-
Notifications
You must be signed in to change notification settings - Fork 7.7k
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
遇见ocrv4训练问题 #11149
Comments
也会出现valid__ratio键值错误 |
采用MultiScaleDataset读取数据集出现properties为int数据 |
在配置文件训练那里加入RecResizeImg后又出现网络问题,输入的tensor要求4-D or 5-D,但是收到的维度为3 |
核查过数据输入的image类型为[96,3,48,320]但进去变成[96,240,256] |
目前问题解决,就是之前问题采用蒸馏的配置文件训练,后面改成v4_rec配置文件是正常的,后续将蒸馏配置修改继续提高识别率,谢谢大佬开源工作!!! |
4-D or 5-D 这个问题是怎么解决的 |
请问具体是怎么做的呢,能详细说下么 |
@yang-chenyu104 你是 v4-distillation 预训练模型 + rec_v4 的 conf,训练的吗?最终训练效果如何呢? |
是hg那个文件准确率目前效果是最好的,蒸馏那个需要改配置文件,hg那个路径正确就可以训练
…---原始邮件---
发件人: ***@***.***>
发送时间: 2023年12月7日(周四) 晚上9:05
收件人: ***@***.***>;
抄送: ***@***.******@***.***>;
主题: Re: [PaddlePaddle/PaddleOCR] 遇见ocrv4训练问题 (Issue #11149)
目前问题解决,就是之前问题采用蒸馏的配置文件训练,后面改成v4_rec配置文件是正常的,后续将蒸馏配置修改继续提高识别率,谢谢大佬开源工作!!!
@yang-chenyu104 你是 v4-distillation 预训练模型 + rec_v4 的 conf,训练的吗?最终训练效果如何呢?
—
Reply to this email directly, view it on GitHub, or unsubscribe.
You are receiving this because you were mentioned.Message ID: ***@***.***>
|
@yang-chenyu104 好的,谢谢 |
遇到同样问题,baidu不升级修补下这个问题,来自于2024.2 |
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
我们提供了AceIssueSolver来帮助你解答问题,你是否想要它来解答(请填写yes/no)?/We provide AceIssueSolver to solve issues, do you want it? (Please write yes/no):
请尽量不要包含图片在问题中/Please try to not include the image in the issue.
训练ocrv4看见配置文件中PostProcess方式为蒸馏的CTCLabel,但前处理方式为NRTR导致后续out_channels_list没有找到NRTRLabelDecode,我将编码改成CTCLabelDecode不知道怎么样,还是需要写一个DistillNRTR解码代码
The text was updated successfully, but these errors were encountered: