<?xml version="1.0"?>
<feed xmlns="http://www.w3.org/2005/Atom" xml:lang="en">
	<id>https://marovi.ai/index.php?action=history&amp;feed=atom&amp;title=Translations%3AConvolutional_Neural_Networks%2F22%2Fzh</id>
	<title>Translations:Convolutional Neural Networks/22/zh - Revision history</title>
	<link rel="self" type="application/atom+xml" href="https://marovi.ai/index.php?action=history&amp;feed=atom&amp;title=Translations%3AConvolutional_Neural_Networks%2F22%2Fzh"/>
	<link rel="alternate" type="text/html" href="https://marovi.ai/index.php?title=Translations:Convolutional_Neural_Networks/22/zh&amp;action=history"/>
	<updated>2026-04-28T03:30:15Z</updated>
	<subtitle>Revision history for this page on the wiki</subtitle>
	<generator>MediaWiki 1.39.1</generator>
	<entry>
		<id>https://marovi.ai/index.php?title=Translations:Convolutional_Neural_Networks/22/zh&amp;diff=17739&amp;oldid=prev</id>
		<title>DeployBot: Batch translate Convolutional Neural Networks unit 22 → zh</title>
		<link rel="alternate" type="text/html" href="https://marovi.ai/index.php?title=Translations:Convolutional_Neural_Networks/22/zh&amp;diff=17739&amp;oldid=prev"/>
		<updated>2026-04-27T23:37:01Z</updated>

		<summary type="html">&lt;p&gt;Batch translate Convolutional Neural Networks unit 22 → zh&lt;/p&gt;
&lt;table style=&quot;background-color: #fff; color: #202122;&quot; data-mw=&quot;interface&quot;&gt;
				&lt;col class=&quot;diff-marker&quot; /&gt;
				&lt;col class=&quot;diff-content&quot; /&gt;
				&lt;col class=&quot;diff-marker&quot; /&gt;
				&lt;col class=&quot;diff-content&quot; /&gt;
				&lt;tr class=&quot;diff-title&quot; lang=&quot;en&quot;&gt;
				&lt;td colspan=&quot;2&quot; style=&quot;background-color: #fff; color: #202122; text-align: center;&quot;&gt;← Older revision&lt;/td&gt;
				&lt;td colspan=&quot;2&quot; style=&quot;background-color: #fff; color: #202122; text-align: center;&quot;&gt;Revision as of 23:37, 27 April 2026&lt;/td&gt;
				&lt;/tr&gt;&lt;tr&gt;&lt;td colspan=&quot;2&quot; class=&quot;diff-lineno&quot; id=&quot;mw-diff-left-l1&quot;&gt;Line 1:&lt;/td&gt;
&lt;td colspan=&quot;2&quot; class=&quot;diff-lineno&quot;&gt;Line 1:&lt;/td&gt;&lt;/tr&gt;
&lt;tr&gt;&lt;td class=&quot;diff-marker&quot;&gt;&lt;/td&gt;&lt;td style=&quot;background-color: #f8f9fa; color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;&quot;&gt;&lt;div&gt;{| class=&amp;quot;wikitable&amp;quot;&lt;/div&gt;&lt;/td&gt;&lt;td class=&quot;diff-marker&quot;&gt;&lt;/td&gt;&lt;td style=&quot;background-color: #f8f9fa; color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;&quot;&gt;&lt;div&gt;{| class=&amp;quot;wikitable&amp;quot;&lt;/div&gt;&lt;/td&gt;&lt;/tr&gt;
&lt;tr&gt;&lt;td class=&quot;diff-marker&quot;&gt;&lt;/td&gt;&lt;td style=&quot;background-color: #f8f9fa; color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;&quot;&gt;&lt;div&gt;|-&lt;/div&gt;&lt;/td&gt;&lt;td class=&quot;diff-marker&quot;&gt;&lt;/td&gt;&lt;td style=&quot;background-color: #f8f9fa; color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;&quot;&gt;&lt;div&gt;|-&lt;/div&gt;&lt;/td&gt;&lt;/tr&gt;
