WangZ comments

Results 182 comments of


                                            WangZ

官方是否可以发布一个ppocrlabel的exe文件，我看issues里面很多人都有这个需求

#https://github.com/PaddlePaddle/PaddleOCR/discussions/11342 #https://github.com/PaddlePaddle/PaddleOCR/discussions/11490 官方目前暂不支持打包，具体可以参考上面链接

The Hmean is very high (around 93%) but can't infer anything with DB++ model. However, the infer code did great with DB

Hello, can you provide a picture after inference and a more detailed description of the problem? I don't understand your question a bit

The Hmean is very high (around 93%) but can't infer anything with DB++ model. However, the infer code did great with DB

This issue has not been updated for a long time. This issue is temporarily closed and can be reopened if necessary.

新人求解，训练模型时，在打印完日志‘During the training process, after the 0th iteration, an evaluation is run every 400 iterations’后，卡住了

你好，请问使用的是cpu版本的paddle还是gpu版本的paddle

新人求解，训练模型时，在打印完日志‘During the training process, after the 0th iteration, an evaluation is run every 400 iterations’后，卡住了

batchsize=8，30张图，一个epoch4个iteration，log_smooth_window : 20,所以应该5个epoch才会打印出一个log。可能与这个有关系

G:\PaddleOCR-release-2.7\PaddleOCR-release-2.7\train_data\det\train\03.jpg [{"transcription": "0007.0", "points": [[612, 379], [1087, 379], [1087, 508], [612, 508]], "difficult": false}] 检查一下图像路径和label之间的分割符是不是\t

文字检测训练总是报错，检查数据文件没有问题

/PaddleOCR/train_data/det/train/0009.jpg \t [{"transcription": "熊杼", "points": [[95, 55], [139, 55], [139, 80], [95, 80]], "difficult": false, "key_cls": "name"}, {"transcription": "性别机器人民族汉", "points": [[45, 88], [215, 88], [215, 109], [45, 109]], "difficult": false,...

文字检测训练总是报错，检查数据文件没有问题

我好像遇到过你这个问题，是不是在docker中训练的呢？ ERROR: Unexpected BUS error encountered in DataLoader worker. **This might be caused by insufficient shared memory (shm)**, please check whether use_shared_memory is set and storage space in /dev/shm is...

训练自己的rec模型报错

检查一下可能是配置文件和预训练模型不匹配导致的