未验证 提交 fc56a698 编写于 作者: C ceci3 提交者: GitHub

fix dead link (#798)

上级 25ee526f
...@@ -47,7 +47,7 @@ PaddleSlim支持以下功能,也支持自定义量化、裁剪等功能。 ...@@ -47,7 +47,7 @@ PaddleSlim支持以下功能,也支持自定义量化、裁剪等功能。
<th><a href="https://github.com/PaddlePaddle/PaddleSlim/blob/release/2.0.0/docs/zh_cn/tutorials/quant/overview.md">Quantization</a></th> <th><a href="https://github.com/PaddlePaddle/PaddleSlim/blob/release/2.0.0/docs/zh_cn/tutorials/quant/overview.md">Quantization</a></th>
<th><a href="https://github.com/PaddlePaddle/PaddleSlim/blob/release/2.0.0/docs/zh_cn/tutorials/pruning/overview.md">Pruning</a></th> <th><a href="https://github.com/PaddlePaddle/PaddleSlim/blob/release/2.0.0/docs/zh_cn/tutorials/pruning/overview.md">Pruning</a></th>
<th><a href="https://github.com/PaddlePaddle/PaddleSlim/blob/release/2.0.0/docs/zh_cn/tutorials/nas/overview.md">NAS</a></th> <th><a href="https://github.com/PaddlePaddle/PaddleSlim/blob/release/2.0.0/docs/zh_cn/tutorials/nas/overview.md">NAS</a></th>
<th><a href="">Distilling</a></th> <th><a href="https://github.com/PaddlePaddle/PaddleSlim/tree/release/2.0.0/docs/zh_cn/tutorials">Distilling</a></th>
</tr> </tr>
<tr valign="top"> <tr valign="top">
<td> <td>
......
...@@ -96,7 +96,7 @@ pip install paddleslim==1.2.0 -i https://pypi.tuna.tsinghua.edu.cn/simple ...@@ -96,7 +96,7 @@ pip install paddleslim==1.2.0 -i https://pypi.tuna.tsinghua.edu.cn/simple
- [Algorithm Background](https://paddleslim.readthedocs.io/en/latest/intro_en.html): Introduce the background of quantization, pruning, distillation, NAS. - [Algorithm Background](https://paddleslim.readthedocs.io/en/latest/intro_en.html): Introduce the background of quantization, pruning, distillation, NAS.
- [PaddleDetection](https://github.com/PaddlePaddle/PaddleDetection/tree/master/slim): Introduce how to use PaddleSlim in PaddleDetection library. - [PaddleDetection](https://github.com/PaddlePaddle/PaddleDetection/tree/develop/configs/slim): Introduce how to use PaddleSlim in PaddleDetection library.
- [PaddleSeg](https://github.com/PaddlePaddle/PaddleSeg/tree/develop/slim): Introduce how to use PaddleSlim in PaddleSeg library. - [PaddleSeg](https://github.com/PaddlePaddle/PaddleSeg/tree/develop/slim): Introduce how to use PaddleSlim in PaddleSeg library.
...@@ -112,9 +112,9 @@ Dataset: ImageNet2012; Model: MobileNetV1; ...@@ -112,9 +112,9 @@ Dataset: ImageNet2012; Model: MobileNetV1;
|Method |Accuracy(baseline: 70.91%) |Model Size(baseline: 17.0M)| |Method |Accuracy(baseline: 70.91%) |Model Size(baseline: 17.0M)|
|:---:|:---:|:---:| |:---:|:---:|:---:|
| Knowledge Distillation(ResNet50)| [+1.06%]() |-| | Knowledge Distillation(ResNet50)| +1.06% |-|
| Knowledge Distillation(ResNet50) + int8 quantization |[+1.10%]()| [-71.76%]()| | Knowledge Distillation(ResNet50) + int8 quantization |+1.10%| -71.76%|
| Pruning(FLOPs-50%) + int8 quantization|[-1.71%]()|[-86.47%]()| | Pruning(FLOPs-50%) + int8 quantization|-1.71%|-86.47%|
### Object Detection ### Object Detection
...@@ -123,17 +123,17 @@ Dataset: ImageNet2012; Model: MobileNetV1; ...@@ -123,17 +123,17 @@ Dataset: ImageNet2012; Model: MobileNetV1;
| Method | mAP(baseline: 76.2%) | Model Size(baseline: 94MB) | | Method | mAP(baseline: 76.2%) | Model Size(baseline: 94MB) |
