PaddleOCR/main/en/version3.x/module_usage/text_detection

[giscus[bot]]

PaddleOCR/main/en/version3.x/module_usage/text_detection

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/module_usage/text_detection.html

[DragonPow]

how to Prepare Dataset, I using coco format like document of PaddleX but it's not right

[liuhongen1234567]

Hello，you can download the data to take a look: https://paddle-model-ecology.bj.bcebos.com/paddlex/data/ocr_det_dataset_examples.tar.
Also, please note that PaddleX’s text recognition data follows a non-COCO format and relies on PPOCRLabel. You can find more details at
https://paddlepaddle.github.io/PaddleX/latest/en/data_annotations/ocr_modules/text_detection_recognition.html

[ilyass-khatib]

i cant find inference.pdmodel file in pp-ocrv5 server inference model because i want to convert it to onnx format to accelare it with cpu