feat: add list support for XThesis
This commit is contained in:
@@ -73,6 +73,12 @@
|
||||
<span>所定义。</span>
|
||||
</paragraph>
|
||||
|
||||
<ol>
|
||||
<li><span>输入图像经过预处理模块进行归一化。</span></li>
|
||||
<li><span>特征提取网络(如</span><cref>fig:arch</cref><span>所示)提取多尺度特征。</span></li>
|
||||
<li><span>分类头根据</span><cref>eq:loss</cref><span>计算损失并输出预测结果。</span></li>
|
||||
</ol>
|
||||
|
||||
<figure label="fig:arch" caption="网络架构示意图">figures/architecture.png</figure>
|
||||
|
||||
<section2 caption="损失函数">
|
||||
@@ -112,15 +118,11 @@
|
||||
</paragraph>
|
||||
|
||||
<section2 caption="数据集">
|
||||
<paragraph>
|
||||
<span>实验采用以下数据集:</span>
|
||||
<b>CIFAR-10</b>
|
||||
<span>、</span>
|
||||
<b>CIFAR-100</b>
|
||||
<span>和</span>
|
||||
<b>ImageNet</b>
|
||||
<span>。</span>
|
||||
</paragraph>
|
||||
<ul>
|
||||
<li><b>CIFAR-10</b><span>:10 个类别,共 60,000 张 32×32 彩色图像。</span></li>
|
||||
<li><b>CIFAR-100</b><span>:100 个类别,共 60,000 张 32×32 彩色图像。</span></li>
|
||||
<li><b>ImageNet</b><span>:1,000 个类别,共约 120 万张训练图像。</span></li>
|
||||
</ul>
|
||||
</section2>
|
||||
|
||||
<section2 caption="结果分析">
|
||||
|
||||
Reference in New Issue
Block a user