参考文献

最新推荐文章于 2025-03-14 13:02:58 发布

半度微凉1993

最新推荐文章于 2025-03-14 13:02:58 发布

阅读量1.1k

点赞数

本文链接：https://blog.youkuaiyun.com/weixin_36835368/article/details/104493806

版权

这篇博客探讨了深度学习模型的优化方法，包括剪枝、量化、融合和参数共享等技术。引用了多个研究论文，如Song Han等人的Deep Compression、Ioffe和Szegedy的Batch Normalization、Pham等人的参数共享方法以及各种模型压缩在边缘设备上的应用，如SqueezeNet和MobileNet。此外，还提到了一些重要的深度学习架构，如ResNet、DeepLab和FCN，以及数据集Cityscapes和COCO。

摘要生成于 C知道，由 DeepSeek-R1 满血版支持，前往体验 >

剪枝：

[1] Song Han, Huizi Mao，William J.Dally. Deep Compression: Compressing Deep Neural Networks with Pruning, Trained Quantization and Huffman coding[C] ICLR2016.

量化：

[1] Benoit Jacob, Skirmantas Kligys, Bo Chen, Menglong Zhu,Matthew Tang, Andrew Howard, Hartwig Adam, and DmitryKalenichenko. Quantization and training of neural networksfor efficient integer-arithmetic-only inference. InThe IEEEConference on Computer Vision and Pattern Recognition(CVPR), June 2018.

[2]Raghuraman Krishnamoorthi.Quantizing deep convolu-tional networks for efficient inference: A whitepaper.CoRR,abs/1806.08342, 2018.

[3]Jiaxiang Wu, Cong Leng, Yuhang Wang, Qinghao Hu, andJian Cheng. Quantized convolutional neural networks formobile devices.CoRR, abs/1512.06473, 2015.

[4]Aojun Zhou, Anbang Yao, Yiwen Guo, Lin Xu, and YurongChen. Incremental network quantization: Towards losslesscnns with low-precision weights.CoRR, abs/1702.03044,2017.</