From 2b68ae333a2e1ecf0b09f56ebadbae797db50f2d Mon Sep 17 00:00:00 2001
From: baiyfbupt <me@ethanbai.com>
Date: Sat, 19 Sep 2020 16:35:54 +0800
Subject: [PATCH] refine slim readme

---
 deploy/slim/quantization/README.md    | 134 ++++++++++++++++++++-
 deploy/slim/quantization/README_en.md | 167 ++++++++++++++++++++++++++
 2 files changed, 298 insertions(+), 3 deletions(-)
 create mode 100755 deploy/slim/quantization/README_en.md

diff --git a/deploy/slim/quantization/README.md b/deploy/slim/quantization/README.md
index f7d87c83..d1aa3d71 100755
--- a/deploy/slim/quantization/README.md
+++ b/deploy/slim/quantization/README.md
@@ -1,21 +1,148 @@
 > è¿è¡Œç¤ºä¾‹å‰è¯·å…ˆå®‰è£…1.2.0æˆ–æ›´é«˜ç‰ˆæœ¬PaddleSlim
 
+
 # æ¨¡åž‹é‡åŒ–åŽ‹ç¼©æ•™ç¨‹
 
+åŽ‹ç¼©ç»“æžœï¼š
+<table>
+<thead>
+  <tr>
+    <th>åºå·</th>
+    <th>ä»»åŠ¡</th>
+    <th>æ¨¡åž‹</th>
+    <th>åŽ‹ç¼©ç–ç•¥</th>
+    <th>ç²¾åº¦(è‡ªå»ºä¸æ–‡æ•°æ®é›†)</th>
+    <th>è€—æ—¶(ms)</th>
+    <th>æ•´ä½“è€—æ—¶(ms)</th>
+    <th>åŠ é€Ÿæ¯”</th>
+    <th>æ•´ä½“æ¨¡åž‹å¤§å°(M)</th>
+    <th>åŽ‹ç¼©æ¯”ä¾‹</th>
+    <th>ä¸‹è½½é“¾æŽ¥</th>
+  </tr>
+</thead>
+<tbody>
+  <tr>
+    <td rowspan="2">0</td>
+    <td>æ£€æµ‹</td>
+    <td>MobileNetV3_DB</td>
+    <td>æ— </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>è¯†åˆ«</td>
+    <td>MobileNetV3_CRNN</td>
+    <td>æ— </td>
+    <td>62.0</td>
+    <td>9.52</td>
+    <td></td>
+  </tr>
+  <tr>
+    <td rowspan="2">1</td>
+    <td>æ£€æµ‹</td>
+    <td>SlimTextDet</td>
+    <td>PACTé‡åŒ–è®ç»ƒ</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>è¯†åˆ«</td>
+    <td>SlimTextRec</td>
+    <td>PACTé‡åŒ–è®ç»ƒ</td>
+    <td>61.48</td>
+    <td>8.6</td>
+    <td></td>
+  </tr>
+  <tr>
+    <td rowspan="2">2</td>
+    <td>æ£€æµ‹</td>
+    <td>SlimTextDet_quat_pruning</td>
+    <td>å‰ªè£+PACTé‡åŒ–è®ç»ƒ</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>è¯†åˆ«</td>
+    <td>SlimTextRec</td>
+    <td>PACTé‡åŒ–è®ç»ƒ</td>
+    <td>61.48</td>
+    <td>8.6</td>
+    <td></td>
+  </tr>
+  <tr>
+    <td rowspan="2">3</td>
+    <td>æ£€æµ‹</td>
+    <td>SlimTextDet_pruning</td>
+    <td>å‰ªè£</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>è¯†åˆ«</td>
+    <td>SlimTextRec</td>
+    <td>PACTé‡åŒ–è®ç»ƒ</td>
+    <td>61.48</td>
+    <td>8.6</td>
+    <td></td>
+  </tr>
+</tbody>
+</table>
+
+
+
 ## æ¦‚è¿°
 
