Deployed 9bcff00c with MkDocs version: 1.0.4

21858a78 · baiyfbupt · e4e5d3e0 · 21858a78 · 21858a78 · 21858a78
Showing with 293 addition and 454 deletion

index.html index.html +1 -1

model_zoo2/index.html model_zoo2/index.html +291 -452

search/search_index.json search/search_index.json +1 -1

sitemap.xml.gz sitemap.xml.gz +0 -0

未找到文件。
--- a/index.html
+++ b/index.html
@@ -298,5 +298,5 @@

 <!--
 MkDocs version : 1.0.4
-Build Date UTC : 2020-01-03 02:58:44
+Build Date UTC : 2020-01-03 03:48:30
 -->
--- a/model_zoo2/index.html
+++ b/model_zoo2/index.html
@@ -136,9 +136,7 @@
        
            <li><a class="toctree-l3" href="#11">1.1 图象分类</a></li>
        
-            <li><a class="toctree-l3" href="#121">1.2.1 目标检测</a></li>
-        
-            <li><a class="toctree-l3" href="#122">1.2.2 目标检测</a></li>
+            <li><a class="toctree-l3" href="#12">1.2 目标检测</a></li>
        
            <li><a class="toctree-l3" href="#13">1.3 图像分割</a></li>
        
@@ -217,386 +215,276 @@
 <th align="center">Model</th>
 <th align="center">Top-1/Top-5</th>
 <th align="center">模型大小（MB）</th>
+<th align="center">下载</th>
 </tr>
 </thead>
 <tbody>
 <tr>
 <td align="center">MobileNetV1 FP32</td>
-<td align="center"><a href="http://paddle-imagenet-models-name.bj.bcebos.com/MobileNetV1_pretrained.tar">70.99%/89.68%</a></td>
+<td align="center">70.99%/89.68%</td>
 <td align="center">xx</td>
+<td align="center"><a href="">下载链接</a></td>
 </tr>
 <tr>
 <td align="center">MobileNetV1 quant_post</td>
-<td align="center"></td>
-<td align="center"></td>
+<td align="center">xx%/xx%</td>
+<td align="center">xx</td>
+<td align="center"><a href="">下载链接</a></td>
 </tr>
 <tr>
 <td align="center">MobileNetV1 quant_aware</td>
-<td align="center"></td>
-<td align="center"></td>
+<td align="center">xx%/xx%</td>
+<td align="center">xx</td>
+<td align="center"><a href="">下载链接</a></td>
 </tr>
 <tr>
 <td align="center">MobileNetV2 FP32</td>
-<td align="center"><a href="https://paddle-imagenet-models-name.bj.bcebos.com/MobileNetV2_pretrained.tar">72.15%/90.65%</a></td>
+<td align="center">72.15%/90.65%</td>
 <td align="center">xx</td>
+<td align="center"><a href="">下载链接</a></td>
 </tr>
 <tr>
 <td align="center">MobileNetV2 quant_post</td>
-<td align="center"></td>
-<td align="center"></td>
+<td align="center">xx%/xx%</td>
+<td align="center">xx</td>
+<td align="center"><a href="">下载链接</a></td>
 </tr>
 <tr>
 <td align="center">MobileNetV2 quant_aware</td>
-<td align="center"></td>
-<td align="center"></td>
+<td align="center">xx%/xx%</td>
+<td align="center">xx</td>
+<td align="center"><a href="">下载链接</a></td>
 </tr>
 <tr>
 <td align="center">ResNet50 FP32</td>
-<td align="center"><a href="http://paddle-imagenet-models-name.bj.bcebos.com/ResNet50_pretrained.tar">76.50%/93.00%</a></td>
+<td align="center">76.50%/93.00%</td>
 <td align="center">xx</td>
+<td align="center"><a href="">下载链接</a></td>
 </tr>
 <tr>
 <td align="center">ResNet50 quant_post</td>
-<td align="center"></td>
-<td align="center"></td>
+<td align="center">xx%/xx%</td>
+<td align="center">xx</td>
+<td align="center"><a href="">下载链接</a></td>
 </tr>
 <tr>
 <td align="center">ResNet50 quant_aware</td>
-<td align="center"></td>
-<td align="center"></td>
+<td align="center">xx%/xx%</td>
+<td align="center">xx</td>
+<td align="center"><a href="">下载链接</a></td>
 </tr>
 </tbody>
 </table>
-<h3 id="121">1.2.1 目标检测<a class="headerlink" href="#121" title="Permanent link">#</a></h3>
+<h3 id="12">1.2 目标检测<a class="headerlink" href="#12" title="Permanent link">#</a></h3>
 <p>数据集：COCO 2017 </p>
 <table>
 <thead>
 <tr>
 <th align="center">Model</th>
-<th align="center">输入尺寸</th>
 <th align="center">Image/GPU</th>
-<th align="center">Box AP</th>
+<th align="center">输入608 Box AP</th>
+<th align="center">输入416 Box AP</th>
+<th align="center">输入320 Box AP</th>
 <th align="center">模型大小(MB)</th>
+<th align="center">下载</th>
 </tr>
 </thead>
 <tbody>
 <tr>
 <td align="center">MobileNet-V1-YOLOv3 FP32</td>
-<td align="center">608</td>
 <td align="center">8</td>
-<td align="center"><a href="https://paddlemodels.bj.bcebos.com/object_detection/yolov3_mobilenet_v1.tar">29.3</a></td>
+<td align="center">29.3</td>
+<td align="center">29.3</td>
+<td align="center">27.1</td>
 <td align="center">xx</td>
-</tr>
-<tr>
-<td align="center">MobileNet-V1-YOLOv3 FP32</td>
-<td align="center">416</td>
-<td align="center"></td>
-<td align="center"></td>
-<td align="center"></td>
-</tr>
-<tr>
-<td align="center">MobileNet-V1-YOLOv3 FP32</td>
-<td align="center">320</td>
-<td align="center"></td>
-<td align="center"></td>
-<td align="center"></td>
+<td align="center"><a href="">下载链接</a></td>
 </tr>
 <tr>
 <td align="center">MobileNet-V1-YOLOv3 quant_post</td>
-<td align="center">608</td>
-<td align="center"></td>
-<td align="center"></td>
-<td align="center"></td>
-</tr>
-<tr>
-<td align="center">MobileNet-V1-YOLOv3 quant_post</td>
-<td align="center">416</td>
-<td align="center"></td>
-<td align="center"></td>
-<td align="center"></td>
-</tr>
-<tr>
-<td align="center">MobileNet-V1-YOLOv3 quant_post</td>
-<td align="center">320</td>
-<td align="center"></td>
-<td align="center"></td>
-<td align="center"></td>
-</tr>
-<tr>
-<td align="center">MobileNet-V1-YOLOv3 quant_aware</td>
-<td align="center">608</td>
-<td align="center"></td>
-<td align="center"></td>
-<td align="center"></td>
-</tr>
-<tr>
-<td align="center">MobileNet-V1-YOLOv3 quant_aware</td>
-<td align="center">416</td>
-<td align="center"></td>
-<td align="center"></td>
-<td align="center"></td>
+<td align="center">8</td>
+<td align="center">xx</td>
+<td align="center">xx</td>
+<td align="center">xx</td>
+<td align="center">xx</td>
+<td align="center"><a href="">下载链接</a></td>
 </tr>
 <tr>
 <td align="center">MobileNet-V1-YOLOv3 quant_aware</td>
-<td align="center">320</td>
-<td align="center"></td>
-<td align="center"></td>
-<td align="center"></td>
-</tr>
-<tr>
-<td align="center">R50-dcn-YOLOv3 FP32</td>
-<td align="center">608</td>
-<td align="center"></td>
-<td align="center"><a href="https://paddlemodels.bj.bcebos.com/object_detection/yolov3_r50vd_dcn_obj365_pretrained_coco.tar">41.4</a></td>
-<td align="center"></td>
-</tr>
-<tr>
-<td align="center">R50-dcn-YOLOv3 FP32</td>
-<td align="center">416</td>
-<td align="center"></td>
-<td align="center"></td>
-<td align="center"></td>
+<td align="center">8</td>
+<td align="center">xx</td>
+<td align="center">xx</td>
+<td align="center">xx</td>
+<td align="center">xx</td>
+<td align="center"><a href="">下载链接</a></td>
 </tr>
 <tr>
 <td align="center">R50-dcn-YOLOv3 FP32</td>
-<td align="center">320</td>
-<td align="center"></td>
-<td align="center"></td>
-<td align="center"></td>
-</tr>
-<tr>
-<td align="center">R50-dcn-YOLOv3 quant_post</td>
-<td align="center">608</td>
-<td align="center"></td>
-<td align="center"></td>
-<td align="center"></td>
-</tr>
-<tr>
-<td align="center">R50-dcn-YOLOv3 quant_post</td>
-<td align="center">416</td>
-<td align="center"></td>
-<td align="center"></td>
-<td align="center"></td>
+<td align="center">8</td>
+<td align="center">41.4</td>
+<td align="center">-</td>
+<td align="center">-</td>
+<td align="center">xx</td>
+<td align="center"><a href="">下载链接</a></td>
 </tr>
 <tr>
 <td align="center">R50-dcn-YOLOv3 quant_post</td>
-<td align="center">320</td>
-<td align="center"></td>
-<td align="center"></td>
-<td align="center"></td>
-</tr>
-<tr>
-<td align="center">R50-dcn-YOLOv3 quant_aware</td>
-<td align="center">608</td>
-<td align="center"></td>
-<td align="center"></td>
-<td align="center"></td>
-</tr>
-<tr>
-<td align="center">R50-dcn-YOLOv3 quant_aware</td>
-<td align="center">416</td>
-<td align="center"></td>
-<td align="center"></td>
-<td align="center"></td>
+<td align="center">8</td>
+<td align="center">xx</td>
+<td align="center">-</td>
+<td align="center">-</td>
+<td align="center">xx</td>
+<td align="center"><a href="">下载链接</a></td>
 </tr>
 <tr>
 <td align="center">R50-dcn-YOLOv3 quant_aware</td>
-<td align="center">320</td>
-<td align="center"></td>
-<td align="center"></td>
-<td align="center"></td>
+<td align="center">8</td>
+<td align="center">xx</td>
+<td align="center">-</td>
+<td align="center">-</td>
+<td align="center">xx</td>
+<td align="center"><a href="">下载链接</a></td>
 </tr>
 </tbody>
 </table>
-<h3 id="122">1.2.2 目标检测<a class="headerlink" href="#122" title="Permanent link">#</a></h3>
-<p>数据集：COCO 2017 </p>
+<p>数据集：WIDER-FACE</p>
 <table>
 <thead>
 <tr>
 <th align="center">Model</th>
 <th align="center">Image/GPU</th>
-<th align="center">输入608 Box AP</th>
-<th>输入416 Box AP</th>
-<th>输入320 Box AP</th>
-<th align="center">模型大小(MB)</th>
+<th align="center">输入尺寸</th>
+<th align="center">Easy/Medium/Hard</th>
+<th align="center">模型大小（MB）</th>
+<th align="center">下载</th>
 </tr>
 </thead>
 <tbody>
 <tr>
-<td align="center">MobileNet-V1-YOLOv3 FP32</td>
+<td align="center">BlazeFace FP32</td>
 <td align="center">8</td>
-<td align="center"><a href="https://paddlemodels.bj.bcebos.com/object_detection/yolov3_mobilenet_v1.tar">29.3</a></td>
-<td><a href="">29.3</a></td>
-<td><a href="">27.1</a></td>
+<td align="center">640</td>
+<td align="center">0.915/0.892/0.797</td>
 <td align="center">xx</td>
+<td align="center"><a href="">下载链接</a></td>
 </tr>
 <tr>
-<td align="center">MobileNet-V1-YOLOv3 quant_post</td>
-<td align="center"></td>
-<td align="center"></td>
-<td></td>
-<td></td>
-<td align="center"></td>
-</tr>
-<tr>
-<td align="center">MobileNet-V1-YOLOv3 quant_aware</td>
-<td align="center"></td>
-<td align="center"></td>
-<td></td>
-<td></td>
-<td align="center"></td>
-</tr>
-<tr>
-<td align="center">R50-dcn-YOLOv3 FP32</td>
-<td align="center"></td>
-<td align="center"><a href="https://paddlemodels.bj.bcebos.com/object_detection/yolov3_r50vd_dcn_obj365_pretrained_coco.tar">41.4</a></td>
-<td></td>
-<td></td>
-<td align="center"></td>
-</tr>
-<tr>
-<td align="center">R50-dcn-YOLOv3 quant_post</td>
-<td align="center"></td>
-<td align="center"></td>
-<td></td>
-<td></td>
-<td align="center"></td>
-</tr>
-<tr>
-<td align="center">R50-dcn-YOLOv3 quant_aware</td>
-<td align="center"></td>
-<td align="center"></td>
-<td></td>
-<td></td>
-<td align="center"></td>
-</tr>
-</tbody>
-</table>
-<h3 id="_1"><a class="headerlink" href="#_1" title="Permanent link">#</a></h3>
-<p>数据集：WIDER-FACE</p>
-<p>评价指标：Easy/Medium/Hard mAP</p>
-<table>
-<thead>
-<tr>
-<th align="center">Model</th>
-<th align="center">输入尺寸</th>
-<th align="center">Image/GPU</th>
-<th align="center">FP32</th>
-<th align="center">离线量化</th>
-<th align="center">量化训练</th>
+<td align="center">BlazeFace quant_post</td>
+<td align="center">8</td>
+<td align="center">640</td>
+<td align="center">xx/xx/xx</td>
+<td align="center">xx</td>
+<td align="center"><a href="">下载链接</a></td>
 </tr>
-</thead>
-<tbody>
 <tr>
-<td align="center">BlazeFace</td>
-<td align="center">640</td>
+<td align="center">BlazeFace quant_aware</td>
 <td align="center">8</td>
-<td align="center"><a href="https://paddlemodels.bj.bcebos.com/object_detection/blazeface_original.tar">0.915/0.892/0.797</a></td>
-<td align="center"><a href="">xx/xx/xx</a></td>
-<td align="center"><a href="">xx/xx/xx</a></td>
+<td align="center">640</td>
+<td align="center">xx/xx/xx</td>
+<td align="center">xx</td>
+<td align="center"><a href="">下载链接</a></td>
 </tr>
 <tr>
-<td align="center">BlazeFace-Lite</td>
+<td align="center">BlazeFace-Lite FP32</td>
+<td align="center">8</td>
 <td align="center">640</td>
-<td align="center"></td>
-<td align="center"><a href="https://paddlemodels.bj.bcebos.com/object_detection/blazeface_lite.tar">0.909/0.885/0.781</a></td>
