-
Notifications
You must be signed in to change notification settings - Fork 8k
New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
训练图和label 里如何让每个字符的出现频率类似,尤其是生僻字 #9830
Comments
我知道,你说的是识别模型,可以数据均衡。 |
数据均衡怎么实现? |
可以采用数据重采样,例如扩增生僻字图片进行copy-paste等方法。 |
styletext不太好,只支持部分语种。而且效果也不接近 |
还有TextRender可以尝试,效果会好于StyleText。数据合成工具总结:https://github.com/PaddlePaddle/PaddleOCR/blob/release/2.6/doc/doc_ch/data_synthesis.md |
resnet34 默认学习率 learning_rate: 0.0005 |
这个可以看你的设置,如果bs增大了,可以采用更大的学习率。另外设置阶梯学习率,例如0.0005、0.0001、0.001、0.002、0.00005等进行尝试,找到适合的学习率在附近微调。 |
[StyleText](https://github.com/PaddlePaddle/PaddleOCR/tree/release/2.6/StyleText resnet34 默认学习率是固定的, learning_rate: 0.0005 训练过程中是可以改的? |
yml怎么改成resnet18或其他backbone, |
yml怎么改成resnet18或其他backbone,改成这些backbone, crnn还能训练吗?源代码要不要改? |
该issue长时间未更新,暂将此issue关闭,如有需要可重新开启。 |
请提供下述完整信息以便快速定位问题/Please provide the following information to quickly locate the problem
训练图和label 里如何让每个字符的出现频率类似,尤其是生僻字
The text was updated successfully, but these errors were encountered: