greatliu
greatliu
Hi, firend. As your reply, I just have tried all the fonts in /usr/share/retroarch-assets/pkg. Unfortunately, all of them diaplay Chinese characters as "口". And, I wish all the lakka UI...
> If you are using xmb you need to restart RetroArch after you changed the font. I confirm restarted, the problem is still unsolved.
> I can't reproduce your issue using [nightly build](https://nightly.builds.lakka.tv/2022-08-04/Generic.x86_64/Lakka-Generic.x86_64-nightly-v4.x-20220804-9e969c4.img.gz) and `chinese-fallback-font.ttf`. > >  > > You have to restart RA > >  > > And Ozone menu is...
Hi, frined. I use Filezilla to transfer. I do not know how to show you screenshot, sorry. I will describe this problem with detail: 1. connect WiFi; 2. in "network...
> Hi, > > By default, it should be `-` and `+` . You can change it from `Settings tab > Input > Hotkeys > Volume Up/Down`. > > Thank...
> 若能确定是OCR抽取没有问题的话，看起来是需要通过数据标注的方式来提升效果，文档中有数据标注方式。https://github.com/PaddlePaddle/PaddleNLP/blob/develop/applications/information_extraction/label_studio_doc.md 收到，我学习一下。
> 若能确定是OCR抽取没有问题的话，看起来是需要通过数据标注的方式来提升效果，文档中有数据标注方式。https://github.com/PaddlePaddle/PaddleNLP/blob/develop/applications/information_extraction/label_studio_doc.md 我看完了数据标注。请问这意思，是标注一些数据让我自己去训练吗？ 如果是的话，那么后面需要看哪几个文档？直到生成模型能调用为止。 刚入门，需要请教，谢谢。
> Architecture.Models.Student.Backbone.checkpoints="./fapiao/ser_vi_layoutxlm_fapiao_trained/best_accuracy/ 断点训练权重传入错误，需要填写完整路径 不好意思，刚上手这个，不太懂。 我看了下我下载的模型下的确没有/best_accuracy/ 这个文件夹。 然后这里应该是需要一个json file吧？例子应该怎样写？
> 先传入正确的路径试一下呢 我的fapiao文件夹下，只有ser_vi_layoutxlm_fapiao_trained和re_vi_layoutxlm_fapiao_trained两个模型文件，再往下就没有文件夹了。 我指向fapiao文件夹运行， (Paddle) E:\Workspace\GitHub\PaddleOCR>python tools/infer_kie_token_ser.py -c ./configs/kie/vi_layoutxlm/ser_vi_layoutxlm_xfund_zh_udml.yml -o Architecture.Models.Student.Backbone.checkpoints="./fapiao/" Global.infer_img=./train_data/zzsfp/ val.json Global.infer_mode=False 报错为 [2024-05-10 19:30:51,225] [ WARNING] - Some weights of LayoutXLMForTokenClassification were not initialized from the model...
> 看这个总文档。https://github.com/PaddlePaddle/PaddleNLP/blob/develop/applications/information_extraction/README.md 谢谢你的回答，正好我需要做中文发票抽取，用uie抽取了发票的大部分数据。有几个小需求能不能解答一下： 1.有多个重名的key，比如买方和卖方都有“名称”这一项，我试了只能抽取到固定一个； 2.竖排文本能抽取到吗？比如“购买方信息”和“销售方信息”都是竖着写的； 3.中间有空格的key怎么抽？比如“金 额”就抽取不到