-<td align="center"></td>
-<td align="center"></td>
+<td align="center">0.909/0.885/0.781</td>
+<td align="center">xx</td>
+<td align="center"><a href="">下载链接</a></td>
 </tr>
 <tr>
-<td align="center">BlazeFace-NAS</td>
+<td align="center">BlazeFace-Lite quant_post</td>
+<td align="center">8</td>
 <td align="center">640</td>
-<td align="center"></td>
-<td align="center"><a href="https://paddlemodels.bj.bcebos.com/object_detection/blazeface_nas.tar">0.837/0.807/0.658</a></td>
-<td align="center"></td>
-<td align="center"></td>
+<td align="center">xx/xx/xx</td>
+<td align="center">xx</td>
+<td align="center"><a href="">下载链接</a></td>
 </tr>
-</tbody>
-</table>
-<p>量化前后，模型大小的变化对比如下：</p>
-<table>
-<thead>
 <tr>
-<th align="center">Model</th>
-<th align="center">FP32</th>
-<th align="center">离线量化</th>
-<th align="center">量化训练</th>
+<td align="center">BlazeFace-Lite quant_aware</td>
+<td align="center">8</td>
+<td align="center">640</td>
+<td align="center">xx/xx/xx</td>
+<td align="center">xx</td>
+<td align="center"><a href="">下载链接</a></td>
 </tr>
-</thead>
-<tbody>
 <tr>
-<td align="center">BlazeFace</td>
-<td align="center">xxM</td>
-<td align="center">xxM</td>
-<td align="center">xxM</td>
+<td align="center">BlazeFace-NAS FP32</td>
+<td align="center">8</td>
+<td align="center">640</td>
+<td align="center">0.837/0.807/0.658</td>
+<td align="center">xx</td>
+<td align="center"><a href="">下载链接</a></td>
 </tr>
 <tr>
-<td align="center">BlazeFace-Lite</td>
-<td align="center">xxM</td>
-<td align="center"></td>
-<td align="center"></td>
+<td align="center">BlazeFace-NAS quant_post</td>
+<td align="center">8</td>
+<td align="center">640</td>
+<td align="center">xx/xx/xx</td>
+<td align="center">xx</td>
+<td align="center"><a href="">下载链接</a></td>
 </tr>
 <tr>
-<td align="center">BlazeFace-NAS</td>
-<td align="center">xxM</td>
-<td align="center"></td>
-<td align="center"></td>
+<td align="center">BlazeFace-NAS quant_aware</td>
+<td align="center">8</td>
+<td align="center">640</td>
+<td align="center">xx/xx/xx</td>
+<td align="center">xx</td>
+<td align="center"><a href="">下载链接</a></td>
 </tr>
 </tbody>
 </table>
-<h3 id="_2"><a class="headerlink" href="#_2" title="Permanent link">#</a></h3>
+<h3 id="_1"><a class="headerlink" href="#_1" title="Permanent link">#</a></h3>
 <h3 id="13">1.3 图像分割<a class="headerlink" href="#13" title="Permanent link">#</a></h3>
 <p>数据集：Cityscapes</p>
 <table>
 <thead>
 <tr>
 <th align="center">Model</th>
-<th align="center">FP32 mIoU</th>
-<th align="center">离线量化 mIoU</th>
-<th align="center">量化训练 mIoU</th>
+<th align="center">mIoU</th>
+<th align="center">模型大小（MB）</th>
+<th align="center">下载</th>
 </tr>
 </thead>
 <tbody>
 <tr>
 <td align="center">DeepLabv3+/MobileNetv1</td>
-<td align="center"><a href="">63.26</a></td>
-<td align="center"><a href="">xx</a></td>
-<td align="center"><a href="">xx</a></td>
+<td align="center">63.26</td>
+<td align="center">xx</td>
+<td align="center"><a href="">下载链接</a></td>
 </tr>
 <tr>
-<td align="center">DeepLabv3+/MobileNetv2</td>
-<td align="center"><a href="https://paddleseg.bj.bcebos.com/models/mobilenet_cityscapes.tgz">69.81</a></td>
-<td align="center"></td>
-<td align="center"></td>
+<td align="center">DeepLabv3+/MobileNetv1 quant_post</td>
+<td align="center">xx</td>
+<td align="center">xx</td>
+<td align="center"><a href="">下载链接</a></td>
 </tr>
-</tbody>
-</table>
-<p>量化前后，模型大小的变化对比如下：</p>
-<table>
-<thead>
 <tr>
-<th align="center">Model</th>
-<th align="center">FP32</th>
-<th align="center">离线量化</th>
-<th align="center">量化训练</th>
+<td align="center">DeepLabv3+/MobileNetv1 quant_aware</td>
+<td align="center">xx</td>
+<td align="center">xx</td>
+<td align="center"><a href="">下载链接</a></td>
 </tr>
-</thead>
-<tbody>
 <tr>
-<td align="center">DeepLabv3+/MobileNetv1</td>
-<td align="center">xxM</td>
