請用此 Handle URI 來引用此文件：
http://tdr.lib.ntu.edu.tw/jspui/handle/123456789/80021完整後設資料紀錄
| DC 欄位 | 值 | 語言 |
|---|---|---|
| dc.contributor.advisor | 簡韶逸(Shao-Yi Chien) | |
| dc.contributor.author | Bo-Ying Chen | en |
| dc.contributor.author | 陳柏穎 | zh_TW |
| dc.date.accessioned | 2022-11-23T09:21:28Z | - |
| dc.date.available | 2021-08-06 | |
| dc.date.available | 2022-11-23T09:21:28Z | - |
| dc.date.copyright | 2021-08-06 | |
| dc.date.issued | 2021 | |
| dc.date.submitted | 2021-07-29 | |
| dc.identifier.citation | T.-J. Yang, A. Howard, B. Chen, X. Zhang, A. Go, M. Sandler, V. Sze, and H. Adam, “Netadapt: Platform-aware neural network adaptation for mobile applications,” in Proceedings of European Conference on Computer Vision (ECCV), 2018, pp. 285–300. H. Li, A. Kadav, I. Durdanovic, H. Samet, and H. P. Graf, “Pruning filters for efficient convnets,” arXiv preprint arXiv:1608.08710, 2016. K. He, X. Zhang, S. Ren, and J. Sun, “Deep residual learning for image recognition,” in Proceedings of IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2016, pp. 770–778. S. Ren, K. He, R. Girshick, and J. Sun, “Faster r-cnn: Towards real-time object detection with region proposal networks,” in Proceedings of Neural Information Processing Systems (NIPS), 2015, pp. 91–99. C. Dong, C. C. Loy, K. He, and X. Tang, “Image super-resolution using deep convolutional networks,” arXiv preprint arXiv:1501.00092, 2015. G. Hinton, O. Vinyals, and J. Dean, “Distilling the knowledge in a neural network,” arXiv preprint arXiv:1503.02531, 2015. T. Chen, I. Goodfellow, and J. Shlens, “Net2Net: Accelerating Learning via Knowledge Transfer,” in International Conference on Learning Representations, nov 2016. A. Tulloch and Y. Jia, “High performance ultra-low-precision convolutions on mobile devices,” Proceedings of Neural Information Processing Systems (NIPS), dec 2017. Y.Gong, L.Liu, M.Yang, and L.Bourdev, “CompressingDeepConvolutional Networks using Vector Quantization,” Proceedings of International Joint Conference on Artificial Intelligence (IJCAI), 2015. D. D. Lin, S. S. Talathi, and V. S. Annapureddy, “Fixed point quantization of deep convolutional networks,” in International Conference on Machine Learning, vol. 6, 2016, pp. 4166–4175. S. Han, J. Pool, J. Tran, and W. Dally, “Learning both weights and connections for efficient neural network,” in Proceedings of Neural Information Processing Systems (NIPS), 2015, pp. 1135–1143. J.-H. Luo, J. Wu, and W. Lin, “Thinet: A filter level pruning method for deep neural network compression,” in Proceedings of IEEE International Conference on Computer Vision (ICCV), 2017, pp. 5058–5066. Z. Liu, J. Li, Z. Shen, G. Huang, S. Yan, and C. Zhang, “Learning efficient convolutional networks through network slimming,” in Proceedings of IEEE International Conference on Computer Vision (ICCV), 2017, pp. 2736–2744. Y.He, X.Zhang, and J.Sun, “Channel pruning for accelerating very deep neural networks,” in Proceedings of IEEE International Conference on Computer Vision (ICCV), 2017, pp. 1389–1397. R. Yu, A. Li, C.-F. Chen, J.-H. Lai, V. I. Morariu, X. Han, M. Gao, C.-Y. Lin, and L. S. Davis, “Nisp: Pruning networks using neuron importance score propagation,” in Proceedings of IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2018, pp. 9194–9203. P. Molchanov, A. Mallya, S. Tyree, I. Frosio, and J. Kautz, “Importance estimation for neural network pruning,” in Proceedings of IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2019, pp. 11 264– 11 272. X. Ding, G. Ding, Y. Guo, and J. Han, “Centripetal sgd for pruning very deep convolutional networks with complicated structure,” in Proceedings of IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2019, pp. 4943–4953. Y. He, P. Liu, Z. Wang, Z. Hu, and Y. Yang, “Filter pruning via geometric median for deep convolutional neural networks acceleration,” in Proceedings of IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2019, pp. 4340–4349. M. Sandler, A. Howard, M. Zhu, A. Zhmoginov, and L.