Skip to content

P
PaddleDetection

PaddlePaddle / PaddleDetection
大约 1 年 前同步成功

通知 695
Star 11112
Fork 2696
P
PaddleDetection
切换分支/标签
查找文件 普通视图历史永久链接Permalink
README.md 13.3 KB
Newer Older
Q
Update docs (#251)  
qingqing01 已提交
1 2 3 4 5 6 7 8 9 10 11 
# 简介

在PaddleDetection, 提供了基于PaddleSlim进行模型压缩的完整教程和实验结果。详细教程请参考：

- [量化](quantization)
- [裁剪](prune)
- [蒸馏](distillation)
- [搜索](nas)

下面给出压缩的benchmark实验结果。
K
add slim model zoo (#193)  
Kaipeng Deng 已提交
12 13 14 15 16 17 18 19 20 21 
# 压缩模型库

## 测试环境

- Python 2.7.1
- PaddlePaddle >=1.6
- CUDA 9.0
- cuDNN >=7.4
- NCCL 2.1.2
K
Add distill prune demo (#210)  
Kaipeng Deng 已提交
22 
## 剪裁模型库
K
add slim model zoo (#193)  
Kaipeng Deng 已提交
23 24 25 

### 训练策略
K
fix dead link in ppdet/slim (#217)  
Kaipeng Deng 已提交
26 
- 剪裁模型训练时使用[PaddleDetection模型库](../docs/MODEL_ZOO_cn.md)发布的模型权重作为预训练权重。
K
Add distill prune demo (#210)  
Kaipeng Deng 已提交
27 28 29 
- 剪裁训练使用模型默认配置，即除`pretrained_weights`外配置不变。
- 剪裁模型全部为基于敏感度的卷积通道剪裁。
- YOLOv3模型主要剪裁`yolo_head`部分，即剪裁参数如下。
K
add slim model zoo (#193)  
Kaipeng Deng 已提交
30 31 32 33 

```
--pruned_params="yolo_block.0.0.0.conv.weights,yolo_block.0.0.1.conv.weights,yolo_block.0.1.0.conv.weights,yolo_block.0.1.1.conv.weights,yolo_block.0.2.conv.weights,yolo_block.0.tip.conv.weights,yolo_block.1.0.0.conv.weights,yolo_block.1.0.1.conv.weights,yolo_block.1.1.0.conv.weights,yolo_block.1.1.1.conv.weights,yolo_block.1.2.conv.weights,yolo_block.1.tip.conv.weights,yolo_block.2.0.0.conv.weights,yolo_block.2.0.1.conv.weights,yolo_block.2.1.0.conv.weights,yolo_block.2.1.1.conv.weights,yolo_block.2.2.conv.weights,yolo_block.2.tip.conv.weights"
```
K
Add distill prune demo (#210)  
Kaipeng Deng 已提交
34 
- YOLOv3模型剪裁中剪裁策略`r578`表示`yolo_head`中三个输出分支一次使用`0.5, 0.7, 0.8`的剪裁率剪裁，即剪裁率如下。
K
add slim model zoo (#193)  
Kaipeng Deng 已提交
35 36 37 38 39 

```
--pruned_ratios="0.5,0.5,0.5,0.5,0.5,0.5,0.7,0.7,0.7,0.7,0.7,0.7,0.8,0.8,0.8,0.8,0.8,0.8"
```
K
Add distill prune demo (#210)  
Kaipeng Deng 已提交
40 
- YOLOv3模型剪裁中剪裁策略`sensity`表示`yolo_head`中各参数剪裁率如下，该剪裁率为使用`yolov3_mobilnet_v1`模型在COCO数据集上敏感度实验分析得出。
K
add slim model zoo (#193)  
Kaipeng Deng 已提交
41 42 43 44 45 46 47 

```
--pruned_ratios="0.1,0.2,0.2,0.2,0.2,0.1,0.2,0.3,0.3,0.3,0.2,0.1,0.3,0.4,0.4,0.4,0.4,0.3"
```