&lt;tr&gt;&lt;td class=&quot;diff-marker&quot; data-marker=&quot;−&quot;&gt;&lt;/td&gt;&lt;td style=&quot;color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #ffe49c; vertical-align: top; white-space: pre-wrap;&quot;&gt;&lt;div&gt;! 架构 !! 年份 !! &lt;del style=&quot;font-weight: bold; text-decoration: none;&quot;&gt;关键贡献 &lt;/del&gt;!! 深度&lt;/div&gt;&lt;/td&gt;&lt;td class=&quot;diff-marker&quot; data-marker=&quot;+&quot;&gt;&lt;/td&gt;&lt;td style=&quot;color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #a3d3ff; vertical-align: top; white-space: pre-wrap;&quot;&gt;&lt;div&gt;! 架构 !! 年份 !! &lt;ins style=&quot;font-weight: bold; text-decoration: none;&quot;&gt;主要贡献 &lt;/ins&gt;!! 深度&lt;/div&gt;&lt;/td&gt;&lt;/tr&gt;
&lt;tr&gt;&lt;td class=&quot;diff-marker&quot;&gt;&lt;/td&gt;&lt;td style=&quot;background-color: #f8f9fa; color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;&quot;&gt;&lt;div&gt;|-&lt;/div&gt;&lt;/td&gt;&lt;td class=&quot;diff-marker&quot;&gt;&lt;/td&gt;&lt;td style=&quot;background-color: #f8f9fa; color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;&quot;&gt;&lt;div&gt;|-&lt;/div&gt;&lt;/td&gt;&lt;/tr&gt;
&lt;tr&gt;&lt;td class=&quot;diff-marker&quot; data-marker=&quot;−&quot;&gt;&lt;/td&gt;&lt;td style=&quot;color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #ffe49c; vertical-align: top; white-space: pre-wrap;&quot;&gt;&lt;div&gt;| &amp;#039;&amp;#039;&amp;#039;LeNet-5&amp;#039;&amp;#039;&amp;#039; || 1998 || &lt;del style=&quot;font-weight: bold; text-decoration: none;&quot;&gt;开创了用于手写数字识别（MNIST）的 &lt;/del&gt;CNN || 5 层&lt;/div&gt;&lt;/td&gt;&lt;td class=&quot;diff-marker&quot; data-marker=&quot;+&quot;&gt;&lt;/td&gt;&lt;td style=&quot;color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #a3d3ff; vertical-align: top; white-space: pre-wrap;&quot;&gt;&lt;div&gt;| &amp;#039;&amp;#039;&amp;#039;LeNet-5&amp;#039;&amp;#039;&amp;#039; || 1998 || &lt;ins style=&quot;font-weight: bold; text-decoration: none;&quot;&gt;开创性地将 &lt;/ins&gt;CNN &lt;ins style=&quot;font-weight: bold; text-decoration: none;&quot;&gt;用于手写数字识别（MNIST） &lt;/ins&gt;|| 5 层&lt;/div&gt;&lt;/td&gt;&lt;/tr&gt;
&lt;tr&gt;&lt;td class=&quot;diff-marker&quot;&gt;&lt;/td&gt;&lt;td style=&quot;background-color: #f8f9fa; color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;&quot;&gt;&lt;div&gt;|-&lt;/div&gt;&lt;/td&gt;&lt;td class=&quot;diff-marker&quot;&gt;&lt;/td&gt;&lt;td style=&quot;background-color: #f8f9fa; color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;&quot;&gt;&lt;div&gt;|-&lt;/div&gt;&lt;/td&gt;&lt;/tr&gt;
&lt;tr&gt;&lt;td class=&quot;diff-marker&quot; data-marker=&quot;−&quot;&gt;&lt;/td&gt;&lt;td style=&quot;color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #ffe49c; vertical-align: top; white-space: pre-wrap;&quot;&gt;&lt;div&gt;| &amp;#039;&amp;#039;&amp;#039;AlexNet&amp;#039;&amp;#039;&amp;#039; || 2012 || 赢得 ImageNet；推广了 &lt;del style=&quot;font-weight: bold; text-decoration: none;&quot;&gt;ReLU、dropout &lt;/del&gt;和 GPU 训练 || 8 层&lt;/div&gt;&lt;/td&gt;&lt;td class=&quot;diff-marker&quot; data-marker=&quot;+&quot;&gt;&lt;/td&gt;&lt;td style=&quot;color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #a3d3ff; vertical-align: top; white-space: pre-wrap;&quot;&gt;&lt;div&gt;| &amp;#039;&amp;#039;&amp;#039;AlexNet&amp;#039;&amp;#039;&amp;#039; || 2012 || 赢得 ImageNet；推广了 &lt;ins style=&quot;font-weight: bold; text-decoration: none;&quot;&gt;ReLU、{{Term|dropout|dropout}} &lt;/ins&gt;和 GPU 训练 || 8 层&lt;/div&gt;&lt;/td&gt;&lt;/tr&gt;
&lt;tr&gt;&lt;td class=&quot;diff-marker&quot;&gt;&lt;/td&gt;&lt;td style=&quot;background-color: #f8f9fa; color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;&quot;&gt;&lt;div&gt;|-&lt;/div&gt;&lt;/td&gt;&lt;td class=&quot;diff-marker&quot;&gt;&lt;/td&gt;&lt;td style=&quot;background-color: #f8f9fa; color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;&quot;&gt;&lt;div&gt;|-&lt;/div&gt;&lt;/td&gt;&lt;/tr&gt;
&lt;tr&gt;&lt;td class=&quot;diff-marker&quot; data-marker=&quot;−&quot;&gt;&lt;/td&gt;&lt;td style=&quot;color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #ffe49c; vertical-align: top; white-space: pre-wrap;&quot;&gt;&lt;div&gt;| &amp;#039;&amp;#039;&amp;#039;VGGNet&amp;#039;&amp;#039;&amp;#039; || 2014 || &lt;del style=&quot;font-weight: bold; text-decoration: none;&quot;&gt;证明深度很重要；全程仅使用 &lt;/del&gt;&amp;lt;math&amp;gt;3 \times 3&amp;lt;/math&amp;gt; 滤波器 || 16–19 层&lt;/div&gt;&lt;/td&gt;&lt;td class=&quot;diff-marker&quot; data-marker=&quot;+&quot;&gt;&lt;/td&gt;&lt;td style=&quot;color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #a3d3ff; vertical-align: top; white-space: pre-wrap;&quot;&gt;&lt;div&gt;| &amp;#039;&amp;#039;&amp;#039;VGGNet&amp;#039;&amp;#039;&amp;#039; || 2014 || &lt;ins style=&quot;font-weight: bold; text-decoration: none;&quot;&gt;表明深度很重要；全网络仅使用 &lt;/ins&gt;&amp;lt;math&amp;gt;3 \times 3&amp;lt;/math&amp;gt; 滤波器 || 16–19 层&lt;/div&gt;&lt;/td&gt;&lt;/tr&gt;
&lt;tr&gt;&lt;td class=&quot;diff-marker&quot;&gt;&lt;/td&gt;&lt;td style=&quot;background-color: #f8f9fa; color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;&quot;&gt;&lt;div&gt;|-&lt;/div&gt;&lt;/td&gt;&lt;td class=&quot;diff-marker&quot;&gt;&lt;/td&gt;&lt;td style=&quot;background-color: #f8f9fa; color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;&quot;&gt;&lt;div&gt;|-&lt;/div&gt;&lt;/td&gt;&lt;/tr&gt;
&lt;tr&gt;&lt;td class=&quot;diff-marker&quot;&gt;&lt;/td&gt;&lt;td style=&quot;background-color: #f8f9fa; color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;&quot;&gt;&lt;div&gt;| &amp;#039;&amp;#039;&amp;#039;GoogLeNet (Inception)&amp;#039;&amp;#039;&amp;#039; || 2014 || 引入了具有并行滤波器尺寸的 inception 模块 || 22 层&lt;/div&gt;&lt;/td&gt;&lt;td class=&quot;diff-marker&quot;&gt;&lt;/td&gt;&lt;td style=&quot;background-color: #f8f9fa; color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;&quot;&gt;&lt;div&gt;| &amp;#039;&amp;#039;&amp;#039;GoogLeNet (Inception)&amp;#039;&amp;#039;&amp;#039; || 2014 || 引入了具有并行滤波器尺寸的 inception 模块 || 22 层&lt;/div&gt;&lt;/td&gt;&lt;/tr&gt;
&lt;tr&gt;&lt;td class=&quot;diff-marker&quot;&gt;&lt;/td&gt;&lt;td style=&quot;background-color: #f8f9fa; color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;&quot;&gt;&lt;div&gt;|-&lt;/div&gt;&lt;/td&gt;&lt;td class=&quot;diff-marker&quot;&gt;&lt;/td&gt;&lt;td style=&quot;background-color: #f8f9fa; color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;&quot;&gt;&lt;div&gt;|-&lt;/div&gt;&lt;/td&gt;&lt;/tr&gt;
&lt;tr&gt;&lt;td class=&quot;diff-marker&quot; data-marker=&quot;−&quot;&gt;&lt;/td&gt;&lt;td style=&quot;color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #ffe49c; vertical-align: top; white-space: pre-wrap;&quot;&gt;&lt;div&gt;| &amp;#039;&amp;#039;&amp;#039;ResNet&amp;#039;&amp;#039;&amp;#039; || 2015 || &lt;del style=&quot;font-weight: bold; text-decoration: none;&quot;&gt;引入残差连接，使非常深的网络成为可能 &lt;/del&gt;|| 50–152+ 层&lt;/div&gt;&lt;/td&gt;&lt;td class=&quot;diff-marker&quot; data-marker=&quot;+&quot;&gt;&lt;/td&gt;&lt;td style=&quot;color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #a3d3ff; vertical-align: top; white-space: pre-wrap;&quot;&gt;&lt;div&gt;| &amp;#039;&amp;#039;&amp;#039;ResNet&amp;#039;&amp;#039;&amp;#039; || 2015 || &lt;ins style=&quot;font-weight: bold; text-decoration: none;&quot;&gt;引入了残差连接，使非常深的网络成为可能 &lt;/ins&gt;|| 50–152+ 层&lt;/div&gt;&lt;/td&gt;&lt;/tr&gt;
&lt;tr&gt;&lt;td class=&quot;diff-marker&quot;&gt;&lt;/td&gt;&lt;td style=&quot;background-color: #f8f9fa; color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;&quot;&gt;&lt;div&gt;|-&lt;/div&gt;&lt;/td&gt;&lt;td class=&quot;diff-marker&quot;&gt;&lt;/td&gt;&lt;td style=&quot;background-color: #f8f9fa; color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;&quot;&gt;&lt;div&gt;|-&lt;/div&gt;&lt;/td&gt;&lt;/tr&gt;
&lt;tr&gt;&lt;td class=&quot;diff-marker&quot; data-marker=&quot;−&quot;&gt;&lt;/td&gt;&lt;td style=&quot;color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #ffe49c; vertical-align: top; white-space: pre-wrap;&quot;&gt;&lt;div&gt;| &amp;#039;&amp;#039;&amp;#039;DenseNet&amp;#039;&amp;#039;&amp;#039; || 2017 || &lt;del style=&quot;font-weight: bold; text-decoration: none;&quot;&gt;通过密集块将每一层与所有后续层相连接 &lt;/del&gt;|| 121–264 层&lt;/div&gt;&lt;/td&gt;&lt;td class=&quot;diff-marker&quot; data-marker=&quot;+&quot;&gt;&lt;/td&gt;&lt;td style=&quot;color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #a3d3ff; vertical-align: top; white-space: pre-wrap;&quot;&gt;&lt;div&gt;| &amp;#039;&amp;#039;&amp;#039;DenseNet&amp;#039;&amp;#039;&amp;#039; || 2017 || &lt;ins style=&quot;font-weight: bold; text-decoration: none;&quot;&gt;通过密集块将每一层连接到后续每一层 &lt;/ins&gt;|| 121–264 层&lt;/div&gt;&lt;/td&gt;&lt;/tr&gt;
&lt;tr&gt;&lt;td class=&quot;diff-marker&quot;&gt;&lt;/td&gt;&lt;td style=&quot;background-color: #f8f9fa; color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;&quot;&gt;&lt;div&gt;|-&lt;/div&gt;&lt;/td&gt;&lt;td class=&quot;diff-marker&quot;&gt;&lt;/td&gt;&lt;td style=&quot;background-color: #f8f9fa; color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;&quot;&gt;&lt;div&gt;|-&lt;/div&gt;&lt;/td&gt;&lt;/tr&gt;
