[1]林大貴, (2017, Jun 15), 人工智慧、機器學習、深度學習介紹, Tensorflowkeras Blog, Available：http://tensorflowkeras.blogspot.com/2017/06/blog-post_15.html#
[2]Searle, J. R. (1980). Minds, brains, and programs. Behavioral and Brain Sciences, 3(3), 417–424. https://doi.org/10.1017/S0140525X00005756
[3]大數據文摘,(2018,Jan 24), AI 入門必備懶人包：圖解 27 種神經模型，讓你秒懂差在哪,TechOrange 科技報橘, Available：
https://buzzorange.com/techorange/2018/01/24/neural-networks-compare/
[4]Jason,(2020, Sep 13), 卷積神經網路（Convolutional Neural Networks，CNN）,隨意窩Xuite日誌, Available：
https://m.xuite.net/blog/metafun/life/589355242
[5]Jonathan Hui,(2017,Mar 5), ”Generative adversarial nets (GAN) , DCGAN, CGAN, InfoGAN” , jhui.github.io, Available:
https://jhui.github.io/2017/03/05/Generative-adversarial-models/
[6]Frank,(2021,Oct 3),激活函數, ithome, Available：
https://ithelp.ithome.com.tw/articles/10276865
[7]Henry chen,(2022,Sep 30),Day 15. 深度學習模型 - CNN（一）,ithome , Available：
https://ithelp.ithome.com.tw/articles/10301321?sc=iThelpR
[8]王鈞奕（2018）。利用卷積神經網路對空拍影像中車輛進行偵測與分類。﹝碩士論文。中原大學﹞臺灣博碩士論文知識加值系統。 https://hdl.handle.net/11296/uq75xh。[9]K. He, G. Gkioxari, P. Dollár and R. Girshick, "Mask R-CNN," 2017 IEEE International Conference on Computer Vision (ICCV), Venice, Italy, 2017, pp. 2980-2988, doi: 10.1109/ICCV.2017.322.
[10]楊道偉（2018）。基於卷積神經網路之市區道路場景自適應車輛偵測機制。﹝碩士論文。國立中央大學﹞臺灣博碩士論文知識加值系統。 https://hdl.handle.net/11296/2azb8s。[11]Shaoqing Ren and Kaiming He and Ross Girshick and Jian Sun,2015," Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks," arXiv preprint, arXiv: 1506.01497
[12]Daodanxiansheng,(2018,Oct 27),two stage、one stage的目標檢測算法,台部落, Available： https://www.twblogs.net/a/5bd3c7c82b717778ac20d716
[13]J. Redmon, S. Divvala, R. Girshick and A. Farhadi, "You Only Look Once: Unified, Real-Time Object Detection," 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Las Vegas, NV, USA, 2016, pp. 779-788, doi: 10.1109/CVPR.2016.91.
[14]呂金和（2021）。以YOLO深度學習模型應用於偵測危險物品標誌車輛。﹝碩士論文。國立宜蘭大學﹞臺灣博碩士論文知識加值系統。 https://hdl.handle.net/11296/4t7a82。[15]許鈺祥（2023）。基於YOLO深度學習應用於火災及人員安全檢測-以建築物及車輛為例。﹝碩士論文。國立成功大學﹞臺灣博碩士論文知識加值系統。 https://hdl.handle.net/11296/96s8mh。[16]S. Zhang, J. Cao, Q. Zhang, Q. Zhang, Y. Zhang and Y. Wang, "An FPGA-Based Reconfigurable CNN Accelerator for YOLO," 2020 IEEE 3rd International Conference on Electronics Technology (ICET), Chengdu, China, 2020, pp. 74-78, doi: 10.1109/ICET49382.2020.9119500.
[17]F. Bi and J. Yang, "Target Detection System Design and FPGA Implementation Based on YOLO v2 Algorithm," 2019 3rd International Conference on Imaging, Signal Processing and Communication (ICISPC), Singapore, 2019, pp. 10-14, doi: 10.1109/ICISPC.2019.8935783.
[18]J. Redmon and A. Farhadi, "YOLO9000: Better, Faster, Stronger," 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Honolulu, HI, USA, 2017, pp. 6517-6525, doi: 10.1109/CVPR.2017.690.
