https://www.cnblogs.com/darkknightzh/p/9410540.html
<div id="post_detail">
<div class="post">
<h2>
<a id="cb_post_title_url" href="https://www.cnblogs.com/darkknightzh/p/9410540.html" target="_blank" rel="external nofollow" target="_blank" rel="external nofollow" target="_blank" rel="external nofollow" >(原)MobileNetV1</a>
</h2>
<div class="postbody">
<div id="cnblogs_post_body" class="blogpost-body"><a name="_labelTop"></a><div id="navCategory"><p style="font-size:16px"><b><span style="color: #d2681e;">~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~</span></b></p><p style="font-size:24px"><b><strong><span style="color: #d2681e;">本文目录</span></strong></b></p><ul class="first_class_ul"><li><a href="#_label0" target="_blank" rel="external nofollow" >1. 深度可分离卷积</a></li><li><a href="#_label1" target="_blank" rel="external nofollow" >2. 网络结构</a></li><li><a href="#_label2" target="_blank" rel="external nofollow" >3. 宽度缩放因子(width multiplier)</a></li><li><a href="#_label3" target="_blank" rel="external nofollow" >4. 分辨率缩放因子(resolution multiplier)</a></li><li><a href="#_label4" target="_blank" rel="external nofollow" >5. pytorch代码</a></li></ul></div><p style="font-size:16px"><b><span style="color: #d2681e;">~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~</span></b></p><p>转载请注明出处:</p>
https://www.cnblogs.com/darkknightzh/p/9410540.html
论文:
MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications
网址:
https://arxiv.org/abs/1704.04861?context=cs
非官方的pytorch代码:
https://github.com/marvis/pytorch-mobilenet
回到顶部(go to top)
1. 深度可分离卷积
mobilenetV1使用的是深度可分离卷积(Depthwise Separable Convolution,DSC),DSC包含两部分:depthwise convolution(DWC)+ pointwise convolution(PWC)。DWC对输入的通道进行滤波,其不增加通道的数量,PWC用于将PWC不同的通道进行连接,其可以增加通道的数量。通过这种分解的方式,可以明显的减少计算量。
如下图所示,传统的卷积(a),卷积核参数为DK⋅DK⋅M⋅NDK⋅DK⋅M⋅N
« 上一篇: (原)Show, Attend and Translate: Unsupervised Image Translation with Self-Regularization and Attention
» 下一篇: (原)MobileNetV2
</div>
<p class="postfoot">
posted on <span id="post-date">2018-08-02 22:12</span> <a href="https://www.cnblogs.com/darkknightzh/" target="_blank" rel="external nofollow" >darkknightzh</a> 阅读(<span id="post_view_count">2750</span>) 评论(<span id="post_comment_count">0</span>) <a href="https://i.cnblogs.com/EditPosts.aspx?postid=9410540" target="_blank" rel="external nofollow" rel="nofollow">编辑</a> <a href="#" target="_blank" rel="external nofollow" target="_blank" rel="external nofollow" onclick="AddToWz(9410540);return false;">收藏</a>
</p>
</div>
<script type="text/javascript">var allowComments=true,cb_blogId=201467,cb_entryId=9410540,cb_blogApp=currentBlogApp,cb_blogUserGuid='2ff23002-a055-e411-b908-9dcfd8948a71',cb_entryCreatedDate='2018/8/2 22:12:00';loadViewCount(cb_entryId);var cb_postType=1;var isMarkdown=false;</script>
</div><a name="!comments"></a><div id="blog-comments-placeholder"></div><script type="text/javascript">var commentManager = new blogCommentManager();commentManager.renderComments(0);</script>
刷新评论 刷新页面 返回顶部 注册用户登录后才能发表评论,请 登录 或 注册, 访问网站首页。 【推荐】超50万C++/C#源码: 大型实时仿真组态图形源码
【前端】SpreadJS表格控件,可嵌入系统开发的在线Excel
【推荐】程序员问答平台,解决您开发中遇到的技术难题