&lt;tr&gt;&lt;td class=&quot;diff-marker&quot;&gt;&lt;/td&gt;&lt;td style=&quot;background-color: #f8f9fa; color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;&quot;&gt;&lt;div&gt;| &amp;#039;&amp;#039;&amp;#039;EfficientNet&amp;#039;&amp;#039;&amp;#039; || 2019 || 对深度、宽度和分辨率进行复合缩放 || 可变&lt;/div&gt;&lt;/td&gt;&lt;td class=&quot;diff-marker&quot;&gt;&lt;/td&gt;&lt;td style=&quot;background-color: #f8f9fa; color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;&quot;&gt;&lt;div&gt;| &amp;#039;&amp;#039;&amp;#039;EfficientNet&amp;#039;&amp;#039;&amp;#039; || 2019 || 对深度、宽度和分辨率进行复合缩放 || 可变&lt;/div&gt;&lt;/td&gt;&lt;/tr&gt;
&lt;tr&gt;&lt;td class=&quot;diff-marker&quot;&gt;&lt;/td&gt;&lt;td style=&quot;background-color: #f8f9fa; color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;&quot;&gt;&lt;div&gt;|}&lt;/div&gt;&lt;/td&gt;&lt;td class=&quot;diff-marker&quot;&gt;&lt;/td&gt;&lt;td style=&quot;background-color: #f8f9fa; color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;&quot;&gt;&lt;div&gt;|}&lt;/div&gt;&lt;/td&gt;&lt;/tr&gt;

&lt;!-- diff cache key mediawiki:diff::1.12:old-14469:rev-17739 --&gt;
&lt;/table&gt;</summary>
		<author><name>DeployBot</name></author>
	</entry>
	<entry>
		<id>https://marovi.ai/index.php?title=Translations:Convolutional_Neural_Networks/22/zh&amp;diff=14469&amp;oldid=prev</id>
		<title>DeployBot: Batch translate Convolutional Neural Networks unit 22 → zh</title>
		<link rel="alternate" type="text/html" href="https://marovi.ai/index.php?title=Translations:Convolutional_Neural_Networks/22/zh&amp;diff=14469&amp;oldid=prev"/>
		<updated>2026-04-27T21:58:54Z</updated>

		<summary type="html">&lt;p&gt;Batch translate Convolutional Neural Networks unit 22 → zh&lt;/p&gt;
&lt;table style=&quot;background-color: #fff; color: #202122;&quot; data-mw=&quot;interface&quot;&gt;
				&lt;col class=&quot;diff-marker&quot; /&gt;
				&lt;col class=&quot;diff-content&quot; /&gt;
				&lt;col class=&quot;diff-marker&quot; /&gt;
				&lt;col class=&quot;diff-content&quot; /&gt;
				&lt;tr class=&quot;diff-title&quot; lang=&quot;en&quot;&gt;
				&lt;td colspan=&quot;2&quot; style=&quot;background-color: #fff; color: #202122; text-align: center;&quot;&gt;← Older revision&lt;/td&gt;
				&lt;td colspan=&quot;2&quot; style=&quot;background-color: #fff; color: #202122; text-align: center;&quot;&gt;Revision as of 21:58, 27 April 2026&lt;/td&gt;
				&lt;/tr&gt;&lt;tr&gt;&lt;td colspan=&quot;2&quot; class=&quot;diff-lineno&quot; id=&quot;mw-diff-left-l7&quot;&gt;Line 7:&lt;/td&gt;
&lt;td colspan=&quot;2&quot; class=&quot;diff-lineno&quot;&gt;Line 7:&lt;/td&gt;&lt;/tr&gt;
