search

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)
Apache License 2.0
40.2k stars 7.45k forks source link

PPOCRv3 不定长文本识别问题 #9842

Closed bianliuyang closed 1 month ago

bianliuyang commented 1 year ago

看了相关的issue，说是在PPOCRV3中对svtr做了改进，改了backbone 为lcnet结构，我想请问一下en_PP-OCRv3_rec.yml中的backbone：mobilenetv1enhance就是lcnet结构吗？另外en_PP-OCRv3_rec.yml文件中，还是要设置max_text_length，那加入我不知道图片中的最长的字符有多长，只知道有短文本和长文本，这怎么完成不定长文本识别呢。

super-tian commented 1 year ago

max_text_length指的是最大长度，你给你的最大长度就行

github-actions[bot] commented 11 months ago

This issue has been automatically marked as stale because it has not had recent activity. It will be closed in 7 days if no further activity occurs. Thank you for your contributions.

ccx1997 commented 7 months ago

ICCV2023的工作LISTER可以解决这个问题 https://github.com/AlibabaResearch/AdvancedLiterateMachinery/tree/main/OCR/LISTER

UserWangZz commented 1 month ago

该issue长时间未更新，暂将此issue关闭，如有需要可重新开启。