PaddleOCR加载chinese_ocr_db_crnn_server模型进行中英文混合预测（命令行）实践

1. 安装相关库文件

# 安装paddlehub和paddlepaddle
pip install paddlehub -i https://pypi.tuna.tsinghua.edu.cn/simple
pip install paddlepaddle -i https://pypi.tuna.tsinghua.edu.cn/simple
# 该Module依赖于第三方库shapely、pyclipper，使用该Module之前，请先安装shapely、pyclipper
pip install shapely -i https://pypi.tuna.tsinghua.edu.cn/simple
pip install pyclipper -i https://pypi.tuna.tsinghua.edu.cn/simple

使用的是清华的源，在安装时出现过https连接池超时的问题，换个网络环境，多试几次就好了。

2. 安装预训练模型

选择的是识别精度相对较高的：chinese_ocr_db_crnn_server
命令是：hub install chinese_ocr_db_crnn_server==1.1.1

(venv) E:\test\PycharmProjects\PaddleStudy2>hub install chinese_ocr_db_crnn_server==1.1.1
e:\test\pycharmprojects\paddlestudy2\venv\lib\site-packages\pip\_vendor\packaging\version.py:127: DeprecationWarning: Creating a LegacyVersion has been deprecated and will be removed in the next major releasewarnings.warn(
e:\test\pycharmprojects\paddlestudy2\venv\lib\site-packages\pip\_vendor\packaging\version.py:127: DeprecationWarning: Creating a LegacyVersion has been deprecated and will be removed in the next major releasewarnings.warn(
2021-03-16 08:50:50,784 - INFO - Lock 601713536 acquired on C:\Users\CTH\.paddlehub\tmp\chinese_ocr_db_crnn_server
[INFO 2021-03-16 08:50:50,784 filelock.py:274] Lock 601713536 acquired on C:\Users\CTH\.paddlehub\tmp\chinese_ocr_db_crnn_server
Download https://bj.bcebos.com/paddlehub/paddlehub_dev/chinese_ocr_db_crnn_server_1.1.1.tar.gz
[##################################################] 100.00%
Decompress C:\Users\CTH\.paddlehub\tmp\tmppwvzfx_9\chinese_ocr_db_crnn_server_1.1.1.tar.gz
[##################################################] 100.00%
[2021-03-16 08:51:44,000] [    INFO] - Successfully installed chinese_ocr_db_crnn_server-1.1.1
2021-03-16 08:51:44,047 - INFO - Lock 601713536 released on C:\Users\CTH\.paddlehub\tmp\chinese_ocr_db_crnn_server
[INFO 2021-03-16 08:51:44,047 filelock.py:318] Lock 601713536 released on C:\Users\CTH\.paddlehub\tmp\chinese_ocr_db_crnn_server

对应的精简版本：chinese_ocr_db_crnn_mobile
命令是：hub install chinese_ocr_db_crnn_mobile==1.1.1

3. 命令行预测

原始图片：

命令是：hub run chinese_ocr_db_crnn_server --input_path “/PATH/TO/IMAGE”

