Language: 🇺🇸 🇨🇳

«NetworkSlimming» re-implements the paper Learning Efficient Convolutional Networks through Network Slimming

More training statistics can see:

• Details

Table of Contents

• Table of Contents
• Background
• Usage
• Maintainers
• Thanks
• Contributing
• License

Background

Network Slimming uses L1 regularization to sparsely train the BN layer's scaling factor; After the training, it performs channel-level pruning operation; Finally, by fine-tuning to recovery performance. it achieves good results in practical application.

Usage

First, you need set env for PYTHONPATH and CUDA_VISIBLE_DEVICES

$ export PYTHONPATH=<project root path>
$ export CUDA_VISIBLE_DEVICES=0

Then, begin train-prune-finetuning

• For train

$ python tools/train.py -cfg=configs/vggnet/vgg16_bn_cifar100_224_e100_sgd_mslr_slim_1e_4.yaml

• For prune

$ python tools/prune/prune_vggnet.py

• For fine-tuning

$ python tools/train.py -cfg=configs/vggnet/refine_pruned_0_2_vgg16_bn_cifar100_224_e100_sgd_mslr_slim_1e_4.yaml

Finally, set the fine-tuning model path in the PRELOADED option of the configuration file

$ python tools/test.py -cfg=configs/vggnet/refine_pruned_0_2_vgg16_bn_cifar100_224_e100_sgd_mslr_slim_1e_4.yaml

Maintainers

• zhujian - Initial work - zjykzj

Thanks

• Eric-mingjie/network-slimming
• wlguan/MobileNet-v2-pruning
• 666DZY666/micronet
• foolwood/pytorch-slimming

@misc{liu2017learning,
      title={Learning Efficient Convolutional Networks through Network Slimming}, 
      author={Zhuang Liu and Jianguo Li and Zhiqiang Shen and Gao Huang and Shoumeng Yan and Changshui Zhang},
      year={2017},
      eprint={1708.06519},
      archivePrefix={arXiv},
      primaryClass={cs.CV}
}

Contributing

Anyone's participation is welcome! Open an issue or submit PRs.

Small note:

• Git submission specifications should be complied with Conventional Commits
• If versioned, please conform to the Semantic Versioning 2.0.0 specification
• If editing the README, please conform to the standard-readme specification.

License

Apache License 2.0 © 2021 zjykzj