-
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
- 系统环境/System Environment：docker 运行
- 版本号/Version：Paddle： PaddleOCR： 问题相关组件/Related components：
params.…
-
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
- 系统环境/System Environment：win10
- 版本号/Version：Paddle： PaddleOCR：2.5 问题相关组件/Related components：
- 运行指令/Com…
-
Hello!
I tried your project with JetsonNano.However, only CarsCounting could not build.
Version
ubuntu：18.04
cuda：10.2
opencv+opencv_contrib：4.3.0
cudnn：8.2.1
gcc：8.4.0
```
The C compiler…
-
up主，想过修改成可以在多个显卡上运行么？
或者可以提供点参考资料。
单单使用Dataparalle，在CTCloss那块会出现batchsize不匹配的问题；
这个batchsize是在dataloader那里就成了para里设定值（B）的一半，还是取完所有B后，split成B/2的？
pytorch的API太高层了，不知道底层怎么实现的，思维有点混乱。不如tensorflow的…
-
the parameter is
Namespace(cls_batch_num=6, cls_image_shape='3, 48, 192', cls_model_dir='~/.paddleocr/2.1/cls', cls_thresh=0.9, det=True, det_algorithm='DB', det_db_box_thresh=0.5, det_db_thresh=0…
-
I wonder why there isn't any GRU-based model implemented here.
Reading [your paper](http://lxie.nwpu-aslp.org/papers/2020ICASSP_HJY.pdf), especially Fig. 1-4, I have the impression that GRU-based m…
-
Hello @githubharald , I am currently working on a project focused on handwritten prescription recognition using a CRNN (Convolutional Recurrent Neural Network) model. My objective is to implement a W…
-
anyone knows how to fix this issue or is it a problem in the training (even though the model is still training)?
i am getting this ppocr WARNING:
[2024/04/05 00:45:30] ppocr WARNING: The pretrain…
-
在端侧部署第五步启动调试时，根据提示执行make -j得不到ocr_db_crnn文件啊，请问怎么编译得到该文件
# 执行编译，得到可执行文件ocr_db_crnn, 第一次执行此命令会下载opencv等依赖库，下载完成后，需要再执行一次
make -j
-
I would like to deploy EasyOCR models using libtorch, and saw your repo does this, which is excellent.
But the official EasyOCR models are not in TorchScript format needed by this software.
Do y…