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)
https://paddlepaddle.github.io/PaddleOCR/
Apache License 2.0
44.09k stars 7.81k forks source link

日语文字识别的预训练模型只有mobilenetV2吗 #2797

Closed guijuzhejiang closed 2 years ago

guijuzhejiang commented 3 years ago

如题,关于日语文字识别的预训练模型我只找到了mobilenetV2版,作为预训练模型会报错,因为backbone只支持['MobileNetV3', 'ResNet', 'ResNetFPN']三种网络,请问日语文字识别的预训练模型有没有骨干网络是'MobileNetV3',或'ResNet'训练好的模型?

littletomatodonkey commented 3 years ago

有的:

https://github.com/PaddlePaddle/PaddleOCR/blob/release%2F2.1/doc/doc_ch/models_list.md

https://github.com/PaddlePaddle/PaddleOCR/blob/release%2F2.1/configs/rec/multi_language/rec_japan_lite_train.yml

guijuzhejiang commented 3 years ago

有的:

https://github.com/PaddlePaddle/PaddleOCR/blob/release%2F2.1/doc/doc_ch/models_list.md

https://github.com/PaddlePaddle/PaddleOCR/blob/release%2F2.1/configs/rec/multi_language/rec_japan_lite_train.yml

谢谢。japan_mobile_v2.0_rec这个我也找到了,不过这个预训练模型就是我说的mobilenetV2训练的。我是想找mobilenetV2以外的模型。

nissansz commented 2 years ago

有好的模型或数据集吗?微信 nlanguage