Lucknicking

His code can be run directly. I don't know what's wrong with you? ------------------ 原始邮件 ------------------ 发件人: ***@***.***>; 发送时间: 2023年3月28日(星期二) 上午9:47 收件人: ***@***.***>; 抄送: ***@***.***>; ***@***.***>; 主题: Re: [SSinyu/RED-CNN] About the PSNR...

If you want to run your own dataset, you may need to modify the pred code. After all, your file path format does not match his requirements, or you can...

> > I've been running your code recently. But my final PSNR value is about 26. The PSNR value written in your paper is above 40. I use the AAPM...

> > > > I've been running your code recently. But my final PSNR value is about 26. The PSNR value written in your paper is above 40. I use...

> > > > > > I've been running your code recently. But my final PSNR value is about 26. The PSNR value written in your paper is above 40....

> > > > > > > > I've been running your code recently. But my final PSNR value is about 26. The PSNR value written in your paper is...

> 我是用cpu训练的ser+re，导出为inference模型后，用官方的predict_kie_token_ser_re.py脚本去推理的时候，就会报这个错误：ValueError: (InvalidArgument) The dims of Input(X) should be greater than 0 [Hint: Expected x_dims[i] > 0, but received x_dims[i]:0

> 不好意思哈，我目前还在尝试Issues其他人提供的解决思路，看推理的时候，还会不会报我之前说的那个错误，因为我没有推理成功，所以我也不知道我的预测结果的好坏，但是你如果没有报错了，仅仅是预测结果不太理想的话，你可以优先看看同类数据集是否>50张以上，并且改善一下学习率等等 > > > 冰封 > ***@***.*** > > > >   > […](#) 你可以先不用导出为inference，可以直接使用如下命令来推理， python3 ./tools/infer_kie_token_ser_re.py -c configs/kie/vi_layoutxlm/re_vi_layoutxlm_hukoubu_zh.yml -o Architecture.Backbone.checkpoints=/root/project/PaddleOCR/output/re_vi_layoutxlm_xfund_zh/latest Global.infer_img=./images/hukoubu_huangxinghua.jpg -c_ser configs/kie/vi_layoutxlm/ser_vi_layoutxlm_hukoubu_zh.yml -o_ser Architecture.Backbone.checkpoints=/root/project/PaddleOCR/output/ser_vi_layoutxlm_hukoubu_zh/best_accuracy