-C. Chen, “Mobilenetv2: Inverted residuals and linear bottlenecks,” in Proceedings of IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2018, pp. 4510–4520. F. N. Iandola, S. Han, M. W. Moskewicz, K. Ashraf, W. J. Dally, and K. Keutzer, “Squeezenet: Alexnet-level accuracy with 50x fewer parameters and <0.5mb model size,” arXiv:1602.07360, 2016. X. Zhang, X. Zhou, M. Lin, and J. Sun, “Shufflenet: An extremely efficient convolutional neural network for mobile devices,” in Proceedings of IEEE Conference on Computer Vision and Pattern Recognition (CVPR), June 2018. Y. He, G. Kang, X. Dong, Y. Fu, and Y. Yang, “Soft filter pruning for accelerating deep convolutional neural networks,” arXiv preprint arXiv:1808.06866, 2018. S. Han, H. Mao, and W. J. Dally, “Deep compression: Compressing deep neural networks with pruning, trained quantization and huffman coding,” The International Conference on Learning Representations (ICLR), 2016. C.-T. Liu, Y.-H. Wu, Y.-S. Lin, and S.-Y. Chien, “Computation-performance optimization of convolutional neural networks with redundant kernel removal,” in 2018 IEEE International Symposium on Circuits and Systems (ISCAS). IEEE, 2018, pp. 1–5. P. Molchanov, S. Tyree, T. Karras, T. Aila, and J. Kautz, “Pruning convolutional neural networks for resource efficient inference,” arXiv preprint arXiv:1611.06440, 2016. M. Lin, R. Ji, Y. Zhang, B. Zhang, Y. Wu, and Y. Tian, “Channel pruning via automatic structure search,” in Proceedings of International Joint Conference on Artificial Intelligence (IJCAI), 2020. Z. Zhuang, M. Tan, B. Zhuang, J. Liu, Y. Guo, Q. Wu, J. Huang, and J. Zhu, “Discrimination-aware channel pruning for deep neural networks,” in Proceedings of Neural Information Processing Systems (NIPS), 2018, pp. 875–886. R. Tibshirani, “Regression shrinkage and selection via the lasso,” Journal of the Royal Statistical Society: Series B (Methodological), vol. 58, no. 1, pp. 267–288, 1996. D. P. Kingma and M. Welling, “Auto-encoding variational bayes,” arXiv:1312.6114, 2014. K. Sohn, H.Lee, and X.Yan, “Learning structured output representation using deep conditional generative models.” in Proceedings of Neural Information Processing Systems (NIPS), 2015. D. Karaboga and B. Basturk, “Artificial bee colony (abc) optimization algorithm for solving constrained optimization problems,” in Proceedings of the 12th International Fuzzy Systems Association World Congress on Foundations of Fuzzy Logic and Soft Computing, ser. IFSA ’07. Springer-Verlag, 2007, p. 789–798. B. Li, B. Wu, J. Su, G. Wang, and L. Lin, “Eagleeye: Fast sub-net evaluation for efficient neural network pruning,” arXiv preprint arXiv:2007.02491, 2020. A. Krizhevsky, G. Hinton et al., “Learning multiple layers of features from tiny images,” Technical report, University of Toronto, 2009. O. Russakovsky, J. Deng, H. Su, J. Krause, S. Satheesh, S. Ma, Z. Huang, A. Karpathy, A. Khosla, M. Bernstein, et al., “Imagenet large scale visual recognition challenge,” International Journal of Computer Vision (IJCV), vol. 115, no. 3, pp. 211–252, 2015. A. G. Howard, M. Zhu, B. Chen, D. Kalenichenko, W. Wang, T. Weyand, M. Andreetto, and H. Adam, “Mobilenets: Efficient convolutional neural networks for mobile vision applications,” 2017. D. P. Kingma and J. Ba, “Adam: A method for stochastic optimization,” arXiv:1412.6980, 2014. | |