(venv) E:\test\PycharmProjects\PaddleStudy2>hub run chinese_ocr_db_crnn_server --input_path "E:/test/PycharmProjects/PaddleStudy2/pic/0-1.jpg"
e:\test\pycharmprojects\paddlestudy2\venv\lib\site-packages\pip\_vendor\packaging\version.py:127: DeprecationWarning: Creating a LegacyVersion has been deprecated and will be removed in the next major releasewarnings.warn(
e:\test\pycharmprojects\paddlestudy2\venv\lib\site-packages\pip\_vendor\packaging\version.py:127: DeprecationWarning: Creating a LegacyVersion has been deprecated and will be removed in the next major releasewarnings.warn(
[2021-03-16 08:53:25,582] [ WARNING] - The _initialize method in HubModule will soon be deprecated, you can use the __init__() to handle the initialization of the object
W0316 08:53:25.598523 12472 analysis_predictor.cc:1145] Deprecated. Please use CreatePredictor instead.
2021-03-16 08:53:26,440 - INFO - Lock 607078624 acquired on C:\Users\CTH\.paddlehub\tmp\chinese_text_detection_db_server
[INFO 2021-03-16 08:53:26,440 filelock.py:274] Lock 607078624 acquired on C:\Users\CTH\.paddlehub\tmp\chinese_text_detection_db_server
Download https://bj.bcebos.com/paddlehub/paddlehub_dev/chinese_text_detection_db_server_1.0.2.tar.gz
[##################################################] 100.00%
Decompress C:\Users\CTH\.paddlehub\tmp\tmpvc1k5tyo\chinese_text_detection_db_server_1.0.2.tar.gz
[##################################################] 100.00%
[2021-03-16 08:53:55,071] [    INFO] - Successfully installed chinese_text_detection_db_server-1.0.2
2021-03-16 08:53:55,118 - INFO - Lock 607078624 released on C:\Users\CTH\.paddlehub\tmp\chinese_text_detection_db_server
[INFO 2021-03-16 08:53:55,118 filelock.py:318] Lock 607078624 released on C:\Users\CTH\.paddlehub\tmp\chinese_text_detection_db_server
[2021-03-16 08:53:55,118] [ WARNING] - The _initialize method in HubModule will soon be deprecated, you can use the __init__() to handle the initialization of the object
[{'save_path': '', 'data': [{'text': '双耳机配对', 'confidence': 0.9995235204696655, 'text_box_position': [[64, 63], [301, 69], [299, 119], [63, 113]]}, {'text': '首次配对方法：', 'confidence': 0.9997860193252563, 'text_box_position':
[[71, 186], [336, 194], [334, 232], [70, 225]]}, {'text': '1、取出两只耳机，再将两只耳机放回充电盒中', 'confidence': 0.9993939399719238, 'text_box_position': [[67, 245], [767, 258], [767, 297], [67, 283]]}, {'text': '（此步骤为新机激活
）', 'confidence': 0.9379152655601501, 'text_box_position': [[116, 293], [411, 300], [410, 335], [115, 328]]}, {'text': '2、再次取出两只耳机', 'confidence': 0.999390721321106, 'text_box_position': [[67, 339], [401, 349], [399, 384], [6
6, 374]]}, {'text': '3、刷新手机蓝牙设备列表，点击配对QCY-T1C，完成配对', 'confidence': 0.9993934035301208, 'text_box_position': [[67, 388], [937, 402], [937, 437], [67, 422]]}, {'text': '耳机取出会自动开机，若未自动开机，请充电后重新
尝试', 'confidence': 0.990841269493103, 'text_box_position': [[80, 436], [938, 451], [938, 483], [80, 468]]}, {'text': '切换设备配对方法：', 'confidence': 0.9996602535247803, 'text_box_position': [[71, 536], [421, 536], [421, 573], [71
, 573]]}, {'text': '1、关闭A手机蓝牙，耳机自动断开进入配对模式', 'confidence': 0.9853517413139343, 'text_box_position': [[67, 590], [791, 598], [791, 636], [67, 629]]}, {'text': '2、刷新B手机蓝牙设备列表，点击配对QCY-T1C，完成配对', 'c
onfidence': 0.9961883425712585, 'text_box_position': [[63, 638], [964, 649], [964, 695], [63, 684]]}, {'text': '*不支持同时连接两台手机，下次开机默认回连上次配对的手机', 'confidence': 0.9984445571899414, 'text_box_position': [[73, 686]
, [989, 698], [989, 748], [73, 736]]}]}]

