PaddleOCRv3中有PP-OCRv5_server_det各个网络结构(backbone,neck,head)实现的源码吗? #15802
Unanswered
lin-contextere
asked this question in
Q&A
Replies: 1 comment
-
https://github.com/PaddlePaddle/PaddleOCR/blob/main/ppocr/modeling/backbones/rec_pphgnetv2.py |
Beta Was this translation helpful? Give feedback.
0 replies
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Uh oh!
There was an error while loading. Please reload this page.
-
我想按照
https://github.com/PaddleOCR-Community/Dive-into-OCR/blob/main/notebook_ch/2.text_detection/%E6%96%87%E6%9C%AC%E6%A3%80%E6%B5%8B%E5%AE%9E%E8%B7%B5%E7%AF%87.ipynb
这个OCR教程,学习了解一下最新的PP-OCRv5_server_det模型。
这个教程是根据DBNet讲解的,其中讲到backbone时,教里举例用的是MobileNetV3,可以通过
from ppocr.modeling.backbones.det_mobilenet_v3 import MobileNetV3
加载MobileNetV3。
然后再
https://github.com/PaddlePaddle/PaddleOCR/blob/main/ppocr/modeling/backbones/det_mobilenet_v3.py
可以看到这个MobileNetV3的具体实现源码。
现在我想看看PP-OCRv5_server_det的backbone模型源码,在

https://github.com/PaddlePaddle/PaddleOCR/blob/main/configs/det/PP-OCRv5/PP-OCRv5_server_det.yml
中可以看到,backbone是PPHGNetV2_B4,回到ppocr/modeling/backbones文件夹下
https://github.com/PaddlePaddle/PaddleOCR/tree/main/ppocr/modeling/backbones
我找不到对应PPHGNetV2_B4的文件。
请问PaddleOCRv3提供了PP-OCRv5_server_det模型的实现源码吗?
Beta Was this translation helpful? Give feedback.
All reactions