-<td align="center">xxM</td>
-<td align="center">xxM</td>
+<td align="center">DeepLabv3+/MobileNetv2</td>
+<td align="center">69.81</td>
+<td align="center">xx</td>
+<td align="center"><a href="">下载链接</a></td>
 </tr>
 <tr>
-<td align="center">DeepLabv3+/MobileNetv2</td>
-<td align="center">xxM</td>
-<td align="center"></td>
-<td align="center"></td>
+<td align="center">DeepLabv3+/MobileNetv2 quant_post</td>
+<td align="center">xx</td>
+<td align="center">xx</td>
+<td align="center"><a href="">下载链接</a></td>
+</tr>
+<tr>
+<td align="center">DeepLabv3+/MobileNetv2 quant_aware</td>
+<td align="center">xx</td>
+<td align="center">xx</td>
+<td align="center"><a href="">下载链接</a></td>
 </tr>
 </tbody>
 </table>
-<h3 id="_3"><a class="headerlink" href="#_3" title="Permanent link">#</a></h3>
+<h3 id="_2"><a class="headerlink" href="#_2" title="Permanent link">#</a></h3>
 <h2 id="2">2. 剪枝<a class="headerlink" href="#2" title="Permanent link">#</a></h2>
 <h3 id="21">2.1 图像分类<a class="headerlink" href="#21" title="Permanent link">#</a></h3>
 <p>数据集：ImageNet1000类</p>
@@ -605,83 +493,78 @@
 <tr>
 <th align="center">Model</th>
 <th align="center">Top-1/Top-5</th>
+<th align="center">模型大小（MB）</th>
+<th align="center">FLOPs</th>
+<th align="center">下载</th>
 </tr>
 </thead>
 <tbody>
 <tr>
 <td align="center">MobileNetV1</td>
-<td align="center"><a href="http://paddle-imagenet-models-name.bj.bcebos.com/MobileNetV1_pretrained.tar">70.99%/89.68%</a></td>
+<td align="center">70.99%/89.68%</td>
+<td align="center">xx</td>
+<td align="center">xx</td>
+<td align="center"><a href="">下载链接</a></td>
 </tr>
 <tr>
 <td align="center">MobileNetV1 uniform -50%</td>
-<td align="center"></td>
+<td align="center">xx%/xx%</td>
+<td align="center">xx</td>
+<td align="center">xx</td>
+<td align="center"><a href="">下载链接</a></td>
 </tr>
 <tr>
 <td align="center">MobileNetV1 sensitive -xx%</td>
-<td align="center"></td>
+<td align="center">xx%/xx%</td>
+<td align="center">xx</td>
+<td align="center">xx</td>
+<td align="center"><a href="">下载链接</a></td>
 </tr>
 <tr>
 <td align="center">MobileNetV2</td>
-<td align="center"><a href="https://paddle-imagenet-models-name.bj.bcebos.com/MobileNetV2_pretrained.tar">72.15%/90.65%</a></td>
+<td align="center">72.15%/90.65%</td>
+<td align="center">xx</td>
+<td align="center">xx</td>
+<td align="center"><a href="">下载链接</a></td>
 </tr>
 <tr>
 <td align="center">MobileNetV2 uniform -50%</td>
-<td align="center"></td>
+<td align="center">xx%/xx%</td>
+<td align="center">xx</td>
+<td align="center">xx</td>
+<td align="center"><a href="">下载链接</a></td>
 </tr>
 <tr>
 <td align="center">MobileNetV2 sensitive -xx%</td>
-<td align="center"></td>
+<td align="center">xx%/xx%</td>
+<td align="center">xx</td>
+<td align="center">xx</td>
+<td align="center"><a href="">下载链接</a></td>
 </tr>
 <tr>
 <td align="center">ResNet34</td>
-<td align="center"><a href="https://paddle-imagenet-models-name.bj.bcebos.com/ResNet34_pretrained.tar">74.57%/92.14%</a></td>
+<td align="center">74.57%/92.14%</td>
+<td align="center">xx</td>
+<td align="center">xx</td>
+<td align="center"><a href="">下载链接</a></td>
 </tr>
 <tr>
 <td align="center">ResNet34 uniform -50%</td>
-<td align="center"></td>
-</tr>
-<tr>
-<td align="center">ResNet34 auto -50%</td>
-<td align="center"></td>
-</tr>
-</tbody>
-</table>
-<p>剪枝前后，模型大小和计算量的变化对比如下：</p>
-<table>
-<thead>
-<tr>
-<th align="center">Model</th>
-<th align="center">baseline FLOPs</th>
-<th align="center">baseline size</th>
-<th align="center">剪枝后 FlOPs</th>
-<th align="center">剪枝后 size</th>
-</tr>
-</thead>
-<tbody>
-<tr>
-<td align="center">MobileNetV1</td>
-<td align="center">xx</td>
-<td align="center">xx</td>
+<td align="center">xx%/xx%</td>
 <td align="center">xx</td>
 <td align="center">xx</td>
+<td align="center"><a href="">下载链接</a></td>
 </tr>
 <tr>
-<td align="center">MobileNetV2</td>