### YOLOv3 on COCO
K
update prune model zoo (#232)  
Kaipeng Deng 已提交
48 49 50 51 52 53 54 55 56 57 
| 骨架网络         |  剪裁策略 | FLOPs剪裁率 | 模型体积剪裁率 | 输入尺寸 | Box AP  |                           下载                          |
| :----------------| :-------: | :---------: | :------------: | :------: | :-----: | :-----------------------------------------------------: |
| ResNet50-vd-dcn  |  sensity  |   18.41%    |     15.46%     |   608    |  39.8   | [下载链接](https://paddlemodels.bj.bcebos.com/PaddleSlim/prune/yolov3_r50vd_dcn_prune1x.tar) |
| ResNet50-vd-dcn  |   r578    |   43.69%    |     36.61%     |   608    |  38.3   | [下载链接](https://paddlemodels.bj.bcebos.com/PaddleSlim/prune/yolov3_r50vd_dcn_prune578.tar) |
| MobileNetV1      |  sensity  |   28.76%    |     28.54%     |   608    |  30.2   | [下载链接](https://paddlemodels.bj.bcebos.com/PaddleSlim/prune/yolov3_mobilenet_v1_prune1x.tar) |
| MobileNetV1      |  sensity  |   28.76%    |     28.54%     |   416    |  29.7   | [下载链接](https://paddlemodels.bj.bcebos.com/PaddleSlim/prune/yolov3_mobilenet_v1_prune1x.tar) |
| MobileNetV1      |  sensity  |   28.76%    |     28.54%     |   320    |  27.2   | [下载链接](https://paddlemodels.bj.bcebos.com/PaddleSlim/prune/yolov3_mobilenet_v1_prune1x.tar) |
| MobileNetV1      |   r578    |   67.56%    |     66.90%     |   608    |  27.8   | [下载链接](https://paddlemodels.bj.bcebos.com/PaddleSlim/prune/yolov3_mobilenet_v1_prune578.tar) |
| MobileNetV1      |   r578    |   67.56%    |     66.90%     |   416    |  26.8   | [下载链接](https://paddlemodels.bj.bcebos.com/PaddleSlim/prune/yolov3_mobilenet_v1_prune578.tar) |
| MobileNetV1      |   r578    |   67.56%    |     66.90%     |   320    |  24.0   | [下载链接](https://paddlemodels.bj.bcebos.com/PaddleSlim/prune/yolov3_mobilenet_v1_prune578.tar) |
K
add slim model zoo (#193)  
Kaipeng Deng 已提交
58 59 60 

### YOLOv3 on Pascal VOC
K
update prune model zoo (#232)  
Kaipeng Deng 已提交
61 62 63 64 65 66 67 68 
| 骨架网络         |  剪裁策略 | FLOPs剪裁率 | 模型体积剪裁率 | 输入尺寸 | Box AP  |                           下载                          |
| :----------------| :-------: | :---------: | :------------: | :------: | :-----: | :-----------------------------------------------------: |
| MobileNetV1      |  sensity  |   34.55%    |     28.75%     |   608    |  78.4   | [下载链接](https://paddlemodels.bj.bcebos.com/PaddleSlim/prune/yolov3_mobilenet_v1_voc_prune1x.tar) |
| MobileNetV1      |  sensity  |   34.55%    |     28.75%     |   416    |  78.7   | [下载链接](https://paddlemodels.bj.bcebos.com/PaddleSlim/prune/yolov3_mobilenet_v1_voc_prune1x.tar) |
| MobileNetV1      |  sensity  |   34.55%    |     28.75%     |   320    |  76.1   | [下载链接](https://paddlemodels.bj.bcebos.com/PaddleSlim/prune/yolov3_mobilenet_v1_voc_prune1x.tar) |
| MobileNetV1      |   r578    |   69.57%    |     67.00%     |   608    |  77.6   | [下载链接](https://paddlemodels.bj.bcebos.com/PaddleSlim/prune/yolov3_mobilenet_v1_voc_prune578.tar) |
| MobileNetV1      |   r578    |   69.57%    |     67.00%     |   416    |  77.7   | [下载链接](https://paddlemodels.bj.bcebos.com/PaddleSlim/prune/yolov3_mobilenet_v1_voc_prune578.tar) |
| MobileNetV1      |   r578    |   69.57%    |     67.00%     |   320    |  75.5   | [下载链接](https://paddlemodels.bj.bcebos.com/PaddleSlim/prune/yolov3_mobilenet_v1_voc_prune578.tar) |
K
add slim model zoo (#193)  
Kaipeng Deng 已提交
69
K
Add distill prune demo (#210)  
Kaipeng Deng 已提交
70 71 
### 蒸馏通道剪裁模型
K
fix dead link in ppdet/slim (#217)  
Kaipeng Deng 已提交
72 
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](./extensions/distill_pruned_model/distill_pruned_model_demo.ipynb)。
K
Add distill prune demo (#210)  
Kaipeng Deng 已提交
73 74 75 