&lt;tr&gt;&lt;td class=&quot;diff-marker&quot;&gt;&lt;/td&gt;&lt;td style=&quot;background-color: #f8f9fa; color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;&quot;&gt;&lt;div&gt;| &amp;#039;&amp;#039;&amp;#039;AlexNet&amp;#039;&amp;#039;&amp;#039; || 2012 || 赢得 ImageNet；推广了 ReLU、dropout 和 GPU 训练 || 8 层&lt;/div&gt;&lt;/td&gt;&lt;td class=&quot;diff-marker&quot;&gt;&lt;/td&gt;&lt;td style=&quot;background-color: #f8f9fa; color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;&quot;&gt;&lt;div&gt;| &amp;#039;&amp;#039;&amp;#039;AlexNet&amp;#039;&amp;#039;&amp;#039; || 2012 || 赢得 ImageNet；推广了 ReLU、dropout 和 GPU 训练 || 8 层&lt;/div&gt;&lt;/td&gt;&lt;/tr&gt;
&lt;tr&gt;&lt;td class=&quot;diff-marker&quot;&gt;&lt;/td&gt;&lt;td style=&quot;background-color: #f8f9fa; color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;&quot;&gt;&lt;div&gt;|-&lt;/div&gt;&lt;/td&gt;&lt;td class=&quot;diff-marker&quot;&gt;&lt;/td&gt;&lt;td style=&quot;background-color: #f8f9fa; color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;&quot;&gt;&lt;div&gt;|-&lt;/div&gt;&lt;/td&gt;&lt;/tr&gt;
&lt;tr&gt;&lt;td class=&quot;diff-marker&quot; data-marker=&quot;−&quot;&gt;&lt;/td&gt;&lt;td style=&quot;color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #ffe49c; vertical-align: top; white-space: pre-wrap;&quot;&gt;&lt;div&gt;| &amp;#039;&amp;#039;&amp;#039;VGGNet&amp;#039;&amp;#039;&amp;#039; || 2014 || &lt;del style=&quot;font-weight: bold; text-decoration: none;&quot;&gt;表明深度很重要；全程仅使用 &lt;/del&gt;&amp;lt;math&amp;gt;3 \times 3&amp;lt;/math&amp;gt; 滤波器 || 16–19 层&lt;/div&gt;&lt;/td&gt;&lt;td class=&quot;diff-marker&quot; data-marker=&quot;+&quot;&gt;&lt;/td&gt;&lt;td style=&quot;color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #a3d3ff; vertical-align: top; white-space: pre-wrap;&quot;&gt;&lt;div&gt;| &amp;#039;&amp;#039;&amp;#039;VGGNet&amp;#039;&amp;#039;&amp;#039; || 2014 || &lt;ins style=&quot;font-weight: bold; text-decoration: none;&quot;&gt;证明深度很重要；全程仅使用 &lt;/ins&gt;&amp;lt;math&amp;gt;3 \times 3&amp;lt;/math&amp;gt; 滤波器 || 16–19 层&lt;/div&gt;&lt;/td&gt;&lt;/tr&gt;
&lt;tr&gt;&lt;td class=&quot;diff-marker&quot;&gt;&lt;/td&gt;&lt;td style=&quot;background-color: #f8f9fa; color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;&quot;&gt;&lt;div&gt;|-&lt;/div&gt;&lt;/td&gt;&lt;td class=&quot;diff-marker&quot;&gt;&lt;/td&gt;&lt;td style=&quot;background-color: #f8f9fa; color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;&quot;&gt;&lt;div&gt;|-&lt;/div&gt;&lt;/td&gt;&lt;/tr&gt;
&lt;tr&gt;&lt;td class=&quot;diff-marker&quot;&gt;&lt;/td&gt;&lt;td style=&quot;background-color: #f8f9fa; color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;&quot;&gt;&lt;div&gt;| &amp;#039;&amp;#039;&amp;#039;GoogLeNet (Inception)&amp;#039;&amp;#039;&amp;#039; || 2014 || 引入了具有并行滤波器尺寸的 inception 模块 || 22 层&lt;/div&gt;&lt;/td&gt;&lt;td class=&quot;diff-marker&quot;&gt;&lt;/td&gt;&lt;td style=&quot;background-color: #f8f9fa; color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;&quot;&gt;&lt;div&gt;| &amp;#039;&amp;#039;&amp;#039;GoogLeNet (Inception)&amp;#039;&amp;#039;&amp;#039; || 2014 || 引入了具有并行滤波器尺寸的 inception 模块 || 22 层&lt;/div&gt;&lt;/td&gt;&lt;/tr&gt;
