An algorithm that effectively prune channels each layer, which could accelerate VGG-16 4x without degradation. Accepted as a poster at _ICCV 2017_.
latex<br/>@article{he2017channel,<br/> title={Channel Pruning for Accelerating Very Deep Neural Networks},<br/> author={He, Yihui and Zhang, Xiangyu and Sun, Jian},<br/> journal={arXiv preprint arXiv:1707.06168},<br/> year={2017}<br/>}<br/>
Models:
- VGG-16 4x 10.1% top-5 error and 29.4% top-1 error on ILSVRC-2012.
[[PDF](https://arxiv.org/abs/1707.06168)] [[Github repo](https://github.com/yihui-he/channel-pruning)]
无链接