[19]Tsung-Yi Lin and Michael Maire and Serge Belongie and Lubomir Bourdev and Ross Girshick and James Hays and Pietro Perona and Deva Ramanan and C. Lawrence Zitnick and Piotr Dollár,2015, "Microsoft COCO: Common Objects in Context," arXiv preprint, arXiv:1405.0312
[20]Joseph Redmon and Ali Farhadi,2018,"YOLOv3: An Incremental Improvement," arXiv preprint, arXiv:1804.02767
[21]Alexey Bochkovskiy and Chien-Yao Wang and Hong-Yuan Mark Liao,2020, "YOLOv4: Optimal Speed and Accuracy of Object Detection," arXiv preprint, arXiv:2004.10934
[22]ultralytics, Yolov5, GitHub, Available：https://github.com/ultralytics/yolov5
[23]Meta Platforms, PyTorch , Available：https://pytorch.org/
[24]Chuyi Li and Lulu Li and Hongliang Jiang and Kaiheng Weng and Yifei Geng and Liang Li and Zaidan Ke and Qingyuan Li and Meng Cheng and Weiqiang Nie and Yiduo Li and Bo Zhang and Yufei Liang and Linyuan Zhou and Xiaoming Xu and Xiangxiang Chu and Xiaoming Wei and Xiaolin Wei,2022,"YOLOv6: A Single-Stage Object Detection Framework for Industrial Applications," arXiv preprint, arXiv:2209.02976
[25]Chien-Yao Wang and I-Hau Yeh and Hong-Yuan Mark Liao,2021,"You Only Learn One Representation: Unified Network for Multiple Tasks," arXiv preprint, arXiv:2105.04206
[26]Chien-Yao Wang and Alexey Bochkovskiy and Hong-Yuan Mark Liao,2022, "YOLOv7: Trainable bag-of-freebies sets new state-of-the-art for real-time object detectors," arXiv preprint, arXiv:2207.02696
[27]Chien-Yao Wang and Hong-Yuan Mark Liao and I-Hau Yeh,2022,"Designing Network Design Strategies Through Gradient Path Analysis," arXiv preprint, arXiv: 2211.04800
[28]李謦伊,(2022, Dec 2),影像分割Image Segmentatio評估指標總覽, Medium, Available：
https://medium.com/ching-i/%E5%BD%B1%E5%83%8F%E5%88%86%E5%89%B2-image-segmentation-%E8%A9%95%E4%BC%B0%E6%8C%87%E6%A8%99%E7%B8%BD%E8%A6%BD-cb738fd8284e
[29]Google , Open Images V7 and Extensions , Available：
https://storage.googleapis.com/openimages/web/index.html
[30]theAIGuysCode, OIDv4_ToolKit, GitHub, Available：
https://github.com/theAIGuysCode/OIDv4_ToolKit
[31]elroye,(2018,Dec 11),數據預處理之標準化(Standardization)、歸一化(Normalization)、中心化/零均值化(Zero-centered),台部落, Available：https://www.twblogs.net/a/5c0f462ebd9eee5e41835e70
[32]LEAKYRELU, PyTorch, Available：
https://pytorch.org/docs/stable/generated/torch.nn.LeakyReLU.html
[33]RELU, PyTorch, Available：
https://pytorch.org/docs/stable/generated/torch.nn.ReLU.html#torch.nn.ReLU
[34]Lutz Roeder, Netron, Available：https://netron.app/
[35]J. Yue et al., "7.5 A 65nm 0.39-to-140.3TOPS/W 1-to-12b Unified Neural Network Processor Using Block-Circulant-Enabled Transpose-Domain Acceleration with 8.1 × Higher TOPS/mm2and 6T HBST-TRAM-Based 2D Data-Reuse Architecture," 2019 IEEE International Solid- State Circuits Conference - (ISSCC), San Francisco, CA, USA, 2019, pp. 138-140, doi: 10.1109/ISSCC.2019.8662360.
[36]Y. -C. Lu et al., "An 176.3 GOPs Object Detection CNN Accelerator Emulated in a 28nm CMOS Technology," 2021 IEEE 3rd International Conference on Artificial Intelligence Circuits and Systems (AICAS), Washington DC, DC, USA, 2021, pp. 1-4, doi: 10.1109/AICAS51828.2021.9458492.
[37]C. -C. Wang et al., "A 40.96-GOPS 196.8-mW Digital Logic Accelerator Used in DNN for Underwater Object Recognition," in IEEE Transactions on Circuits and Systems I: Regular Papers, vol. 69, no. 12, pp. 4860-4871, Dec. 2022, doi: 10.1109/TCSI.2022.3187450.
[38]Q. Song, J. Zhang, L. Sun and G. Jin, "Design and Implementation of Convolutional Neural Networks Accelerator Based on Multidie," in IEEE Access, vol. 10, pp. 91497-91508, 2022, doi: 10.1109/ACCESS.2022.3199441.