结果：

{
‘text’: ‘双耳机配对’,
‘confidence’: 0.9995235204696655,
‘text_box_position’: [[64, 63], [301, 69], [299, 119], [63, 113]]
},
{
‘text’: ‘首次配对方法：’,
‘confidence’: 0.9997860193252563,
‘text_box_position’: [[71, 186], [336, 194], [334, 232], [70, 225]]
},
{
‘text’: ‘1、取出两只耳机，再将两只耳机放回充电盒中’,
‘confidence’: 0.9993939399719238,
‘text_box_position’: [[67, 245], [767, 258], [767, 297], [67, 283]]
},
{
‘text’: ‘（此步骤为新机激活）’,
‘confidence’: 0.9379152655601501,
‘text_box_position’: [[116, 293], [411, 300], [410, 335], [115, 328]]
},
{
‘text’: ‘2、再次取出两只耳机’,
‘confidence’: 0.999390721321106,
‘text_box_position’: [[67, 339], [401, 349], [399, 384], [66, 374]]
},
{
‘text’: ‘3、刷新手机蓝牙设备列表，点击配对QCY-T1C，完成配对’,
‘confidence’: 0.9993934035301208,
‘text_box_position’: [[67, 388], [937, 402], [937, 437], [67, 422]]
},
{
‘text’: ‘耳机取出会自动开机，若未自动开机，请充电后重新尝试’,
‘confidence’: 0.990841269493103,
‘text_box_position’: [[80, 436], [938, 451], [938, 483], [80, 468]]
},
{
‘text’: ‘切换设备配对方法：’,
‘confidence’: 0.9996602535247803,
‘text_box_position’: [[71, 536], [421, 536], [421, 573], [71, 573]]
},
{
‘text’: ‘1、关闭A手机蓝牙，耳机自动断开进入配对模式’,
‘confidence’: 0.9853517413139343,
‘text_box_position’: [[67, 590], [791, 598], [791, 636], [67, 629]]
},
{
‘text’: ‘2、刷新B手机蓝牙设备列表，点击配对QCY-T1C，完成配对’,
‘confidence’: 0.9961883425712585,
‘text_box_position’: [[63, 638], [964, 649], [964, 695], [63, 684]]
},
{
‘text’: ‘*不支持同时连接两台手机，下次开机默认回连上次配对的手机’,
‘confidence’: 0.9984445571899414,
‘text_box_position’: [[73, 686], [989, 698], [989, 748], [73, 736]]
}

识别效果非常好！！！

【参考文档】
《PaddleHub一键OCR中文识别》
《PaddleHub》

PaddleOCR加载chinese_ocr_db_crnn_server模型进行中英文混合预测（命令行）实践相关推荐

PaddleOCR加载chinese_ocr_db_crnn_modile模型进行中英文混合预测（Http服务）实践
1. 环境搭建参考:<PaddleOCR加载chinese_ocr_db_crnn_server模型进行中英文混合预测(命令行)实践> 2. 服务端部署 hub serving star ...
PaddleOCR加载chinese_ocr_db_crnn_server/chinese_ocr_db_crnn_modile模型进行中英文混合预测（代码）实践
1. 环境搭建参考:<PaddleOCR加载chinese_ocr_db_crnn_server模型进行中英文混合预测(命令行)实践> 2. 代码 import paddlehub as ...
加载tf模型正确率很低_深度学习模型训练全流程！
↑↑↑关注后"星标"Datawhale 每日干货 & 每月组队学习,不错过 Datawhale干货作者:黄星源.奉现,Datawhale优秀学习者本文从构建数据验证集. ...
在C++中加载TorchScript模型
在C++中加载TorchScript模型本教程已更新为可与PyTorch 1.2一起使用顾名思义,PyTorch的主要接口是Python编程语言.尽管Python是合适于许多需要动态性和易于迭代的 ...
xBIM 实战01 在浏览器中加载IFC模型文件
系列目录 [已更新最新开发文章,点击查看详细] 一.创建Web项目打开VS,新建Web项目,选择 .NET Framework 4.5 选择一个空的项目新建完成后,项目结构如下: 二.添 ...
Python时间序列模型推理预测实战：时序推理数据预处理（特征生成、lstm输入结构组织）、模型加载、模型预测结果保存、条件判断模型循环运行
Python时间序列模型推理预测实战:时序推理数据预处理(特征生成.lstm输入结构组织).模型加载.模型预测结果保存.条件判断模型循环运行目录
threejs加载obj模型_Vulkan编程指南(章节31-载入模型)
章节31 载入模型介绍本章节我们将会渲染一个带有纹理的三维模型. 库我们使用tinyobjloader库来从OBJ文件加载顶点数据.tinyobjloader库是一个简单易用的单文件OBJ加载器 ...
threejs加载3D模型例子
加载3D模型首先要引入ColladaLoader加载器,Collada是一个3D模型交换方案,即不同的3D模型可以通过Collada进行相互转换,言外之意,threejs可以使用Collada将3D ...
python加载模型_解决python 无法加载downsample模型的问题
downsample 在最新版本里面修改了位置 from theano.tensor.single import downsample (旧版本) 上面以上的的import会有error raise: ...

PaddleOCR加载chinese_ocr_db_crnn_server模型进行中英文混合预测（命令行）实践

1. 安装相关库文件

2. 安装预训练模型

3. 命令行预测

PaddleOCR加载chinese_ocr_db_crnn_server模型进行中英文混合预测（命令行）实践相关推荐

最新文章

热门文章