&lt;tr&gt;&lt;td class=&quot;diff-marker&quot;&gt;&lt;/td&gt;&lt;td style=&quot;background-color: #f8f9fa; color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;&quot;&gt;&lt;div&gt;|-&lt;/div&gt;&lt;/td&gt;&lt;td class=&quot;diff-marker&quot;&gt;&lt;/td&gt;&lt;td style=&quot;background-color: #f8f9fa; color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;&quot;&gt;&lt;div&gt;|-&lt;/div&gt;&lt;/td&gt;&lt;/tr&gt;
&lt;tr&gt;&lt;td class=&quot;diff-marker&quot; data-marker=&quot;−&quot;&gt;&lt;/td&gt;&lt;td style=&quot;color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #ffe49c; vertical-align: top; white-space: pre-wrap;&quot;&gt;&lt;div&gt;| &amp;#039;&amp;#039;&amp;#039;ResNet&amp;#039;&amp;#039;&amp;#039; || 2015 || &lt;del style=&quot;font-weight: bold; text-decoration: none;&quot;&gt;引入残差连接，使训练非常深的网络成为可能 &lt;/del&gt;|| 50–152+ 层&lt;/div&gt;&lt;/td&gt;&lt;td class=&quot;diff-marker&quot; data-marker=&quot;+&quot;&gt;&lt;/td&gt;&lt;td style=&quot;color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #a3d3ff; vertical-align: top; white-space: pre-wrap;&quot;&gt;&lt;div&gt;| &amp;#039;&amp;#039;&amp;#039;ResNet&amp;#039;&amp;#039;&amp;#039; || 2015 || &lt;ins style=&quot;font-weight: bold; text-decoration: none;&quot;&gt;引入残差连接，使非常深的网络成为可能 &lt;/ins&gt;|| 50–152+ 层&lt;/div&gt;&lt;/td&gt;&lt;/tr&gt;
&lt;tr&gt;&lt;td class=&quot;diff-marker&quot;&gt;&lt;/td&gt;&lt;td style=&quot;background-color: #f8f9fa; color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;&quot;&gt;&lt;div&gt;|-&lt;/div&gt;&lt;/td&gt;&lt;td class=&quot;diff-marker&quot;&gt;&lt;/td&gt;&lt;td style=&quot;background-color: #f8f9fa; color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;&quot;&gt;&lt;div&gt;|-&lt;/div&gt;&lt;/td&gt;&lt;/tr&gt;
&lt;tr&gt;&lt;td class=&quot;diff-marker&quot; data-marker=&quot;−&quot;&gt;&lt;/td&gt;&lt;td style=&quot;color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #ffe49c; vertical-align: top; white-space: pre-wrap;&quot;&gt;&lt;div&gt;| &amp;#039;&amp;#039;&amp;#039;DenseNet&amp;#039;&amp;#039;&amp;#039; || 2017 || &lt;del style=&quot;font-weight: bold; text-decoration: none;&quot;&gt;通过密集块将每一层与之后的所有层相连 &lt;/del&gt;|| 121–264 层&lt;/div&gt;&lt;/td&gt;&lt;td class=&quot;diff-marker&quot; data-marker=&quot;+&quot;&gt;&lt;/td&gt;&lt;td style=&quot;color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #a3d3ff; vertical-align: top; white-space: pre-wrap;&quot;&gt;&lt;div&gt;| &amp;#039;&amp;#039;&amp;#039;DenseNet&amp;#039;&amp;#039;&amp;#039; || 2017 || &lt;ins style=&quot;font-weight: bold; text-decoration: none;&quot;&gt;通过密集块将每一层与所有后续层相连接 &lt;/ins&gt;|| 121–264 层&lt;/div&gt;&lt;/td&gt;&lt;/tr&gt;
&lt;tr&gt;&lt;td class=&quot;diff-marker&quot;&gt;&lt;/td&gt;&lt;td style=&quot;background-color: #f8f9fa; color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;&quot;&gt;&lt;div&gt;|-&lt;/div&gt;&lt;/td&gt;&lt;td class=&quot;diff-marker&quot;&gt;&lt;/td&gt;&lt;td style=&quot;background-color: #f8f9fa; color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;&quot;&gt;&lt;div&gt;|-&lt;/div&gt;&lt;/td&gt;&lt;/tr&gt;
