PaddleOCR/v2.10.0/

[giscus[bot]]

PaddleOCR/v2.10.0/

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)

https://paddlepaddle.github.io/PaddleOCR/v2.10.0/

[Sujit230]

im using ch_PP-OCRv4_rec_infer model can anyone suggest code

[liuhongen1234567]

Hello, it is recommended to use paddleocr3.0, as this version provides more diverse models and simpler inference methods. For instance, if you wish to use ch_PP-OCRv4_rec_infer, you can refer to the following example code. In paddleocr3.0, ch_PP-OCRv4_rec_infer corresponds to PP-OCRv4_mobile_rec.yml. The detailed documentation is as follows: https://paddlepaddle.github.io/PaddleOCR/main/en/version3.x/pipeline_usage/OCR.html

from paddleocr import PaddleOCR
ocr = PaddleOCR(
    text_recognition_model_name="PP-OCRv4_mobile_rec",
    use_doc_orientation_classify=False,
    use_doc_unwarping=False,
    use_textline_orientation=False,
) # 更换 PP-OCRv5_server 模型
result = ocr.predict("./general_ocr_002.png")
for res in result:
    res.print()
    res.save_to_img("output")
    res.save_to_json("output")