| dc.identifier.uri | http://tdr.lib.ntu.edu.tw/jspui/handle/123456789/80021 | - |
| dc.description.abstract | 卷積神經網絡廣泛用於計算機視覺。需要存儲的大量參數和高計算複雜度導致它們需要具有大量資源的平台來實現某些場景，例如實時應用。為了在資源有限的平台上適應這些計算密集型網絡，研究人員開發了許多網絡壓縮技術，以在減少資源消耗的同時保持性能。成功的壓縮方法的關鍵是在給定資源(例如，參數、推理延遲)約束下產生具有最高性能的網絡。 剪枝是一種有效的網絡壓縮方法。它估計每個濾波器的重要性並消除那些不太重要的過濾器，直到滿足資源限制。雖然現有方法僅考慮網絡中的參數總量或浮點運算 (FLOPs) 作為約束，但這些指標忽略了網絡如何在目標平台上執行。在本論文中，將推理延遲等平台特性引入到修剪指標中。我們提出了一種新的平台感知過濾器修剪方法，可以擴大整個網絡的搜索空間。稱為平台感知架構生成器和搜索(PAGS)，它可以生成給定延遲約束的網絡架構並擴展整體模型架構搜索空間。在搜索階段，我們從生成器構建的候選集中搜索最佳修剪結構。最後，進行典型的剪枝程序將預訓練的模型剪枝為最佳剪枝結構和微調它以恢復性能。大量實驗表明，在相同的延遲約束下，我們的方法可以實現比最先進的方法更好的性能和更低的延遲。 | zh_TW |
| dc.description.provenance | Made available in DSpace on 2022-11-23T09:21:28Z (GMT). No. of bitstreams: 1 U0001-1907202101395100.pdf: 2610913 bytes, checksum: 15d3baaf814289b4f78068dfccece2a6 (MD5) Previous issue date: 2021 | en |
| dc.description.tableofcontents | Abstract i List of Figures v List of Tables vii 1 Introduction 1 1.1 NetworkPruning .......................... 2 1.1.1 UnstructuredPruning.................... 3 1.1.2 StructuredPruning ..................... 5 1.2 Challenge.............................. 5 1.3 Contribution............................. 9 1.4 ThesisOrganization......................... 10 2 Platform-aware Filter Pruning 13 2.1 Related Work ............................ 13 2.1.1 FilterPruning........................ 13 2.1.2 Platform-based Network Optimization . . . . . . . . . . . 15 2.1.3 Deep Generative Models.................. 16 2.1.4 Searching Algorithm.................... 18 3 Proposed Method 21 3.1 Preliminary ............................. 23 3.2 Platform-awareArchitectureGenerator. . . . . . . . . . . . . . . 24 3.3 ArchitectureSearch......................... 27 4 Experiments 33 4.1 ArchitectureGenerator ....................... 33 4.1.1 ImplementationDetails................... 33 4.1.2 Evaluation ......................... 37 4.2 Experiments............................. 38 4.2.1 ImplementationDetails................... 38 4.2.2 ResultsonMobileCPU .................. 40 4.2.3 ResultsonMobileGPU .................. 43 4.2.4 Comparison with Traditional Method . . . . . . . . . . . 45 4.3 AblationStudy ........................... 48 5 Conclusion 51 Reference 53 | |
| dc.language.iso | en | |
| dc.subject | 生成器 | zh_TW |
| dc.subject | 卷積神經網路 | zh_TW |
| dc.subject | 網路壓縮 | zh_TW |
| dc.subject | 剪枝 | zh_TW |
| dc.subject | Network compression | en |
| dc.subject | Pruning | en |
| dc.subject | Generator | en |
| dc.subject | convolutional neural network | en |
| dc.title | 基於架構生成器及搜尋進行硬體平台感知之神經網路剪枝 | zh_TW |
| dc.title | Platform-aware Network Pruning with Architecture Generator and Search | en |
| dc.date.schoolyear | 109-2 | |
| dc.description.degree | 碩士 | |
| dc.contributor.oralexamcommittee | 黃朝宗(Hsin-Tsai Liu),鄭文皇(Chih-Yang Tseng),曹昱 | |
| dc.subject.keyword | 卷積神經網路,網路壓縮,剪枝,生成器, | zh_TW |
| dc.subject.keyword | convolutional neural network,Network compression,Pruning,Generator, | en |
| dc.relation.page | 57 | |
| dc.identifier.doi | 10.6342/NTU202101554 | |
| dc.rights.note | 同意授權(全球公開) | |
| dc.date.accepted | 2021-07-30 | |
| dc.contributor.author-college | 電機資訊學院 | zh_TW |
| dc.contributor.author-dept | 電子工程學研究所 | zh_TW |
| 顯示於系所單位： | 電子工程學研究所 | |
文件中的檔案：
| 檔案 | 大小 | 格式 | |
|---|---|---|---|
| U0001-1907202101395100.pdf | 2.55 MB | Adobe PDF | 檢視/開啟 |
系統中的文件，除了特別指名其著作權條款之外，均受到著作權保護，並且保留所有的權利。