For more information about the method, please read the paper (.pdf) above.

This repository was not created by the paper author.

If you find an error, please, let me know creating an issue on github.

1. Download the code base

   CMD: git clone https://github.com/SilvestrePerret/weldon.reset.keras.tensorflow.git

2. Create the environnement

   CMD: python -m virtualenv .env

3. Activate it

   • for Windows: CMD: .env\Script\activate
   • for linux: CMD: .env\bin\activate

4. Install the requirements

   CMD: pip install -r requirements.txt

5. Run the tests

   CMD: python -m unittest discover -s tests

@inproceedings{Durand_WELDON_CVPR_2016,
author = {Durand, Thibaut and Thome, Nicolas and Cord, Matthieu},
title = {{WELDON: Weakly Supervised Learning of Deep Convolutional Neural Networks}},
booktitle = {The IEEE Conference on Computer Vision and Pattern Recognition (CVPR)},
year = {2016}
}