额外介绍一点别的，如何docker 快速启动一个PaddleOCR的能力见这里：https://qq742971636.blog.csdn.net/article/details/135109278

python包：pip install baidu-aip

详细教程：https://www.jianshu.com/p/e10dc43c38d0

我的代码：

python
import json
import os
import shutil
import cv2
from aip import AipOcr
from tqdm import tqdm
# """ 你的 APPID AK SK  图2的内容"""
APP_ID = '27145052'
API_KEY = '26T8PoG7inAFTF3MF99E0Pbg  '
SECRET_KEY = 'CCbIfR0f9wLMgPXs3c0G6MTYwawpwZXi '
client = AipOcr(APP_ID, API_KEY, SECRET_KEY)
def get_file_content(filePath):
    with open(filePath, 'rb') as fp:
        return fp.read()
rootpath = r"C:\Users\dong.xie\Desktop\xsz111\学生证\u=693650192"
print(rootpath)
res = {}
files = os.listdir(rootpath)
for file in tqdm(files):
    try:
        fname = os.path.join(rootpath, file)
        image = get_file_content(fname)
        """ 调用通用文字识别, 图片参数为本地图片 """
        results = client.general(image)
        res[fname] = results
    except:
        print("error", fname)

最好的方式还是ocr+docker：

https://github.com/PaddlePaddle/PaddleOCR