+å¤æ‚çš„æ¨¡åž‹æœ‰åˆ©äºŽæé«˜æ¨¡åž‹çš„æ€§èƒ½ï¼Œä½†ä¹Ÿå¯¼è‡´æ¨¡åž‹ä¸å˜åœ¨ä¸€å®šå†—ä½™ï¼Œæ¨¡åž‹é‡åŒ–å°†å…¨ç²¾åº¦ç¼©å‡åˆ°å®šç‚¹æ•°å‡å°‘è¿™ç§å†—ä½™ï¼Œè¾¾åˆ°å‡å°‘æ¨¡åž‹è®¡ç®—å¤æ‚åº¦ï¼Œæé«˜æ¨¡åž‹æŽ¨ç†æ€§èƒ½çš„ç›®çš„ã€‚
+
 è¯¥ç¤ºä¾‹ä½¿ç”¨PaddleSlimæä¾›çš„[é‡åŒ–åŽ‹ç¼©API](https://paddlepaddle.github.io/PaddleSlim/api/quantization_api/)å¯¹OCRæ¨¡åž‹è¿›è¡ŒåŽ‹ç¼©ã€‚
 åœ¨é˜…è¯»è¯¥ç¤ºä¾‹å‰ï¼Œå»ºè®®æ‚¨å…ˆäº†è§£ä»¥ä¸‹å†…å®¹ï¼š
 
 - [OCRæ¨¡åž‹çš„å¸¸è§„è®ç»ƒæ–¹æ³•](https://github.com/PaddlePaddle/PaddleOCR/blob/develop/doc/doc_ch/detection.md)
-- [PaddleSlimä½¿ç”¨æ–‡æ¡£](https://paddlepaddle.github.io/PaddleSlim/)
+- [PaddleSlimä½¿ç”¨æ–‡æ¡£](https://paddleslim.readthedocs.io/zh_CN/latest/index.html)
+
+
 
 ## å®‰è£…PaddleSlim
-å¯æŒ‰ç…§[PaddleSlimä½¿ç”¨æ–‡æ¡£](https://paddlepaddle.github.io/PaddleSlim/)ä¸çš„æ¥éª¤å®‰è£…PaddleSlimã€‚
 
+```bash
+git clone https://github.com/PaddlePaddle/PaddleSlim.git
+
+cd Paddleslim
+
+python setup.py install
+```
+
+
+
+## èŽ·å–é¢„è®ç»ƒæ¨¡åž‹
+
+[è¯†åˆ«é¢„è®ç»ƒæ¨¡åž‹ä¸‹è½½åœ°å€]()
+
+[æ£€æµ‹é¢„è®ç»ƒæ¨¡åž‹ä¸‹è½½åœ°å€]()
 
 
 ## é‡åŒ–è®ç»ƒ
+åŠ è½½é¢„è®ç»ƒæ¨¡åž‹åŽï¼Œåœ¨å®šä¹‰å¥½é‡åŒ–ç–ç•¥åŽå³å¯å¯¹æ¨¡åž‹è¿›è¡Œé‡åŒ–ã€‚é‡åŒ–ç›¸å…³åŠŸèƒ½çš„ä½¿ç”¨å…·ä½“ç»†èŠ‚è§ï¼š[æ¨¡åž‹é‡åŒ–](https://paddleslim.readthedocs.io/zh_CN/latest/api_cn/quantization_api.html)
 
 è¿›å…¥PaddleOCRæ ¹ç›®å½•ï¼Œé€šè¿‡ä»¥ä¸‹å‘½ä»¤å¯¹æ¨¡åž‹è¿›è¡Œé‡åŒ–ï¼š
 
@@ -25,10 +152,11 @@ python deploy/slim/quantization/quant.py -c configs/det/det_mv3_db.yml -o Global
 
 
 
+
 ## å¯¼å‡ºæ¨¡åž‹
 
 åœ¨å¾—åˆ°é‡åŒ–è®ç»ƒä¿å˜çš„æ¨¡åž‹åŽï¼Œæˆ‘ä»¬å¯ä»¥å°†å…¶å¯¼å‡ºä¸ºinference_modelï¼Œç”¨äºŽé¢„æµ‹éƒ¨ç½²ï¼š
 
 ```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
 ```
diff --git a/deploy/slim/quantization/README_en.md b/deploy/slim/quantization/README_en.md
new file mode 100755
index 00000000..4b8a2b23
--- /dev/null
+++ b/deploy/slim/quantization/README_en.md
@@ -0,0 +1,167 @@
+\> PaddleSlim 1.2.0 or higher version should be installed before runing this example.
+
+
+
+# Model compress tutorial (Quantization)
+
+Compress resultsï¼š
+<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,ï¼š
+
+
+
+- [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, seeï¼š[Model Quantization](https://paddleslim.readthedocs.io/zh_CN/latest/api_cn/quantization_api.html)
+
+Enter the PaddleOCR root directoryï¼Œperform model quantization with the following commandï¼š
+
+```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
+```
-- 
GitLab