COCO数据集上蒸馏通道剪裁模型库如下。
K
update prune model zoo (#232)  
Kaipeng Deng 已提交
76 77 78 79 80 81 
| 骨架网络         |  剪裁策略 | FLOPs剪裁率 | 模型体积剪裁率 | 输入尺寸 |      teacher模型       | Box AP  |                           下载                          |
| :----------------| :-------: | :---------: | :------------: | :------: | :--------------------- | :-----: | :-----------------------------------------------------: |
| ResNet50-vd-dcn  |   r578    |   43.69%    |     36.61%     |   608    | YOLOv3-ResNet50-vd-dcn |  39.7   | [下载链接](https://paddlemodels.bj.bcebos.com/PaddleSlim/prune/yolov3_r50vd_dcn_prune578_distill.tar) |
| MobileNetV1      |   r578    |   67.56%    |     66.90%     |   608    | YOLOv3-ResNet34        |  29.0   | [下载链接](https://paddlemodels.bj.bcebos.com/PaddleSlim/prune/yolov3_mobilenet_v1_prune578_distillby_r34.tar) |
| MobileNetV1      |   r578    |   67.56%    |     66.90%     |   416    | YOLOv3-ResNet34        |  28.0   | [下载链接](https://paddlemodels.bj.bcebos.com/PaddleSlim/prune/yolov3_mobilenet_v1_prune578_distillby_r34.tar) |
| MobileNetV1      |   r578    |   67.56%    |     66.90%     |   320    | YOLOv3-ResNet34        |  25.1   | [下载链接](https://paddlemodels.bj.bcebos.com/PaddleSlim/prune/yolov3_mobilenet_v1_prune578_distillby_r34.tar) |
K
Add distill prune demo (#210)  
Kaipeng Deng 已提交
82 83 84 

Pascal VOC数据集上蒸馏通道剪裁模型库如下。
K
update prune model zoo (#232)  
Kaipeng Deng 已提交
85 86 87 88 89 
| 骨架网络         |  剪裁策略 | FLOPs剪裁率 | 模型体积剪裁率 | 输入尺寸 |      teacher模型       | Box AP  |                           下载                          |
| :----------------| :-------: | :---------: | :------------: | :------: | :--------------------- | :-----: | :-----------------------------------------------------: |
| MobileNetV1      |   r578    |   69.57%    |     67.00%     |   608    | YOLOv3-ResNet34        |  78.8   | [下载链接](https://paddlemodels.bj.bcebos.com/PaddleSlim/prune/yolov3_mobilenet_v1_voc_prune578_distillby_r34.tar) |
| MobileNetV1      |   r578    |   69.57%    |     67.00%     |   416    | YOLOv3-ResNet34        |  78.7   | [下载链接](https://paddlemodels.bj.bcebos.com/PaddleSlim/prune/yolov3_mobilenet_v1_voc_prune578_distillby_r34.tar) |
| MobileNetV1      |   r578    |   69.57%    |     67.00%     |   320    | YOLOv3-ResNet34        |  76.3   | [下载链接](https://paddlemodels.bj.bcebos.com/PaddleSlim/prune/yolov3_mobilenet_v1_voc_prune578_distillby_r34.tar) |
K
Add distill prune demo (#210)  
Kaipeng Deng 已提交
90
K
add slim model zoo (#193)  
Kaipeng Deng 已提交
91 92 93 94 95 