+<td align="center">ResNet34 auto -50%</td>
+<td align="center">xx%/xx%</td>
 <td align="center">xx</td>
-<td align="center"></td>
-<td align="center"></td>
-<td align="center"></td>
-</tr>
-<tr>
-<td align="center">ResNet34</td>
 <td align="center">xx</td>
-<td align="center"></td>
-<td align="center"></td>
-<td align="center"></td>
+<td align="center"><a href="">下载链接</a></td>
 </tr>
 </tbody>
 </table>
-<h3 id="_4"><a class="headerlink" href="#_4" title="Permanent link">#</a></h3>
+<h3 id="_3"><a class="headerlink" href="#_3" title="Permanent link">#</a></h3>
 <h3 id="22">2.2 目标检测<a class="headerlink" href="#22" title="Permanent link">#</a></h3>
 <p>数据集：Pasacl VOC &amp; COCO 2017</p>
 <table>
@@ -689,119 +572,81 @@
 <tr>
 <th align="center">Model</th>
 <th align="center">数据集</th>
-<th align="center">输入尺寸</th>
 <th align="center">Image/GPU</th>
-<th align="center">baseline mAP</th>
-<th align="center">敏感度剪枝 mAP</th>
+<th align="center">输入608 mAP</th>
+<th align="center">输入416 mAP</th>
+<th align="center">输入320  mAP</th>
+<th align="center">模型大小（MB）</th>
+<th align="center">FLOPs</th>
+<th align="center">下载</th>
 </tr>
 </thead>
 <tbody>
 <tr>
 <td align="center">MobileNet-V1-YOLOv3</td>
 <td align="center">Pasacl VOC</td>
-<td align="center">608</td>
 <td align="center">8</td>
-<td align="center"><a href="">76.2</a></td>
-<td align="center"><a href="">77.59</a> (-50%)</td>
-</tr>
-<tr>
-<td align="center">MobileNet-V1-YOLOv3</td>
-<td align="center">Pasacl VOC</td>
-<td align="center">416</td>
-<td align="center"></td>
-<td align="center"><a href="">76.7</a></td>
-<td align="center"><a href="">xx</a></td>
+<td align="center">76.2</td>
+<td align="center">76.7</td>
+<td align="center">75.3</td>
+<td align="center">xx</td>
+<td align="center">xx</td>
+<td align="center"><a href="">下载链接</a></td>
 </tr>
 <tr>
-<td align="center">MobileNet-V1-YOLOv3</td>
+<td align="center">MobileNet-V1-YOLOv3 prune xx%</td>
 <td align="center">Pasacl VOC</td>
-<td align="center">320</td>
-<td align="center"></td>
-<td align="center"><a href="">75.2</a></td>
-<td align="center"><a href="">xx</a></td>
-</tr>
-<tr>
-<td align="center">MobileNet-V1-YOLOv3</td>
-<td align="center">COCO</td>
-<td align="center">608</td>
-<td align="center"></td>
-<td align="center"><a href="https://paddlemodels.bj.bcebos.com/object_detection/yolov3_mobilenet_v1.tar">29.3</a></td>
-<td align="center"><a href="">29.56</a> (-20%)</td>
-</tr>
-<tr>
-<td align="center">MobileNet-V1-YOLOv3</td>
-<td align="center">COCO</td>
-<td align="center">416</td>
-<td align="center"></td>
-<td align="center"><a href="">29.3</a></td>
-<td align="center"><a href="">xx</a></td>
+<td align="center">8</td>
+<td align="center">xx</td>
+<td align="center">xx</td>
+<td align="center">xx</td>
+<td align="center">xx</td>
+<td align="center">xx</td>
+<td align="center"><a href="">下载链接</a></td>
 </tr>
 <tr>
 <td align="center">MobileNet-V1-YOLOv3</td>
 <td align="center">COCO</td>
-<td align="center">320</td>
-<td align="center"></td>
-<td align="center"><a href="">27.1</a></td>
-<td align="center"><a href="">xx</a></td>
-</tr>
-<tr>
-<td align="center">R50-dcn-YOLOv3</td>
-<td align="center">COCO</td>
-<td align="center">608</td>
-<td align="center"></td>
-<td align="center"><a href="https://paddlemodels.bj.bcebos.com/object_detection/yolov3_r50vd_dcn_obj365_pretrained_coco.tar">41.4</a></td>
-<td align="center"><a href="">37.8</a> (-30%)</td>
+<td align="center">8</td>
+<td align="center">29.3</td>
+<td align="center">29.3</td>
+<td align="center">27.1</td>
+<td align="center">xx</td>
+<td align="center">xx</td>
+<td align="center"><a href="">下载链接</a></td>
 </tr>
 <tr>
-<td align="center">R50-dcn-YOLOv3</td>
+<td align="center">MobileNet-V1-YOLOv3 prune xx%</td>
 <td align="center">COCO</td>
-<td align="center">416</td>
-<td align="center"></td>
