百度飞桨(PaddlePaddle) - PP-OCRv3 文字检测识别系统 Paddle Inference 模型推理

pip install paddleocr -i http://pypi.tuna.tsinghua.edu.cn/simple  --verbose

import cv2
import matplotlib.pyplot as plt
import numpy as np
import os
from paddleocr import PaddleOCR, draw_ocr

ocr = PaddleOCR(use_gpu=False)  # need to run only once to download and load model into memory
img_path = './images/006.jpg'
result = ocr.ocr(img_path, rec=False)
for line in result:
    print(line)

# 显示结果
from PIL import Image

image = Image.open(img_path).convert('RGB')
im_show = draw_ocr(image, result, txts=None, scores=None, font_path='./fonts/simfang.ttf')
plt.figure(figsize=(15, 8))
plt.imshow(im_show)
plt.show()

import matplotlib.pyplot as plt
from paddleocr import PaddleOCR, draw_ocr

ocr = PaddleOCR(use_gpu=False)  # need to run only once to download and load model into memory
img_path = './images/006.jpg'
result = ocr.ocr(img_path, det=False)
for line in result:
    print(line)

import cv2
import matplotlib.pyplot as plt
from paddleocr import PaddleOCR, draw_ocr

ocr = PaddleOCR(use_angle_cls=True, use_gpu=False)  # need to run only once to download and load model into memory
img_path = './images/006.jpg'
result = ocr.ocr(img_path, det=False, rec=False, cls=True)
for line in result:
    print(line)

img = cv2.imread(img_path)
plt.imshow(img[...,::-1])
plt.show()

import cv2
import os
import matplotlib.pyplot as plt
from paddleocr import PaddleOCR, draw_ocr

# 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
# 参数依次为`ch`, `en`, `french`, `german`, `korean`, `japan`。
ocr = PaddleOCR(use_angle_cls=True, lang="ch", use_gpu=False)  # need to run only once to download and load model into memory
save_results = []
img_path = 'images/003.jpg'
save_dir = 'ocr_result'
result = ocr.ocr(img_path, cls=True)[0]
# 将结果写入文件
with open(
        os.path.join(save_dir, "003_result.txt"),
        'w',
        encoding='utf-8') as f:
    for line in result:
        f.writelines(str(line)+'\n')
        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')
cv2.imwrite(os.path.join(save_dir, "003_result.jpg"), im_show)
plt.figure(figsize=(15, 8))
plt.imshow(im_show)
plt.show()

shapely
scikit-image
imgaug
pyclipper
lmdb
tqdm
numpy
visualdl
rapidfuzz
opencv-python==4.6.0.66
opencv-contrib-python==4.6.0.66
cython
lxml
premailer
openpyxl
attrdict
Polygon3
lanms-neo==1.0.2
PyMuPDF<1.21.0

D:\OpenSource\PaddlePaddle\PaddleOCR-release-2.6>pip install -r requirements.txt -i http://pypi.tuna.tsinghua.edu.cn/simple  --verbose
D:\OpenSource\PaddlePaddle\PaddleOCR-release-2.6>pip install paddlenlp -i http://pypi.tuna.tsinghua.edu.cn/simple  --verbose

import cv2
import matplotlib.pyplot as plt
import numpy as np
import os

# 选择2张图像可视化
img1 = cv2.imread("doc/imgs/00006737.jpg")
img2 = cv2.imread("doc/imgs/00056221.jpg")
plt.figure(figsize=(15, 6))
plt.subplot(1, 2, 1)  # 定义 1行2列
plt.imshow(img1[:, :, ::-1])  # 第1列 放 img1 ，::-1 => axis 3 倒序
plt.subplot(1, 2, 2)  # 定义 1行2列
plt.imshow(img2[:, :, ::-1])  # 第2列 放 img1
plt.show()

# 参考代码
# http://github.com/PaddlePaddle/PaddleOCR/blob/release/2.4/tools/export_model.py
# 下载预训练模型(V2)
wget http://paddleocr.bj.bcebos.com/PP-OCRv2/chinese/ch_PP-OCRv2_det_distill_train.tar && tar -xf ch_PP-OCRv2_det_distill_train.tar && rm ch_PP-OCRv2_det_distill_train.tar

# 导出推理模型(V2)
python tools/export_model.py -c configs/det/ch_PP-OCRv2/ch_PP-OCRv2_det_cml.yml \
    -o Global.pretrained_model="ch_PP-OCRv2_det_distill_train/best_accuracy" \
    Global.save_inference_dir="./my_model"

# 预测 
python tools/infer/predict_det.py --image_dir="./doc/imgs/00018069.jpg" --det_model_dir="./inference/ch_PP-OCRv3_det_infer" --use_gpu=False

# 预测 
python tools/infer/predict_cls.py \
    --image_dir="./doc/imgs_words/ch/word_1.jpg" \
    --cls_model_dir="./inference/ch_ppocr_mobile_v2.0_cls_infer" \
    --use_gpu=False

# 预测 
python tools/infer/predict_rec.py \
    --image_dir="./doc/imgs_words/ch/word_4.jpg" \
    --rec_model_dir="./inference/ch_PP-OCRv3_rec_infer" \
    --use_gpu=False

# 预测 
python tools/infer/predict_system.py \
    --image_dir="./doc/imgs/00018069.jpg" \
    --det_model_dir="./inference/ch_PP-OCRv3_det_infer/" \
    --cls_model_dir="./inference/ch_ppocr_mobile_v2.0_cls_infer/" \
    --rec_model_dir="./inference/ch_PP-OCRv3_rec_infer/" \
    --use_angle_cls=True

python tools/infer/predict_system.py \
    --image_dir="./doc/imgs/00018069.jpg" \
    --det_model_dir="./inference/ch_PP-OCRv3_det_infer/" \
    --cls_model_dir="./inference/ch_ppocr_mobile_v2.0_cls_infer/" \
    --rec_model_dir="./inference/ch_PP-OCRv3_rec_infer/" \
    --use_angle_cls=True \
    --save_crop_res=True