Need help with MatchingNetworks?
Click the “chat” button below for chat support from the developer who created it, or find similar developers for support.

About the developer

gitabcworld
272 Stars 74 Forks Other 28 Commits 7 Opened issues

Description

This repo provides pytorch code which replicates the results of the Matching Networks for One Shot Learning paper on the Omniglot and MiniImageNet dataset

Services available

!
?

Need anything else?

Contributors list

# 146,396
Python
few-sho...
optimiz...
pytorch
24 commits
# 303,010
Jupyter...
Python
review
HTML
1 commit

Matching Networks for One Shot Learning

This repo provides a Pytorch implementation fo the Matching Networks for One Shot Learning paper.

Installation of pytorch

The experiments needs installing Pytorch

Data

For the Omniglot dataset the download of the dataset is automatic. For the miniImageNet you need to download the ImageNet dataset and execute the script utils.createminiImagenet.py changing the lines: ``` pathImageNet = '<pathtodownloadedImageNet>/ILSVRC2012imgtrain' pathminiImageNet = '/miniImagenet/'

And also change the main file option.py line or pass it by command line arguments:
parser.addargument('--dataroot', type=str, default='<pathtosaveMiniImageNet>/miniImagenet/',help='path to dataset') ```

Installation

$ pip install -r requirements.txt
$ python mainOmniglot.py `#Code for OmniGlot`
$ python mainMiniImageNet.py `#Code for miniImageNet`

Acknowledgements

Special thanks to https://github.com/zergylord and https://github.com/AntreasAntoniou for their Matching Networks implementation. I intend to use some parts for this implementation. More details at https://github.com/zergylord/oneshot and https://github.com/AntreasAntoniou/MatchingNetworks

Cite

@inproceedings{vinyals2016matching,
  title={Matching networks for one shot learning},
  author={Vinyals, Oriol and Blundell, Charles and Lillicrap, Tim and Wierstra, Daan and others},
  booktitle={Advances in Neural Information Processing Systems},
  pages={3630--3638},
  year={2016}
}

Authors

  • Albert Berenguel (@aberenguel) Webpage

We use cookies. If you continue to browse the site, you agree to the use of cookies. For more information on our use of cookies please see our Privacy Policy.