2015
1 parent 6f13f87 commit 00f7f00
Show file tree
Hide file tree
Showing 8 changed files with 123,424 additions and 65 deletions.
39 changes: 21 additions & 18 deletions README.md
Original file line number Diff line number Diff line change
@@ -1,22 +1,7 @@
# arctic-captions

Source code for [Show, Attend and Tell: Neural Image Caption Generation with Visual Attention](https://arxiv.org/abs/1502.03044)
runnable on cpu and gpu.

## License

Code is released under the [revised (3-clause) BSD
License](https://directory.fsf.org/wiki/License:BSD_3Clause). If you use this
code as part of any published research, please acknowledge the following paper.
(It does encourages researchers who publish their code!)

**"Show, Attend and Tell: Neural Image Caption Generation with Visual Attention."**
Kelvin Xu, Jimmy Ba, Ryan Kiros, Kyunghyun Cho, Aaron Courville, Ruslan
Salakhutdinov, Richard Zemel, Yoshua Bengio.
University of Toronto & Université de Montréal,
To appear in ICML (2015)

[[bibtex coming soon]()]
runnable on CPU and GPU. Joint collaboration between Université de Montréal & University of Toronto.

## Dependencies

Expand All @@ -32,9 +17,27 @@ In addition, this code is built using
problems with specific to Theano, please use a commit from around February 2015
and notify the authors.

To use the evaluation script: see [coco-caption](https://github.com/tylin/coco-caption)
To use the evaluation script: see [coco-caption](https://github.com/tylin/coco-caption) for the requirements.

## License

Code is released under the [revised (3-clause) BSD License](https://directory.fsf.org/wiki/License:BSD_3Clause). If you use this
code as part of any published research, please acknowledge the following paper
(It does encourages researchers who publish their code!):

**"Show, Attend and Tell: Neural Image Caption Generation with Visual Attention."**
Kelvin Xu, Jimmy Ba, Ryan Kiros, Kyunghyun Cho, Aaron Courville, Ruslan
Salakhutdinov, Richard Zemel, Yoshua Bengio. To appear ICML (2015)

@article{Xu2015show,
title={Show, Attend and Tell: Neural Image Caption Generation with Visual Attention},
author={Xu, Kelvin and Ba, Jimmy and Kiros, Ryan and Courville, Aaron and Salakhutdinov, Ruslan and Zemel, Richard and Bengio, Yoshua},
journal={arXiv preprint arXiv:1502.03044},
year={2015}
}

## Installation + Experiment Instructions

###Installation + Experiment Instructions
1) Install the above dependencies and `$ git clone` the repo
2) Install Theano using your [favourite method](https://www.deeplearning.net/software/theano/)
3) TODO, rest of this
Loading

0 comments on commit 00f7f00

Please sign in to comment.