Repository files navigation

This code is a re-implementation of the imagenet classification experiments in the paperData-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 modifiedMXNet which supportsResNeXt-like augmentation. (This version of MXNet does not support cudnn7)

Download theImageNet dataset and create pass through rec (followingtornadomeet's repository but using unchange mode)

• modifyconfig/cfgs.py
• python train.py