PaddleOCR/main/en/version3.x/pipeline_usage/OCR

[giscus[bot]]

PaddleOCR/main/en/version3.x/pipeline_usage/OCR

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/main/en/version3.x/pipeline_usage/OCR.html

[AadelAbk-aiio]

Bug Report: PaddleOCR 3.0.1 Error with MKLDNN

Experiencing an error when using PaddleOCR version 3.0.1.

Machine Specs:

• Python: 3.9.6
• Compiler: Clang 17.0.0 (clang-1700.0.13.5)
• OS: arm64-Darwin (macOS)
• paddleocr: 3.0.1
• paddlepaddle: 3.0.0
• paddlex: 3.0.1

Code Snippet:

ocr = PaddleOCR(lang=lang, text_recognition_model_name="PP-OCRv5_server_det")

Terminal Output:

Creating model: ('PP-LCNet_x1_0_doc_ori', None) 
Using official model (PP-LCNet_x1_0_doc_ori), the model files will be automatically downloaded and saved in /Users/username/.paddlex/official_models.
E0610 16:49:53.615828 4167163648 analysis_config.cc:672] Please compile with MKLDNN first to use MKLDNN
Error during OCR processing: 'paddle.base.libpaddle.AnalysisConfig' object has no attribute 'set_mkldnn_cache_capacity'

[Zahrachab]

Did you try to set enable_mkldnn=False ?

[andwizard]

save_to_img保存的几张图片中，除了检测结果以外的其他三张图片是什么

[antonjms]

Hi is there any possibilities we can make the detection only focus on horizontal text only even with a little separation in the text?

[HK-SOURCE-beep]

你好，用OCRv5运行ppstruture的predict_table.py报错，用OCRv4就没事，请问这是咋回事，谢谢！
Traceback (most recent call last):
File "/root/autodl-tmp/PaddleOCR/ppstructure/table/predict_table.py", line 241, in
main(args)
File "/root/autodl-tmp/PaddleOCR/ppstructure/table/predict_table.py", line 189, in main
pred_res, _ = table_sys(img)
File "/root/autodl-tmp/PaddleOCR/ppstructure/table/predict_table.py", line 100, in call
dt_boxes, rec_res, det_elapse, rec_elapse = self._ocr(copy.deepcopy(img))
File "/root/autodl-tmp/PaddleOCR/ppstructure/table/predict_table.py", line 145, in _ocr
rec_res, rec_elapse = self.text_recognizer(img_crop_list)
File "/root/autodl-tmp/PaddleOCR/tools/infer/predict_rec.py", line 826, in call
rec_result = self.postprocess_op(
File "/root/autodl-tmp/PaddleOCR/ppocr/postprocess/rec_postprocess.py", line 208, in call
text = self.decode(
File "/root/autodl-tmp/PaddleOCR/ppocr/postprocess/rec_postprocess.py", line 156, in decode
char_list = [
File "/root/autodl-tmp/PaddleOCR/ppocr/postprocess/rec_postprocess.py", line 157, in
self.character[text_id] for text_id in text_index[batch_idx][selection]
IndexError: list index out of range

[z-one]

Why is the structure of the returned data modified every time a major version is released?

[NexuChat]

We want you to support Arabic (ar) with PP-OCRv5, not only v3.

[ObaidQatan]

it's supported as of the current time. I've just tested it now.

[G97-point]

怎么可以只使用识别模型而不使用检测模型