paddleocr window10 first experience

paddle环境安装

• 由于cMy plate is fullcondaThe whole movedd盘

在cmd中的代码

conda create --prefix==D:\...  python

使用–prefix==指定了位置
The corresponding activation also uses a specific path

activate  D:\conda\envs\paddle_env

• Then follow it honestly官网进行下载
• 有多个python.exe文件
  
  这里最好指定python进行,Sometimes it is okay not to specify,Occasionally report an error

Python 3.8.8 (tags/v3.8.8:024d805, Feb 19 2021, 13:18:16) [MSC v.1928 64 bit (AMD64)] on win32
Type "help", "copyright", "credits" or "license" for more information.
>>> import paddle
>>> print(paddle.utils.run_check())
Running verify PaddlePaddle program ... 
W0719 02:01:59.063643 16104 gpu_resources.cc:61] Please NOTE: device: 0, GPU Compute Capability: 6.1, Driver API Version: 10.2, Runtime API Version: 10.2  
W0719 02:01:59.066314 16104 dynamic_loader.cc:276] Note: [Recommend] copy cudnn into CUDA installation directory.
 For instance, download cudnn-10.0-windows10-x64-v7.6.5.32.zip from NVIDIA's official website,
then, unzip it and copy it into C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v10.0
You should do this according to your CUDA installation directory and CUDNN version.
Traceback (most recent call last):
  File "<stdin>", line 1, in <module>

测试代码：

import paddle
paddle.utils.run_check()

My words are directly specified in the environment just createdpython（这部分是在cmdinside）

在pycharmThe command line doesn't seem to respondwhere python,但是使用pythonBetter to specify！！！

paddle 安装

1. 根据gitee官方介绍Basically a perfect configuration can be achieved
2. 注意一些小细节

• 我是直接在pycharmIt directly opens a virtual environment for configuration,Click on the far right belowterminal直接进入终端

• 在配置环境中 直接python（如下图）
  

• 其次就是GitHubThe code above will report some inexplicable errors

• Check the installation package

pip list

使用

（1）命令行使用

cd 图片文件夹路径

cd /path/to/ppocr_img

paddleocr --image_dir ./imgs/11.jpg --use_angle_cls true --use_gpu false

• –use_angle_cls Set whether to use orientation classifier recognition180度旋转文字

• –use_gpu false设置是否使用GPU

• 单独使用检测：设置–rec为false
  given at this time坐标位置

• 单独使用识别：设置–det为false
  The identified is given at this timecontent and confidence

• due to environment configuration,我使用的是cpu
  Therefore, an additional sentence is added to the two codes on the official website**–use_gpu false**

单独使用：

paddleocr --image_dir ./imgs/11.jpg --rec false --use_gpu false

单独使用识别：

paddleocr --image_dir ./imgs_words/ch/word_1.jpg --det false --use_gpu false

Below is the code from the official website（cpufriends, press the change above,gpu按下面的）

不然会报错（如下面代码）！！！！！paddle默认是开gpu的

RuntimeError: (PreconditionNotMet) The third-party dynamic library (cudnn64_7.dll) that Paddle depends on is not configured correctly. (error code is 126) 
  Suggestions:
  1. Check if the third-party dynamic library (e.g. CUDA, CUDNN) is installed correctly and its version is matched with paddlepaddle you installed.        
  2. Configure third-party dynamic library environment variables as follows:
  - Linux: set LD_LIBRARY_PATH by `export LD_LIBRARY_PATH=...`
  - Windows: set PATH by `set PATH=XXX; (at ..\paddle\phi\backends\dynload\dynamic_loader.cc:303)

(2)python脚本使用

1）常用语句

• 导入常用包

from paddleocr import PaddleOCR, draw_ocr

• 实例化ocr

 ocr = PaddleOCR(use_angle_cls=True, lang="ch")
 #中文识别
 

• 调用ocr接口

result = ocr.ocr(img_path, cls=True)

2）报错

1. The problem has been initialized

OMP: Error #15: Initializing libiomp5md.dll, but found libiomp5md.dll already initialized.

我是直接将paddle环境中的libiomp5md.dll删除

2.我是使用cpu在跑

ocr = PaddleOCR(use_angle_cls=True, lang="ch",use_gpu=False)
#加上use_gpu=False

Attached is my modification官网的完整代码

from paddleocr import PaddleOCR, draw_ocr

# Paddleocr目前支持的多语言语种可以通过修改lang参数进行切换
# 例如`ch`, `en`, `fr`, `german`, `korean`, `japan`
ocr = PaddleOCR(use_angle_cls=True, lang="ch",use_gpu=False)#加上use_gpu=False
# need to run only once to download and load model into memory

img_path = 'D:/computervision/ocr/ppocr_img/imgs/11.jpg'#改成自己的路径

result = ocr.ocr(img_path, cls=True)
for line in result:
    print(line)

# 显示结果
from PIL import Image

image = Image.open(img_path).convert('RGB')
boxes = [line[0] for line in result]
txts = [line[1][0] for line in result]
scores = [line[1][1] for line in result]
im_show = draw_ocr(image, boxes, txts, scores, font_path='./fonts/simfang.ttf')
im_show = Image.fromarray(im_show)
im_show.save('result.jpg')

There might be a problem with the visualization！！！If you see something wrong, let me know！！！