-<td align="center"></td>
-<td align="center"></td>
+<td align="center">8</td>
+<td align="center">xx</td>
+<td align="center">xx</td>
+<td align="center">xx</td>
+<td align="center">xx</td>
+<td align="center">xx</td>
+<td align="center"><a href="">下载链接</a></td>
 </tr>
 <tr>
 <td align="center">R50-dcn-YOLOv3</td>
 <td align="center">COCO</td>
-<td align="center">320</td>
-<td align="center"></td>
-<td align="center"></td>
-<td align="center"></td>
-</tr>
-</tbody>
-</table>
-<p>剪枝前后，模型大小和计算量的变化对比如下：</p>
-<table>
-<thead>
-<tr>
-<th align="center">Model</th>
-<th align="center">baseline FLOPs</th>
-<th align="center">baseline size</th>
-<th align="center">剪枝后 FlOPs</th>
-<th align="center">剪枝后 size</th>
-</tr>
-</thead>
-<tbody>
-<tr>
-<td align="center">MobileNet-V1-YOLOv3-VOC</td>
+<td align="center">8</td>
+<td align="center">41.4</td>
+<td align="center">-</td>
+<td align="center">-</td>
 <td align="center">xx</td>
-<td align="center">xxM</td>
 <td align="center">xx</td>
-<td align="center">xxM</td>
+<td align="center"><a href="">下载链接</a></td>
 </tr>
 <tr>
-<td align="center">MobileNet-V1-YOLOv3-COCO</td>
+<td align="center">R50-dcn-YOLOv3 prune xx%</td>
+<td align="center">COCO</td>
+<td align="center">8</td>
+<td align="center">xx</td>
+<td align="center">-</td>
+<td align="center">-</td>
 <td align="center">xx</td>
-<td align="center"></td>
-<td align="center"></td>
-<td align="center"></td>
-</tr>
-<tr>
-<td align="center">R50-dcn-YOLOv3-COCO</td>
 <td align="center">xx</td>
-<td align="center"></td>
-<td align="center"></td>
-<td align="center"></td>
+<td align="center"><a href="">下载链接</a></td>
 </tr>
 </tbody>
 </table>
@@ -811,36 +656,26 @@
 <thead>
 <tr>
 <th align="center">Model</th>
-<th align="center">Baseline mIoU</th>
-<th align="center">xx剪枝 mIoU</th>
+<th align="center">mIoU</th>
+<th align="center">模型大小（MB）</th>
+<th align="center">FLOPs</th>
+<th align="center">下载</th>
 </tr>
 </thead>
 <tbody>
 <tr>
 <td align="center">DeepLabv3+/MobileNetv2</td>
-<td align="center"><a href="https://paddleseg.bj.bcebos.com/models/mobilenet_cityscapes.tgz">69.81</a></td>
-<td align="center"><a href="">xx</a></td>
-</tr>
-</tbody>
-</table>
-<p>剪枝前后，模型大小和计算量的变化对比如下：</p>
-<table>
-<thead>
-<tr>
-<th align="center">Model</th>
-<th align="center">baseline FLOPs</th>
-<th align="center">baseline size</th>
-<th align="center">剪枝后 FlOPs</th>
-<th align="center">剪枝后 size</th>
+<td align="center">69.81</td>
+<td align="center">xx</td>
+<td align="center">xx</td>
+<td align="center"><a href="">下载链接</a></td>
 </tr>
-</thead>
-<tbody>
 <tr>
-<td align="center">DeepLabv3+/MobileNetv2</td>
+<td align="center">DeepLabv3+/MobileNetv2 prune xx%</td>
+<td align="center">xx</td>
 <td align="center">xx</td>
-<td align="center">xxM</td>
 <td align="center">xx</td>
-<td align="center">xxM</td>
+<td align="center"><a href="">下载链接</a></td>
 </tr>
 </tbody>
 </table>
@@ -853,24 +688,39 @@
 <tr>
 <th align="center">Model</th>
 <th align="center">baseline</th>
-<th align="center">蒸馏后</th>
+<th align="center">下载</th>
 </tr>
 </thead>
 <tbody>
 <tr>
 <td align="center">MobileNetV1</td>
-<td align="center"><a href="http://paddle-imagenet-models-name.bj.bcebos.com/MobileNetV1_pretrained.tar">70.99%/89.68%</a></td>
-<td align="center"><a href="">72.79%/90.69%</a> (teacher: ResNet50_vd<sup><a href="#trans1">1</a></sup>)</td>
+<td align="center">70.99%/89.68%</td>
+<td align="center"><a href="http://paddle-imagenet-models-name.bj.bcebos.com/MobileNetV1_pretrained.tar">下载链接</a></td>
+</tr>
+<tr>
+<td align="center">MobileNetV1 distilled (teacher: ResNet50_vd<sup><a href="#trans1">1</a></sup>)</td>
+<td align="center">72.79%/90.69%</td>
+<td align="center"><a href="">下载链接</a></td>
 </tr>
 <tr>
 <td align="center">MobileNetV2</td>
-<td align="center"><a href="https://paddle-imagenet-models-name.bj.bcebos.com/MobileNetV2_pretrained.tar">72.15%/90.65%</a></td>