&lt;tr&gt;&lt;td class=&quot;diff-marker&quot;&gt;&lt;/td&gt;&lt;td style=&quot;background-color: #f8f9fa; color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;&quot;&gt;&lt;div&gt;| &amp;#039;&amp;#039;&amp;#039;EfficientNet&amp;#039;&amp;#039;&amp;#039; || 2019 || 对深度、宽度和分辨率进行复合缩放 || 可变&lt;/div&gt;&lt;/td&gt;&lt;td class=&quot;diff-marker&quot;&gt;&lt;/td&gt;&lt;td style=&quot;background-color: #f8f9fa; color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;&quot;&gt;&lt;div&gt;| &amp;#039;&amp;#039;&amp;#039;EfficientNet&amp;#039;&amp;#039;&amp;#039; || 2019 || 对深度、宽度和分辨率进行复合缩放 || 可变&lt;/div&gt;&lt;/td&gt;&lt;/tr&gt;
&lt;tr&gt;&lt;td class=&quot;diff-marker&quot;&gt;&lt;/td&gt;&lt;td style=&quot;background-color: #f8f9fa; color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;&quot;&gt;&lt;div&gt;|}&lt;/div&gt;&lt;/td&gt;&lt;td class=&quot;diff-marker&quot;&gt;&lt;/td&gt;&lt;td style=&quot;background-color: #f8f9fa; color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;&quot;&gt;&lt;div&gt;|}&lt;/div&gt;&lt;/td&gt;&lt;/tr&gt;

&lt;!-- diff cache key mediawiki:diff::1.12:old-5740:rev-14469 --&gt;
&lt;/table&gt;</summary>
		<author><name>DeployBot</name></author>
	</entry>
	<entry>
		<id>https://marovi.ai/index.php?title=Translations:Convolutional_Neural_Networks/22/zh&amp;diff=5740&amp;oldid=prev</id>
		<title>DeployBot: Batch translate Convolutional Neural Networks unit 22 -&gt; zh</title>
		<link rel="alternate" type="text/html" href="https://marovi.ai/index.php?title=Translations:Convolutional_Neural_Networks/22/zh&amp;diff=5740&amp;oldid=prev"/>
		<updated>2026-04-27T03:51:05Z</updated>

		<summary type="html">&lt;p&gt;Batch translate Convolutional Neural Networks unit 22 -&amp;gt; zh&lt;/p&gt;
&lt;p&gt;&lt;b&gt;New page&lt;/b&gt;&lt;/p&gt;&lt;div&gt;{| class=&amp;quot;wikitable&amp;quot;&lt;br /&gt;
|-&lt;br /&gt;
! 架构 !! 年份 !! 关键贡献 !! 深度&lt;br /&gt;
|-&lt;br /&gt;
| &amp;#039;&amp;#039;&amp;#039;LeNet-5&amp;#039;&amp;#039;&amp;#039; || 1998 || 开创了用于手写数字识别（MNIST）的 CNN || 5 层&lt;br /&gt;
|-&lt;br /&gt;
| &amp;#039;&amp;#039;&amp;#039;AlexNet&amp;#039;&amp;#039;&amp;#039; || 2012 || 赢得 ImageNet；推广了 ReLU、dropout 和 GPU 训练 || 8 层&lt;br /&gt;
|-&lt;br /&gt;
| &amp;#039;&amp;#039;&amp;#039;VGGNet&amp;#039;&amp;#039;&amp;#039; || 2014 || 表明深度很重要；全程仅使用 &amp;lt;math&amp;gt;3 \times 3&amp;lt;/math&amp;gt; 滤波器 || 16–19 层&lt;br /&gt;
|-&lt;br /&gt;
| &amp;#039;&amp;#039;&amp;#039;GoogLeNet (Inception)&amp;#039;&amp;#039;&amp;#039; || 2014 || 引入了具有并行滤波器尺寸的 inception 模块 || 22 层&lt;br /&gt;
|-&lt;br /&gt;
| &amp;#039;&amp;#039;&amp;#039;ResNet&amp;#039;&amp;#039;&amp;#039; || 2015 || 引入残差连接，使训练非常深的网络成为可能 || 50–152+ 层&lt;br /&gt;
|-&lt;br /&gt;
| &amp;#039;&amp;#039;&amp;#039;DenseNet&amp;#039;&amp;#039;&amp;#039; || 2017 || 通过密集块将每一层与之后的所有层相连 || 121–264 层&lt;br /&gt;
|-&lt;br /&gt;
| &amp;#039;&amp;#039;&amp;#039;EfficientNet&amp;#039;&amp;#039;&amp;#039; || 2019 || 对深度、宽度和分辨率进行复合缩放 || 可变&lt;br /&gt;
|}&lt;/div&gt;</summary>
		<author><name>DeployBot</name></author>
	</entry>
</feed>