淡江大學機構典藏:Item 987654321/116071
English  |  正體中文  |  简体中文  |  全文笔数/总笔数 : 55025/89277 (62%)
造访人次 : 10606121      在线人数 : 23
RC Version 7.0 © Powered By DSPACE, MIT. Enhanced by NTU Library & TKU Library IR team.
搜寻范围 查询小技巧:
  • 您可在西文检索词汇前后加上"双引号",以获取较精准的检索结果
  • 若欲以作者姓名搜寻,建议至进阶搜寻限定作者字段,可获得较完整数据
  • 进阶搜寻


    jsp.display-item.identifier=請使用永久網址來引用或連結此文件: http://tkuir.lib.tku.edu.tw:8080/dspace/handle/987654321/116071


    题名: A Study on the Convolutional Neural Algorithm of Image Style Transfer
    作者: Yang, Fu Wen;Lin, Hwei Jen;Yen, Shwu-Huey;Wang, Chun-Hui
    关键词: Max-pooling;back-propagation;style transfer;over-fitting;deep convolutional neural networks;fully convolutional networks;receptive field;kernel;merge kernel
    日期: 2018-11-05
    上传时间: 2019-03-30 12:10:48 (UTC+8)
    摘要: Recently, deep convolutional neural networks have resulted in noticeable improvements in image classification and have been used to transfer artistic style of images. Gatys et al. proposed the use of a learned Convolutional Neural Network (CNN) architecture VGG to transfer image style, but problems occur during the back propagation process because there is a heavy computational load. This paper solves these problems, including the simplification of the computation of chains of derivatives, accelerating the computation of adjustments, and efficiently choosing weights for different energy functions. The experimental results show that the proposed solutions improve the computational efficiency and render the adjustment of weights for energy functions easier.
    關聯: International Journal of Pattern Recognition and Artificial Intelligence 33(5), p.1954020
    DOI: 10.1142/S021800141954020X
    显示于类别:[資訊工程學系暨研究所] 期刊論文

    文件中的档案:

    档案 描述 大小格式浏览次数
    index.html0KbHTML40检视/开启

    在機構典藏中所有的数据项都受到原著作权保护.

    TAIR相关文章

    DSpace Software Copyright © 2002-2004  MIT &  Hewlett-Packard  /   Enhanced by   NTU Library & TKU Library IR teams. Copyright ©   - 回馈