-<td align="center"><a href="">74.30%/91.52%</a> (teacher: ResNet50_vd)</td>
+<td align="center">72.15%/90.65%</td>
+<td align="center"><a href="">下载链接</a></td>
+</tr>
+<tr>
+<td align="center">MobileNetV2 distilled (teacher: ResNet50_vd)</td>
+<td align="center">74.30%/91.52%</td>
+<td align="center"><a href="">下载链接</a></td>
 </tr>
 <tr>
 <td align="center">ResNet50</td>
-<td align="center"><a href="http://paddle-imagenet-models-name.bj.bcebos.com/ResNet50_pretrained.tar">76.50%/93.00%</a></td>
-<td align="center"><a href="">77.40%/93.48%</a> (teacher: ResNet101<sup><a href="#trans2">2</a></sup>)</td>
+<td align="center">76.50%/93.00%</td>
+<td align="center"><a href="">下载链接</a></td>
+</tr>
+<tr>
+<td align="center">ResNet50 distilled (teacher: ResNet101<sup><a href="#trans2">2</a></sup>)</td>
+<td align="center">77.40%/93.48%</td>
+<td align="center"><a href="">下载链接</a></td>
 </tr>
 </tbody>
 </table>
@@ -887,60 +737,49 @@
 <tr>
 <th align="center">Model</th>
 <th align="center">数据集</th>
-<th align="center">输入尺寸</th>
 <th align="center">Image/GPU</th>
-<th align="center">baseline</th>
-<th align="center">蒸馏后 mAP</th>
+<th align="center">输入640 mAP</th>
+<th align="center">输入416 mAP</th>
+<th align="center">输入320 mAP</th>
+<th align="center">下载链接</th>
 </tr>
 </thead>
 <tbody>
 <tr>
 <td align="center">MobileNet-V1-YOLOv3</td>
 <td align="center">Pasacl VOC</td>
-<td align="center">640</td>
 <td align="center">16</td>
-<td align="center"><a href="">76.2</a></td>
-<td align="center"><a href="">79.0</a> (teacher: ResNet34-YOLOv3-VOC<sup><a href="#trans3">3</a></sup>)</td>
-</tr>
-<tr>
-<td align="center">MobileNet-V1-YOLOv3</td>
-<td align="center">Pasacl VOC</td>
-<td align="center">416</td>
-<td align="center"></td>
-<td align="center"><a href="">76.7</a></td>
-<td align="center"><a href="">78.2</a></td>
+<td align="center">76.2</td>
+<td align="center">76.7</td>
+<td align="center">75.3</td>
+<td align="center"><a href="">下载链接</a></td>
 </tr>
 <tr>
-<td align="center">MobileNet-V1-YOLOv3</td>
+<td align="center">MobileNet-V1-YOLOv3 distilled (teacher: ResNet34-YOLOv3-VOC<sup><a href="#trans3">3</a></sup>)</td>
 <td align="center">Pasacl VOC</td>
-<td align="center">320</td>
-<td align="center"></td>
-<td align="center"><a href="">75.2</a></td>
-<td align="center"><a href="">75.5</a></td>
-</tr>
-<tr>
-<td align="center">MobileNet-V1-YOLOv3</td>
-<td align="center">COCO</td>
-<td align="center">640</td>
-<td align="center"></td>
-<td align="center"><a href="https://paddlemodels.bj.bcebos.com/object_detection/yolov3_mobilenet_v1.tar">29.3</a></td>
-<td align="center"><a href="">31.0</a> (teacher: ResNet34-YOLOv3-COCO<sup><a href="#trans4">4</a></sup>)</td>
+<td align="center">16</td>
+<td align="center">xx</td>
+<td align="center">xx</td>
+<td align="center">xx</td>
+<td align="center"><a href="">下载链接</a></td>
 </tr>
 <tr>
 <td align="center">MobileNet-V1-YOLOv3</td>
 <td align="center">COCO</td>
-<td align="center">416</td>
-<td align="center"></td>
-<td align="center"></td>
-<td align="center"></td>
+<td align="center">16</td>
+<td align="center">29.3</td>
+<td align="center">29.3</td>
+<td align="center">27.1</td>
+<td align="center"><a href="">下载链接</a></td>
 </tr>
 <tr>
-<td align="center">MobileNet-V1-YOLOv3</td>
+<td align="center">MobileNet-V1-YOLOv3 distilled (teacher: ResNet34-YOLOv3-COCO<sup><a href="#trans4">4</a></sup>)</td>
 <td align="center">COCO</td>
-<td align="center">320</td>
-<td align="center"></td>
-<td align="center"></td>
-<td align="center"></td>
+<td align="center">16</td>
+<td align="center">xx</td>
+<td align="center">xx</td>
+<td align="center">xx</td>
+<td align="center"><a href="">下载链接</a></td>
 </tr>
 </tbody>
 </table>

--- a/search/search_index.json
+++ b/search/search_index.json
--- a/sitemap.xml.gz
+++ b/sitemap.xml.gz