Paddle-OCR本地部署(GPU版)
- 项目地址:GitHub - PaddlePaddle/PaddleOCR: Awesome multilingual OCR toolkits based on PaddlePaddle (practical ultra lightweight OCR system, support 80+ languages recognition, provide data annotation and synthesis tools, support training and deployment among server, mobile, embedded and IoT devices)
- 环境工具准备:Anaconda3,cuda12.4(本机),pycharm
Pytorch:pip install torch==2.3.1 torchvision==0.18.1 torchaudio==2.3.1 --index-url https://download.pytorch.org/whl/cu121
- 本地部署:
打开anaconda终端
- 创建虚拟环境:conda create -n paddle python=3.10 -y
- 激活虚拟环境:conda activate paddle
- 安装应用包:pip install paddlepaddle-gpu
- 安装PaddleOCR whl包:pip install paddleocr
- 使用
命令行使用
(图像使用):paddleocr --image_dir 图像路径 --use_angle_cls true --use_gpu true
在使用前可以先使用cd命令切换到图像存放目录
(pdf使用):并且可以通过指定参数page_num来控制推理前面几页,默认为0,表示推理所有页。paddleocr --image_dir pdf路径 --use_angle_cls true --use_gpu true --page_num 0
运行结果:
Python脚本使用:
图像(官网参考代码):
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") # need to run only once to download and load model into memory
img_path = './imgs/11.jpg'
result = ocr.ocr(img_path, cls=True)
for idx in range(len(result)):
res = result[idx]
for line in res:
print(line)
# 显示结果
from PIL import Image
result = result[0]
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')
PDF(参考代码):
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`
PAGE_NUM = 10 # 将识别页码前置作为全局,防止后续打开pdf的参数和前文识别参数不一致 / Set the recognition page number
pdf_path = 'default.pdf'
ocr = PaddleOCR(use_angle_cls=True, lang="ch", page_num=PAGE_NUM) # need to run only once to download and load model into memory
# ocr = PaddleOCR(use_angle_cls=True, lang="ch", page_num=PAGE_NUM,use_gpu=0) # 如果需要使用GPU,请取消此行的注释 并注释上一行 / To Use GPU,uncomment this line and comment the above one.
result = ocr.ocr(pdf_path, cls=True)
for idx in range(len(result)):
res = result[idx]
if res == None: # 识别到空页就跳过,防止程序报错 / Skip when empty result detected to avoid TypeError:NoneType
print(f"[DEBUG] Empty page {idx+1} detected, skip it.")
continue
for line in res:
print(line)
# 显示结果
import fitz
from PIL import Image
import cv2
import numpy as np
imgs = []
with fitz.open(pdf_path) as pdf:
for pg in range(0, PAGE_NUM):
page = pdf[pg]
mat = fitz.Matrix(2, 2)
pm = page.get_pixmap(matrix=mat, alpha=False)
# if width or height > 2000 pixels, don't enlarge the image
if pm.width > 2000 or pm.height > 2000:
pm = page.get_pixmap(matrix=fitz.Matrix(1, 1), alpha=False)
img = Image.frombytes("RGB", [pm.width, pm.height], pm.samples)
img = cv2.cvtColor(np.array(img), cv2.COLOR_RGB2BGR)
imgs.append(img)
for idx in range(len(result)):
res = result[idx]
if res == None:
continue
image = imgs[idx]
boxes = [line[0] for line in res]
txts = [line[1][0] for line in res]
scores = [line[1][1] for line in res]
im_show = draw_ocr(image, boxes, txts, scores, font_path='doc/fonts/simfang.ttf')
im_show = Image.fromarray(im_show)
im_show.save('result_page_{}.jpg'.format(idx))
更多机器学习课程: