Skip to content

P
PaddleOCR

weixin_41840029 / PaddleOCR
与 Fork 源项目一致

Fork自 PaddlePaddle / PaddleOCR

通知 1
Star 1
Fork 0
P
PaddleOCR
未验证 提交 de5c741a 编写于 作者: D dyning 提交者： GitHub
浏览文件
操作

Merge pull request #753 from baiyfbupt/doc 

refine slim readme
上级 77cd8c1e 2b68ae33
显示空白变更内容
内联 并排
Showing with 298 addition and 3 deletion
deploy/slim/quantization/README.md
浏览文件 @ de5c741a
> 运行示例前请先安装1.2.0或更高版本PaddleSlim > 运行示例前请先安装1.2.0或更高版本PaddleSlim
# 模型量化压缩教程 # 模型量化压缩教程
压缩结果：
<table>
<thead>
<tr>
<th>序号</th>
<th>任务</th>
<th>模型</th>
<th>压缩策略</th>
<th>精度(自建中文数据集)</th>
<th>耗时(ms)</th>
<th>整体耗时(ms)</th>
<th>加速比</th>
<th>整体模型大小(M)</th>
<th>压缩比例</th>
<th>下载链接</th>
</tr>
</thead>
<tbody>
<tr>
<td rowspan="2">0</td>
<td>检测</td>
<td>MobileNetV3_DB</td>
<td>无</td>
<td>61.7</td>
<td>224</td>
<td rowspan="2">375</td>
<td rowspan="2">-</td>
<td rowspan="2">8.6</td>
<td rowspan="2">-</td>
<td></td>
</tr>
<tr>
<td>识别</td>
<td>MobileNetV3_CRNN</td>
<td>无</td>
<td>62.0</td>
<td>9.52</td>
<td></td>
</tr>
<tr>
<td rowspan="2">1</td>
<td>检测</td>
<td>SlimTextDet</td>
<td>PACT量化训练</td>
<td>62.1</td>
<td>195</td>
<td rowspan="2">348</td>
<td rowspan="2">8%</td>
<td rowspan="2">2.8</td>
<td rowspan="2">67.82%</td>
<td></td>
</tr>
<tr>
<td>识别</td>
<td>SlimTextRec</td>
<td>PACT量化训练</td>
<td>61.48</td>
<td>8.6</td>
<td></td>
</tr>
<tr>
<td rowspan="2">2</td>
<td>检测</td>
<td>SlimTextDet_quat_pruning</td>
<td>剪裁+PACT量化训练</td>
<td>60.86</td>
<td>142</td>
<td rowspan="2">288</td>
<td rowspan="2">30%</td>
<td rowspan="2">2.8</td>
<td rowspan="2">67.82%</td>
<td></td>
</tr>
<tr>
<td>识别</td>
<td>SlimTextRec</td>
<td>PACT量化训练</td>
<td>61.48</td>
<td>8.6</td>
<td></td>
</tr>
<tr>
<td rowspan="2">3</td>
<td>检测</td>
<td>SlimTextDet_pruning</td>
<td>剪裁</td>
<td>61.57</td>
<td>138</td>
<td rowspan="2">295</td>
<td rowspan="2">27%</td>
<td rowspan="2">2.9</td>
<td rowspan="2">66.28%</td>
<td></td>
</tr>
<tr>
<td>识别</td>
<td>SlimTextRec</td>
<td>PACT量化训练</td>
<td>61.48</td>
<td>8.6</td>
<td></td>
</tr>
</tbody>
</table>
## 概述 ## 概述
复杂的模型有利于提高模型的性能，但也导致模型中存在一定冗余，模型量化将全精度缩减到定点数减少这种冗余，达到减少模型计算复杂度，提高模型推理性能的目的。
该示例使用PaddleSlim提供的[量化压缩API](https://paddlepaddle.github.io/PaddleSlim/api/quantization_api/)对OCR模型进行压缩。 该示例使用PaddleSlim提供的[量化压缩API](https://paddlepaddle.github.io/PaddleSlim/api/quantization_api/)对OCR模型进行压缩。
在阅读该示例前，建议您先了解以下内容： 在阅读该示例前，建议您先了解以下内容：
- [OCR模型的常规训练方法](https://github.com/PaddlePaddle/PaddleOCR/blob/develop/doc/doc_ch/detection.md) - [OCR模型的常规训练方法](https://github.com/PaddlePaddle/PaddleOCR/blob/develop/doc/doc_ch/detection.md)
- [PaddleSlim使用文档](https://paddlepaddle.github.io/PaddleSlim/) - [PaddleSlim使用文档](https://paddleslim.readthedocs.io/zh_CN/latest/index.html)
## 安装PaddleSlim ## 安装PaddleSlim
可按照[PaddleSlim使用文档](https://paddlepaddle.github.io/PaddleSlim/)中的步骤安装PaddleSlim。
```bash
git clone https://github.com/PaddlePaddle/PaddleSlim.git
cd Paddleslim
python setup.py install
```
## 获取预训练模型
[识别预训练模型下载地址]()
[检测预训练模型下载地址]()
## 量化训练 ## 量化训练
加载预训练模型后，在定义好量化策略后即可对模型进行量化。量化相关功能的使用具体细节见：[模型量化](https://paddleslim.readthedocs.io/zh_CN/latest/api_cn/quantization_api.html)
进入PaddleOCR根目录，通过以下命令对模型进行量化： 进入PaddleOCR根目录，通过以下命令对模型进行量化：
...@@ -25,10 +152,11 @@ python deploy/slim/quantization/quant.py -c configs/det/det_mv3_db.yml -o Global ...@@ -25,10 +152,11 @@ python deploy/slim/quantization/quant.py -c configs/det/det_mv3_db.yml -o Global
## 导出模型 ## 导出模型
在得到量化训练保存的模型后，我们可以将其导出为inference_model，用于预测部署： 在得到量化训练保存的模型后，我们可以将其导出为inference_model，用于预测部署：
```bash ```bash
python deploy/slim/quantization/export_model.py -c configs/det/det_mv3_db.yml -o Global.checkpoints=output/quant_model/best_accuracy Global.save_model_dir=./output/quant_model python deploy/slim/quantization/export_model.py -c configs/det/det_mv3_db.yml -o Global.checkpoints=output/quant_model/best_accuracy Global.save_model_dir=./output/quant_inference_model
``` ```
deploy/slim/quantization/README_en.md 0 → 100755
浏览文件 @ de5c741a
