提交 c2edc285 编写于 作者: B baiyfbupt

Deployed 9bcff00c with MkDocs version: 1.0.4

上级 432b38fd
......@@ -303,5 +303,5 @@
<!--
MkDocs version : 1.0.4
Build Date UTC : 2020-01-03 08:31:03
Build Date UTC : 2020-01-03 08:35:42
-->
......@@ -687,9 +687,9 @@
<p class="admonition-title">Note</p>
<p><a name="trans1">  [1]</a><a href="https://paddle-imagenet-models-name.bj.bcebos.com/ResNet50_vd_pretrained.tar">ResNet50_vd</a>预训练模型Top-1/Top-5准确率分别为79.12%/94.44%</p>
<p>带_vd后缀代表开启了Mixup训练,Mixup相关介绍参考<a href="https://arxiv.org/abs/1710.09412">mixup: Beyond Empirical Risk Minimization</a></p>
<p><a name="trans1">[2]</a><a href="https://paddle-imagenet-models-name.bj.bcebos.com/ResNet101_pretrained.tar">ResNet101</a>预训练模型Top-1/Top-5准确率分别为77.56%/93.64%</p>
<p><a name="trans1">[3]</a><a href="">ResNet34-YOLOv3-VOC</a>预训练模型的Box AP为82.6</p>
<p><a name="trans1">[4]</a><a href="">ResNet34-YOLOv3-COCO</a>预训练模型的Box AP为36.2</p>
<p><a name="trans2">[2]</a><a href="https://paddle-imagenet-models-name.bj.bcebos.com/ResNet101_pretrained.tar">ResNet101</a>预训练模型Top-1/Top-5准确率分别为77.56%/93.64%</p>
<p><a name="trans3">[3]</a><a href="">ResNet34-YOLOv3-VOC</a>预训练模型的Box AP为82.6</p>
<p><a name="trans4">[4]</a><a href="">ResNet34-YOLOv3-COCO</a>预训练模型的Box AP为36.2</p>
</div>
</div>
......
无法预览此类型文件
Markdown is supported
0% .
You are about to add 0 people to the discussion. Proceed with caution.
先完成此消息的编辑!
想要评论请 注册