In this paper, we introduce a new channel pruning method to accelerate very deep convolutional neural networks. Given a trained CNN model, we propose an iterative two-step algorithm to effectively prune each layer, by a LASSO regression based channel selection and least square reconstruction. We further generalize this algorithm to multi-layer and multi-branch cases. Our method reduces the accumulated error and enhances the compatibility with various architectures. Our pruned VGG-16 achieves the state-of-the-art results by 5x speed-up along with only 0.3% increase of error. More importantly, our method is able to accelerate modern networks like ResNet, Xception and suffers only 1.4%, 1.0% accuracy loss under 2x speed-up respectively, which is significant. Our code has been made publicly available.
@article{arxiv.2211.08339,
title = {Pruning Very Deep Neural Network Channels for Efficient Inference},
author = {Yihui He},
journal= {arXiv preprint arXiv:2211.08339},
year = {2022}
}
Comments
an extension of Channel Pruning for Accelerating Very Deep Neural Networks. arXiv admin note: substantial text overlap with arXiv:1707.06168