安装飞桨https://www.paddlepaddle.org.cn/

是在python3.8下成功的

yum install python38

python3.8 -m pip install paddlepaddle==2.3.2 -i https://pypi.tuna.tsinghua.edu.cn/simple

============

下面都加

python3.8 -m pip

第一：安装 python

第二步：安装cv2

宝塔提示 Command "python setup.py egg_info" failed with error code 1 in

更新下python3.8 -m pip install --upgrade --force pip

如果你已经装好了pip，那就直接

python3.8 -m pip install opencv-python

如果：ImportError: libGL.so.1: cannot open shared object file: No such file or directory cv2报错opencv-python安装错误.

解决方案 将原来下载的opencv卸载然后

python3.8 -m pip install opencv-python-headless

python3.8 -m pip install opencv-contrib-python-headless

Python使用pip安装matplotlib模块

python3.8 -m pip install matplotlib进行自动的安装，系统会自动下载安装包。

===========

下载 https://github.com/PaddlePaddle/PaddleOCR

cd PaddleOCR

python3.8 -m pip install -r requirements.txt

python3.8 -m pip install "paddleocr>=2.0.1" -i https://mirror.baidu.com/pypi/simple --default-timeout=10000

===================

from paddleocr import PaddleOCR, draw_ocr

from PIL import Image

# load model

# Paddleocr目前支持中英文、英文、法语、德语、韩语、日语，可以通过修改 lang参数进行切换

# lang参数依次为`ch`, `en`, `french`, `german`, `korean`, `japan`

ocr = PaddleOCR(lang="ch",

                use_gpu=False,

                det_model_dir="../paddleORC_model/ch_ppocr_server_v2.0_det_infer/",

                cls_model_dir="ch_ppocr_mobile_v2.0_cls_infer/",

                rec_model_dir="ch_ppocr_server_v2.0_rec_infer/")

# load dataset

img_path = 'abc.jpg'

result = ocr.ocr(img_path)

for line in result:

    print(line)

# 注：

# result是一个list，每个item包含了文本框，文字和识别置信度

# line的格式为：

# [[[3.0, 149.0], [43.0, 149.0], [43.0, 163.0], [3.0, 163.0]], ('人心安', 0.6762619018554688)]

# 文字框 boxes = line[0]，包含文字框的四个角的(x,y)坐标

# 文字 txts = line[1][0]

# 识别置信度 scores = line[1][1]

# visual

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)

im_show = Image.fromarray(im_show)

im_show.save('result.jpg')