apps/FastDeploy
1
0
Fork 0
mirror of https://github.com/PaddlePaddle/FastDeploy.git synced 2025-10-07 17:41:52 +08:00
Code Issues Actions 2 Packages Projects Releases Wiki Activity
Files
0c664fd006b6e70fff81c4500a1c405a9b42ef0c
FastDeploy/examples/vision/ocr
History
chenjian 7c4e0d7ba0 [C API] Add c apis for ppocr models (#1351) 
* add batch_predict and initialized api for c

* add batch_predict and result str in C api

* modify visualization function

* add micro to add models batchify

* refactor and add models for ppdet others

* add base define

* add results api

* add headers

* add ppocr models

* add codes for implementing api

* add code

* add ppocr apis

* fix code

* add codes

* fix codes

* add demo
2023-02-17 15:43:12 +08:00
..
PP-OCRv2
[C API] Add c apis for ppocr models (#1351)
2023-02-17 15:43:12 +08:00
PP-OCRv3
[C API] Add c apis for ppocr models (#1351)
2023-02-17 15:43:12 +08:00
README_CN.md
[Doc]Add English version of documents in examples (#1070)
2023-01-06 09:34:28 +08:00
README.md
[Doc]Add English version of documents in examples (#1070)
2023-01-06 09:34:28 +08:00

README.md

English | 简体中文

PaddleOCR Model Deployment

PaddleOCR contains a series of tasks with multiple models, including

  • Text detection DBDetector
  • [Optional] Direction classification Classifer is used to adjust the direction of images before text recognition
  • Character recognition Recognizer is used to recognize characters from images

According to different scenarios, FastDeploy provides the following OCR task deployment. Users need to download three models and dictionary files (or two, optional classifier) simultaneously to complete the entire OCR prediction process

PP-OCR Model in English and Chinese Scenarios

The model download links in the following table are provided by PaddleOCR model library. Refer to PP-OCR Model List for details

OCR version Text box detection Direction classification model Character recognition Dictionary file Note
ch_PP-OCRv3[Recommended] ch_PP-OCRv3_det ch_ppocr_mobile_v2.0_cls ch_PP-OCRv3_rec ppocr_keys_v1.txt OCRv3 Original Ultra-Lightweight Model supports text detection in Chinese, English and multiple languages
en_PP-OCRv3[Recommended] en_PP-OCRv3_det ch_ppocr_mobile_v2.0_cls en_PP-OCRv3_rec en_dict.txt OCRv3 Original Ultra-Lightweight Model supports English and digital recognition. Its training data of detection model and recognition model is different from that of Chinese model, and no other differences can be detected
ch_PP-OCRv2 ch_PP-OCRv2_det ch_ppocr_mobile_v2.0_cls ch_PP-OCRv2_rec ppocr_keys_v1.txt OCRv2 Original Ultra-Lightweight Model supports text detection in Chinese, English and multiple languages
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 Original Ultra-Lightweight Model Supports text detection in Chinese, English and multiple languages with lighter weight than PPOCRv2
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 Server Model supports text detection in Chinese, English and multiple languages. It has better effects though being larger than the ultra-lightweight model