This code is a re-implementation of the imagenet classification experiments in the paper Data-Driven Sparse Structure Selection for Deep Neural Networks (ECCV2018).

If you use our code in your research or wish to refer to the baseline results, please use the following BibTeX entry.

@article{SSS2018
  author =   {Zehao Huang and Naiyan Wang},
  title =    {Data-Driven Sparse Structure Selection for Deep Neural Networks},
  journal =  {ECCV},
  year =     {2018}
}

This code is implemented by a modified MXNet which supports ResNeXt-like augmentation. (This version of MXNet does not support cudnn7)

Download the ImageNet dataset and create pass through rec (following tornadomeet's repository but using unchange mode)

• modify config/cfgs.py
• python train.py