如何对特定的模型微调，而不是对官方的预训练模型微调？ #17740
Unanswered
xiaohong1633
asked this question in
Q&A
如何对特定的模型微调，而不是对官方的预训练模型微调？
#17740
Replies: 2 comments
-
|
en_PP-OCRv5_mobile_rec 的权重链接如下： https://paddle-model-ecology.bj.bcebos.com/paddlex/official_pretrained_model/en_PP-OCRv5_mobile_rec_pretrained.pdparams ，具体可以从文本识别模块文档 https://www.paddleocr.ai/latest/version3.x/module_usage/text_recognition.html#_3 ——二、支持模型列表 ——👉模型列表详情 中的训练模型处下载 |
Beta Was this translation helpful? Give feedback.
0 replies
-
|
好的，非常感谢！！！！ |
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.
-
比如说，我想对en_PP-OCRv5_mobile_rec 这个模型微调，字典保持一致。我去哪里下载对应的预训练模型权重？ 或者下载的推理权重如何转化为训练模型权重（模型层名不对应）？
Beta Was this translation helpful? Give feedback.
All reactions