## 蒸馏模型库

### 训练策略
K
fix dead link in ppdet/slim (#217)  
Kaipeng Deng 已提交
96 
- 蒸馏模型训练时teacher模型使用[PaddleDetection模型库](../docs/MODEL_ZOO_cn.md)发布的模型权重作为预训练权重。
K
add slim model zoo (#193)  
Kaipeng Deng 已提交
97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 
- 蒸馏模型训练时student模型使用backbone的预训练权重

### YOLOv3 on COCO

| 骨架网络         |    蒸馏策略   | 输入尺寸 | Box AP  |                           下载                          |
| :----------------| :-----------: | :------: |:------: | :-----------------------------------------------------: |
| MobileNetV1      | split_distiil |   608    |  31.4   | [下载链接](https://paddlemodels.bj.bcebos.com/PaddleSlim/yolov3_mobilenetv1_coco_distilled.tar) |
| MobileNetV1      | split_distiil |   416    |  30.0   | [下载链接](https://paddlemodels.bj.bcebos.com/PaddleSlim/yolov3_mobilenetv1_coco_distilled.tar) |
| MobileNetV1      | split_distiil |   320    |  27.1   | [下载链接](https://paddlemodels.bj.bcebos.com/PaddleSlim/yolov3_mobilenetv1_coco_distilled.tar) |

### YOLOv3 on Pascal VOC

| 骨架网络         |    蒸馏策略   | 输入尺寸 | Box AP  |                           下载                          |
| :----------------| :-----------: | :------: |:------: | :-----------------------------------------------------: |
| MobileNetV1      |  l2_distiil   |   608    |  79.0   | [下载链接](https://paddlemodels.bj.bcebos.com/PaddleSlim/yolov3_mobilenetv1_voc_distilled.tar) |
| MobileNetV1      |  l2_distiil   |   416    |  78.2   | [下载链接](https://paddlemodels.bj.bcebos.com/PaddleSlim/yolov3_mobilenetv1_voc_distilled.tar) |
| MobileNetV1      |  l2_distiil   |   320    |  75.5   | [下载链接](https://paddlemodels.bj.bcebos.com/PaddleSlim/yolov3_mobilenetv1_voc_distilled.tar) |