\> PaddleSlim 1.2.0 or higher version should be installed before runing this example.
# Model compress tutorial (Quantization)
Compress results：
<table>
<thead>
<tr>
<th>ID</th>
<th>Task</th>
<th>Model</th>
<th>Compress Strategy</th>
<th>Criterion(Chinese dataset)</th>
<th>Inference Time(ms)</th>
<th>Inference Time(Total model)(ms)</th>
<th>Acceleration Ratio</th>
<th>Model Size(MB)</th>
<th>Commpress Ratio</th>
<th>Download Link</th>
</tr>
</thead>
<tbody>
<tr>
<td rowspan="2">0</td>
<td>Detection</td>
<td>MobileNetV3_DB</td>
<td>None</td>
<td>61.7</td>
<td>224</td>
<td rowspan="2">375</td>
<td rowspan="2">-</td>
<td rowspan="2">8.6</td>
<td rowspan="2">-</td>
<td></td>
</tr>
<tr>
<td>Recognition</td>
<td>MobileNetV3_CRNN</td>
<td>None</td>
<td>62.0</td>
<td>9.52</td>
<td></td>
</tr>
<tr>
<td rowspan="2">1</td>
<td>Detection</td>
<td>SlimTextDet</td>
<td>PACT Quant Aware Training</td>
<td>62.1</td>
<td>195</td>
<td rowspan="2">348</td>
<td rowspan="2">8%</td>
<td rowspan="2">2.8</td>
<td rowspan="2">67.82%</td>
<td></td>
</tr>
<tr>
<td>Recognition</td>
<td>SlimTextRec</td>
<td>PACT Quant Aware Training</td>
<td>61.48</td>
<td>8.6</td>
<td></td>
</tr>
<tr>
<td rowspan="2">2</td>
<td>Detection</td>
<td>SlimTextDet_quat_pruning</td>
<td>Pruning+PACT Quant Aware Training</td>
<td>60.86</td>
<td>142</td>
<td rowspan="2">288</td>
<td rowspan="2">30%</td>
<td rowspan="2">2.8</td>
<td rowspan="2">67.82%</td>
<td></td>
</tr>
<tr>
<td>Recognition</td>
<td>SlimTextRec</td>
<td>PPACT Quant Aware Training</td>
<td>61.48</td>
<td>8.6</td>
<td></td>
</tr>
<tr>
<td rowspan="2">3</td>
<td>Detection</td>
<td>SlimTextDet_pruning</td>
<td>Pruning</td>
<td>61.57</td>
<td>138</td>
<td rowspan="2">295</td>
<td rowspan="2">27%</td>
<td rowspan="2">2.9</td>
<td rowspan="2">66.28%</td>
<td></td>
</tr>
<tr>
<td>Recognition</td>
<td>SlimTextRec</td>
<td>PACT Quant Aware Training</td>
<td>61.48</td>
<td>8.6</td>
<td></td>
</tr>
</tbody>
</table>
## Overview
Generally, a more complex model would achive better performance in the task, but it also leads to some redundancy in the model. Quantization is a technique that reduces this redundancyby reducing the full precision data to a fixed number, so as to reduce model calculation complexity and improve model inference performance.
This example uses PaddleSlim provided [APIs of Quantization](https://paddlepaddle.github.io/PaddleSlim/api/quantization_api/) to compress the OCR model.
It is recommended that you could understand following pages before reading this example,：
- [The training strategy of OCR model](https://github.com/PaddlePaddle/PaddleOCR/blob/develop/doc/doc_ch/detection.md)
- [PaddleSlim Document](https://paddlepaddle.github.io/PaddleSlim/api/quantization_api/)
## Install PaddleSlim
```bash
git clone https://github.com/PaddlePaddle/PaddleSlim.git
cd Paddleslim
python setup.py install
```
## Download Pretrain Model
[Download link of Detection pretrain model]()
[Download link of recognization pretrain model]()
## Quan-Aware Training
After loading the pre training model, the model can be quantified after defining the quantization strategy. For specific details of quantization method, see：[Model Quantization](https://paddleslim.readthedocs.io/zh_CN/latest/api_cn/quantization_api.html)
Enter the PaddleOCR root directory，perform model quantization with the following command：
```bash
python deploy/slim/prune/sensitivity_anal.py -c configs/det/det_mv3_db.yml -o Global.pretrain_weights=./deploy/slim/prune/pretrain_models/det_mv3_db/best_accuracy Global.test_batch_size_per_card=1
```
## Export inference model
After getting the model after pruning and finetuning we, can export it as inference_model for predictive deployment:
```bash
python deploy/slim/quantization/export_model.py -c configs/det/det_mv3_db.yml -o Global.checkpoints=output/quant_model/best_accuracy Global.save_model_dir=./output/quant_inference_model
```
Markdown is supported
0% 或 .
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 或