Reproduce “Learning Efficient Convolutional Networks through Network Slimming” on OpenResearch

Turn your favorite coding agents into research agents that review literature, develop hypotheses, and run experiments.

Universal app for Apple silicon and Intel. Requires macOS 11 or later.

About this paper

Zhuang Liu, Jianguo Li, Zhiqiang Shen, Gao Huang, Shoumeng Yan, Changshui Zhang

The authors present network slimming, which uses batch-normalization scale factors to identify channels to prune, encourages factors toward zero during training, then removes channels and fine-tunes the narrower network. On CIFAR-10 VGGNet, pruning 70% of channels reduced parameters from 20.04M to 2.30M and FLOPs by 51.0%, while test error fell from 6.34% to 6.20% in this single-pass experiment.

Summary by alphaXiv.

Tip: change arxiv.org to autoarxiv.org in any arXiv abstract link to open the paper here.