## 量化模型库

### 训练策略

- 量化策略`post`为使用离线量化得到的模型，`aware`为在线量化训练得到的模型。

### YOLOv3 on COCO

| 骨架网络         | 预训练权重 | 量化策略 | 输入尺寸 | Box AP  |                           下载                          |
| :----------------| :--------: | :------: | :------: |:------: | :-----------------------------------------------------: |
| MobileNetV1      |  ImageNet  |   post   |   608    |  27.9   | [下载链接](https://paddlemodels.bj.bcebos.com/PaddleSlim/yolov3_mobilenetv1_coco_quant_post.tar) |
| MobileNetV1      |  ImageNet  |   post   |   416    |  28.0   | [下载链接](https://paddlemodels.bj.bcebos.com/PaddleSlim/yolov3_mobilenetv1_coco_quant_post.tar) |
| MobileNetV1      |  ImageNet  |   post   |   320    |  26.0   | [下载链接](https://paddlemodels.bj.bcebos.com/PaddleSlim/yolov3_mobilenetv1_coco_quant_post.tar) |
| MobileNetV1      |  ImageNet  |  aware   |   608    |  28.1   | [下载链接](https://paddlemodels.bj.bcebos.com/PaddleSlim/yolov3_mobilenetv1_coco_quant_aware.tar) |
| MobileNetV1      |  ImageNet  |  aware   |   416    |  28.2   | [下载链接](https://paddlemodels.bj.bcebos.com/PaddleSlim/yolov3_mobilenetv1_coco_quant_aware.tar) |
| MobileNetV1      |  ImageNet  |  aware   |   320    |  25.8   | [下载链接](https://paddlemodels.bj.bcebos.com/PaddleSlim/yolov3_mobilenetv1_coco_quant_aware.tar) |
| ResNet34         |  ImageNet  |   post   |   608    |  35.7   | [下载链接](https://paddlemodels.bj.bcebos.com/PaddleSlim/yolov3_r34_coco_quant_post.tar) |
| ResNet34         |  ImageNet  |  aware   |   608    |  35.2   | [下载链接](https://paddlemodels.bj.bcebos.com/PaddleSlim/yolov3_r34_coco_quant_aware.tar) |
| ResNet34         |  ImageNet  |  aware   |   416    |  33.3   | [下载链接](https://paddlemodels.bj.bcebos.com/PaddleSlim/yolov3_r34_coco_quant_aware.tar) |
| ResNet34         |  ImageNet  |  aware   |   320    |  30.3   | [下载链接](https://paddlemodels.bj.bcebos.com/PaddleSlim/yolov3_r34_coco_quant_aware.tar) |
| R50vd-dcn        | object365  |  aware   |   608    |  40.6   | [下载链接](https://paddlemodels.bj.bcebos.com/PaddleSlim/yolov3_r50vd_dcn_obj365_pretrained_coco_quant_aware.tar) |
| R50vd-dcn        | object365  |  aware   |   416    |  37.5   | [下载链接](https://paddlemodels.bj.bcebos.com/PaddleSlim/yolov3_r50vd_dcn_obj365_pretrained_coco_quant_aware.tar) |
| R50vd-dcn        | object365  |  aware   |   320    |  34.1   | [下载链接](https://paddlemodels.bj.bcebos.com/PaddleSlim/yolov3_r50vd_dcn_obj365_pretrained_coco_quant_aware.tar) |

### BlazeFace on WIDER FACE

| 模型             | 量化策略 | 输入尺寸 | Easy Set | Medium Set | Hard Set |                           下载                          |
| :--------------- | :------: | :------: | :------: | :--------: | :------: | :-----------------------------------------------------: |
| BlazeFace        |   post   |   640    |   87.8   |    85.1    |   74.9   | [下载链接](https://paddlemodels.bj.bcebos.com/PaddleSlim/blazeface_origin_quant_post.tar) |
| BlazeFace        |  aware   |   640    |   90.5   |    87.9    |   77.6   | [下载链接](https://paddlemodels.bj.bcebos.com/PaddleSlim/blazeface_origin_quant_aware.tar) |
| BlazeFace-Lite   |   post   |   640    |   89.4   |    86.7    |   75.7   | [下载链接](https://paddlemodels.bj.bcebos.com/PaddleSlim/blazeface_lite_quant_post.tar) |
| BlazeFace-Lite   |  aware   |   640    |   89.7   |    87.3    |   77.0   | [下载链接](https://paddlemodels.bj.bcebos.com/PaddleSlim/blazeface_lite_quant_aware.tar) |
| BlazeFace-NAS    |   post   |   640    |   81.6   |    78.3    |   63.6   | [下载链接](https://paddlemodels.bj.bcebos.com/PaddleSlim/blazeface_nas_quant_post.tar) |
| BlazeFace-NAS    |  aware   |   640    |   83.1   |    79.7    |   64.2   | [下载链接](https://paddlemodels.bj.bcebos.com/PaddleSlim/blazeface_nas_quant_aware.tar) |