-
https://github.com/PaddlePaddle/PaddleSlim/tree/develop/example/auto_compression/ocr
该方案更换ICDAR2015数据集，采用预训练ResNet50模型（更改模型配置即可）可以成功运行，其精度基本不变，速度减少为1/4，获得Inference模型。此时的模型在转为ONNX时报错，缺少量化配置文件（cali…
-
对run_ocr_2.0.py的代码做了一些修改后运行在Notebook中，识别./GOT-OCR2.0/assets/wechat3.jpg等图片出现的打印信息，还望解惑谢谢
![捕获2](https://github…
-
#### 问题描述 / Problem Description
程序报错
#### 运行环境 / Runtime Environment
- OS: windows 11
- Paddle: paddlepaddle-gpu 2.6.1
- PaddleOCR: paddleocr …
-
### Description of the bug | 错误描述
我的机器很差，内存只有40G，怕解析中途内存爆了，在解析一些5000多页的PDF的时候，我会先把PDF切成80页一个的小文件，然后再用MAGIC-PDF去解析。然后一大堆文件中偶尔会看到回显有如下日志这样的找不到图片的错误，一旦出现这样的错误，这个PDF就不会有任何layout或者markdown文件被输出。
不知道是不是…
-
训练训练自己的数据报错：
File "/root/miniconda/envs/d2/lib/python3.7/site-packages/mmdet/models/detectors/base.py", line 181, in forward
return self.forward_train(img, img_metas, **kwargs)
File "/roo…
-
### 🔎 Search before asking
- [X] I have searched the PaddleOCR [Docs](https://paddlepaddle.github.io/PaddleOCR/) and found no similar bug report.
- [X] I have searched the PaddleOCR [Issues](https://…
-
We use the below config to get the table ocr, but there is no way to get hocr of the image. can someone add this feature please?
`
d = os.path.dirname(sys.modules["table_ocr"].__file__)
…
-
- [ ] ✔️✔️✔️✔️✔️ Adjust spreadsheet formula feature to something usable (adjust to excel). Complicated functions
- [ ] ✔️✔️✔️✔️✔️ Improve template management. Not intuitive/discoverable now.
- [ ] ✔️✔…
-
```python
from gmft import AutoTableFormatter, TATRFormatConfig, TATRTableFormatter
config = TATRFormatConfig()
config.total_overlap_reject_threshold = 0.5
formatter = TATRTableFormatter(config = …
-
Hello,
It would be amazing to see some accuracy metrics for this solution as compared to specific OCR tools.
Have you thought about normalizing and diffing the raw output between this tool and a de…