卷积池化计算 深度学习

卷积后图片输出大小

W:图像宽,H:图像高,D:图像深度(通道数)
F:卷积核宽高,N:卷积核(过滤器)个数
S:步长,P:用零填充个数
卷积后输出图像大小:

                                Width=(W-F+2P)/S+1
                            Height=(H-F+2P)/S+1
  • 1
  • 2
  • 3

卷积后输出图像深度: D=N
输出图像大小: (width,height,N)
weight个数: FFD*N
bias个数: N

总结:卷积输出大小=[(输入大小-卷积核(过滤器)大小+2*P)/步长]+1
卷积中[]代表向下取整,

通用的卷积时padding 的选择
如卷积核宽高为3时 padding 选择1
如卷积核宽高为5时 padding 选择2
如卷积核宽高为7时 padding 选择3

池化后图片输出大小及个数

W:图像宽,H:图像高,D:图像深度(通道数)
F:卷积核宽高,S:步长
池化后输出图像大小:

                               W=(W-F)/S+1
                           H=(H-F)/S+1
  • 1
  • 2
  • 3

池化后输出图像深度: D=N
总结:池化输出大小=[(输入大小-卷积核(过滤器)大小)/步长]+1
池化中[]代表向上取整。
在这里插入图片描述

原文:
https://blog.csdn.net/zhongjunlang/article/details/79566422

https://blog.csdn.net/ddy_sweety/article/details/79798117

                                </div>
            <link href="https://csdnimg.cn/release/phoenix/mdeditor/markdown_views-b6c3c6d139.css" rel="stylesheet">
                                            <div class="more-toolbox">
            <div class="left-toolbox">
                <ul class="toolbox-list">
                    
                    <li class="tool-item tool-active is-like "><a href="javascript:;"><svg class="icon" aria-hidden="true">
                        <use xlink:href="#csdnc-thumbsup"></use>
                    </svg><span class="name">点赞</span>
                    <span class="count"></span>
                    </a></li>
                    <li class="tool-item tool-active is-collection "><a href="javascript:;" data-report-click="{&quot;mod&quot;:&quot;popu_824&quot;}"><svg class="icon" aria-hidden="true">
                        <use xlink:href="#icon-csdnc-Collection-G"></use>
                    </svg><span class="name">收藏</span></a></li>
                    <li class="tool-item tool-active is-share"><a href="javascript:;"><svg class="icon" aria-hidden="true">
                        <use xlink:href="#icon-csdnc-fenxiang"></use>
                    </svg>分享</a></li>
                    <!--打赏开始-->
                                            <!--打赏结束-->
                                            <li class="tool-item tool-more">
                        <a>
                        <svg t="1575545411852" class="icon" viewBox="0 0 1024 1024" version="1.1" xmlns="http://www.w3.org/2000/svg" p-id="5717" xmlns:xlink="http://www.w3.org/1999/xlink" width="200" height="200"><defs><style type="text/css"></style></defs><path d="M179.176 499.222m-113.245 0a113.245 113.245 0 1 0 226.49 0 113.245 113.245 0 1 0-226.49 0Z" p-id="5718"></path><path d="M509.684 499.222m-113.245 0a113.245 113.245 0 1 0 226.49 0 113.245 113.245 0 1 0-226.49 0Z" p-id="5719"></path><path d="M846.175 499.222m-113.245 0a113.245 113.245 0 1 0 226.49 0 113.245 113.245 0 1 0-226.49 0Z" p-id="5720"></path></svg>
                        </a>
                        <ul class="more-box">
                            <li class="item"><a class="article-report">文章举报</a></li>
                        </ul>
                    </li>
                                        </ul>
            </div>
                        </div>
        <div class="person-messagebox">
            <div class="left-message"><a href="https://blog.csdn.net/weixin_44135282">
                <img src="https://profile.csdnimg.cn/8/5/5/3_weixin_44135282" class="avatar_pic" username="weixin_44135282">
                                        <img src="https://g.csdnimg.cn/static/user-reg-year/2x/1.png" class="user-years">
                                </a></div>
            <div class="middle-message">
                                    <div class="title"><span class="tit"><a href="https://blog.csdn.net/weixin_44135282" data-report-click="{&quot;mod&quot;:&quot;popu_379&quot;}" target="_blank">ying______</a></span>
                                        </div>
                <div class="text"><span>发布了188 篇原创文章</span> · <span>获赞 23</span> · <span>访问量 2万+</span></div>
            </div>
                            <div class="right-message">
                                        <a href="https://im.csdn.net/im/main.html?userName=weixin_44135282" target="_blank" class="btn btn-sm btn-red-hollow bt-button personal-letter">私信
                    </a>
                                                        <a class="btn btn-sm  bt-button personal-watch" data-report-click="{&quot;mod&quot;:&quot;popu_379&quot;}">关注</a>
                                </div>
                        </div>
                </div>
</article>

在这里插入图片描述

发布了259 篇原创文章 · 获赞 7 · 访问量 2万+

卷积后图片输出大小

W:图像宽,H:图像高,D:图像深度(通道数)
F:卷积核宽高,N:卷积核(过滤器)个数
S:步长,P:用零填充个数
卷积后输出图像大小:

                                Width=(W-F+2P)/S+1
                            Height=(H-F+2P)/S+1

猜你喜欢

转载自blog.csdn.net/kyle1314608/article/details/104540789