Yang Liu
Yang Liu
Thanks for your contribution and we appreciate it a lot. The following instructions would make your pull request more healthy and more easily get feedback. If you do not understand...
使用这种编号方式后，在专注模式下，标题的编号并不会跟模式一起变化，如图所示 
Thanks for your contribution and we appreciate it a lot. The following instructions would make your pull request more healthy and more easily get feedback. If you do not understand...
我希望能够对齐论文精度，如果使用DDP的训练方式，在八卡的情况下，相关参数例如batchsize和lr应该怎么给呢？
svtr训练错误
- 系统环境/System Environment：4 x A100, Nvidia 470.129.06, centos 7, 基于 paddle 官方的 docker 镜像 [2.3.2-gpu-cuda10.2-cudnn7](https://hub.docker.com/layers/paddlepaddle/paddle/2.3.2-gpu-cuda10.2-cudnn7/images/sha256-791967cae01bd2de42f9aed8e78be6d16a8807f9773b7e4d59e76fae89f98124?context=explore) 安装的 PPOCR 2.6 - 版本号/Version：Paddle：2.3.2 PaddleOCR 2.6 问题相关组件/Related components： SVTR - 运行指令/Command Code： ```bash python...
- 系统环境/System Environment：Docker [2.1.3-gpu-cuda11.2-cudnn8](https://hub.docker.com/layers/paddlepaddle/paddle/2.1.3-gpu-cuda11.2-cudnn8/images/sha256-ad3b494a60a52390199902e284c1d87e40defe390ca702619bde51f5aa904364?context=explore) - 版本号/Version：Paddle：2.1.3 PaddleOCR 2.6： 问题相关组件/Related components：SVTR 直接调用[readme](https://github.com/PaddlePaddle/PaddleOCR/blob/release%2F2.6/doc/doc_ch/algorithm_rec_svtr.md#svtr%E7%AE%97%E6%B3%95%E7%AE%80%E4%BB%8B)中的提供的配置和权重对svtr_base模型进行评测时，会报找不到SVTRLabelDecode的错误。我留意到配置文件里提到这个设定只在评测时用到，请问这一部分的模块是不是还没开源？实现起来跟CTC有什么区别呢？
The problem of the previous [issue](https://github.com/lkeab/BCNet/issues/124) has not been resolved. I took a look at the config and code of this repo, which also uses fcos, but it seems that...
There is no polygon label information in my dataset, only bbox in the form of xyxy. What should I do if I want to evaluate the effect of the trained...
There is a custom dataset, each picture contains multiple objects, how to modify the dataloader or model to train such a dataset?