mirror of
https://github.com/PaddlePaddle/FastDeploy.git
synced 2025-10-05 16:48:03 +08:00
e50c1030cd
* Imporve OCR Readme * Improve OCR Readme * Improve OCR Readme * Improve OCR Readme * Improve OCR Readme * Add Initialize function to PP-OCR * Add Initialize function to PP-OCR * Add Initialize function to PP-OCR * Make all the model links come from PaddleOCR * Improve OCR readme * Improve OCR readme * Improve OCR readme * Improve OCR readme * Add Readme for vision results * Add Readme for vision results * Add Readme for vision results * Add Readme for vision results * Add Readme for vision results * Add Readme for vision results * Add Readme for vision results * Add Readme for vision results * Add Readme for vision results * Add Readme for vision results * Add check for label file in postprocess of Rec model * Add check for label file in postprocess of Rec model * Add check for label file in postprocess of Rec model * Add check for label file in postprocess of Rec model * Add check for label file in postprocess of Rec model * Add check for label file in postprocess of Rec model * Add comments to create API docs * Improve OCR comments * Rename OCR and add comments * Make sure previous python example works * Make sure previous python example works * Fix Rec model bug * Fix Rec model bug * Fix rec model bug * Add SetTrtMaxBatchSize function for TensorRT * Add SetTrtMaxBatchSize Pybind * Add set_trt_max_batch_size python function * Set TRT dynamic shape in PPOCR examples * Set TRT dynamic shape in PPOCR examples * Set TRT dynamic shape in PPOCR examples * Fix PPOCRv2 python example Co-authored-by: Jason <jiangjiajun@baidu.com>
PaddleOCR 模型部署
PaddleOCR为多个模型组合串联任务，包含
- 文本检测
DBDetector - [可选]方向分类
Classifer用于调整进入文字识别前的图像方向 - 文字识别
Recognizer用于从图像中识别出文字
根据不同场景, FastDeploy汇总提供如下OCR任务部署, 用户需同时下载3个模型与字典文件（或2个，分类器可选), 完成OCR整个预测流程
PP-OCR 中英文系列模型
下表中的模型下载链接由PaddleOCR模型库提供, 详见PP-OCR系列模型列表
| OCR版本 | 文本框检测 | 方向分类模型 | 文字识别 | 字典文件 | 说明 |
|---|---|---|---|---|---|
| ch_PP-OCRv3[推荐] | ch_PP-OCRv3_det | ch_ppocr_mobile_v2.0_cls | ch_PP-OCRv3_rec | ppocr_keys_v1.txt | OCRv3系列原始超轻量模型，支持中英文、多语种文本检测 |
| en_PP-OCRv3[推荐] | en_PP-OCRv3_det | ch_ppocr_mobile_v2.0_cls | en_PP-OCRv3_rec | en_dict.txt | OCRv3系列原始超轻量模型，支持英文与数字识别，除检测模型和识别模型的训练数据与中文模型不同以外，无其他区别 |
| ch_PP-OCRv2 | ch_PP-OCRv2_det | ch_ppocr_mobile_v2.0_cls | ch_PP-OCRv2_rec | ppocr_keys_v1.txt | OCRv2系列原始超轻量模型，支持中英文、多语种文本检测 |
| ch_PP-OCRv2_mobile | ch_ppocr_mobile_v2.0_det | ch_ppocr_mobile_v2.0_cls | ch_ppocr_mobile_v2.0_rec | ppocr_keys_v1.txt | OCRv2系列原始超轻量模型，支持中英文、多语种文本检测,比PPOCRv2更加轻量 |
| ch_PP-OCRv2_server | ch_ppocr_server_v2.0_det | ch_ppocr_mobile_v2.0_cls | ch_ppocr_server_v2.0_rec | ppocr_keys_v1.txt | OCRv2服务器系列模型, 支持中英文、多语种文本检测，比超轻量模型更大，但效果更好 |