| :---------------------: | :------------: | :------------:| | :---------------------: | :------------: | :------------:|
| Knowledge Distillation(ResNet34-YOLOv3) | [+2.8%]() | - | | Knowledge Distillation(ResNet34-YOLOv3) | +2.8% | - |
| Pruning(FLOPs -52.88%) | [+1.4%]() | [-67.76%]() | | Pruning(FLOPs -52.88%) | +1.4% | -67.76% |
|Knowledge DistillationResNet34-YOLOv3)+Pruning(FLOPs-69.57%)| [+2.6%]()|[-67.00%]()| |Knowledge DistillationResNet34-YOLOv3)+Pruning(FLOPs-69.57%)| +2.6%|-67.00%|
#### Dataset: COCO; Model: MobileNet-V1-YOLOv3 #### Dataset: COCO; Model: MobileNet-V1-YOLOv3
| Method | mAP(baseline: 29.3%) | Model Size| | Method | mAP(baseline: 29.3%) | Model Size|
| :---------------------: | :------------: | :------:| | :---------------------: | :------------: | :------:|
| Knowledge Distillation(ResNet34-YOLOv3) | [+2.1%]() |-| | Knowledge Distillation(ResNet34-YOLOv3) | +2.1% |-|
| Knowledge Distillation(ResNet34-YOLOv3)+Pruning(FLOPs-67.56%) | [-0.3%]() | [-66.90%]()| | Knowledge Distillation(ResNet34-YOLOv3)+Pruning(FLOPs-67.56%) | -0.3% | -66.90%|
### NAS ### NAS
...@@ -141,6 +141,6 @@ Dataset: ImageNet2012; Model: MobileNetV2 ...@@ -141,6 +141,6 @@ Dataset: ImageNet2012; Model: MobileNetV2
|Device | Infer time cost | Top1 accuracy(baseline:71.90%) | |Device | Infer time cost | Top1 accuracy(baseline:71.90%) |
|:---------------:|:---------:|:--------------------:| |:---------------:|:---------:|:--------------------:|
| RK3288 | [-23%]() | +0.07% | | RK3288 | -23% | +0.07% |
| Android cellphone | [-20%]() | +0.16% | | Android cellphone | -20% | +0.16% |
| iPhone 6s | [-17%]() | +0.32% | | iPhone 6s | -17% | +0.32% |
...@@ -83,7 +83,7 @@ ...@@ -83,7 +83,7 @@
### 蒸馏通道剪裁模型 ### 蒸馏通道剪裁模型
可通过高精度模型蒸馏通道剪裁后模型的方式,训练方法及相关示例见[蒸馏通道剪裁模型](https://github.com/PaddlePaddle/PaddleDetection/blob/master/slim/extensions/distill_pruned_model/distill_pruned_model_demo.ipynb) 可通过高精度模型蒸馏通道剪裁后模型的方式,训练方法及相关示例见[蒸馏通道剪裁模型](https://github.com/PaddlePaddle/PaddleDetection/blob/develop/static/slim/extensions/distill_pruned_model/distill_pruned_model_demo.ipynb)
COCO数据集上蒸馏通道剪裁模型库如下。 COCO数据集上蒸馏通道剪裁模型库如下。
......
...@@ -199,7 +199,7 @@ PaddleLite版本: v2.3 ...@@ -199,7 +199,7 @@ PaddleLite版本: v2.3
| BlazeFace-NAS | - | 8 | 640 | 83.7/80.7/65.8 | 244 | 21.117 |[下载链接](https://paddlemodels.bj.bcebos.com/object_detection/blazeface_nas.tar) | | BlazeFace-NAS | - | 8 | 640 | 83.7/80.7/65.8 | 244 | 21.117 |[下载链接](https://paddlemodels.bj.bcebos.com/object_detection/blazeface_nas.tar) |
| BlazeFace-NASV2 | SANAS | 8 | 640 | 87.0/83.7/68.5 | 389 | 22.558 | [下载链接](https://paddlemodels.bj.bcebos.com/object_detection/blazeface_nas2.tar) | | BlazeFace-NASV2 | SANAS | 8 | 640 | 87.0/83.7/68.5 | 389 | 22.558 | [下载链接](https://paddlemodels.bj.bcebos.com/object_detection/blazeface_nas2.tar) |
Note: 硬件延时时间是利用提供的硬件延时表得到的,硬件延时表是在855芯片上基于PaddleLite测试的结果。BlazeFace-NASV2的详细配置在[这里](https://github.com/PaddlePaddle/PaddleDetection/blob/master/configs/face_detection/blazeface_nas_v2.yml). Note: 硬件延时时间是利用提供的硬件延时表得到的,硬件延时表是在855芯片上基于PaddleLite测试的结果。BlazeFace-NASV2的详细配置在[这里](https://github.com/PaddlePaddle/PaddleDetection/blob/release/2.1/static/configs/face_detection/blazeface_nas_v2.yml)
## 3. 图像分割 ## 3. 图像分割
......
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