PaddleOCR icon indicating copy to clipboard operation
PaddleOCR copied to clipboard

Multilingual detection model training data

Open deckardcain1 opened this issue 2 years ago • 1 comments

What training data was used to produce the multilingual detection models? I have trained DB/DB++ models with MLT but was wondering if additional data sets were used in training the pre-trained models in the model zoo.

deckardcain1 avatar Sep 19 '22 19:09 deckardcain1

Use a lot of synthesis data for training

an1018 avatar Sep 22 '22 05:09 an1018