-
### Finetuninng on RVLCDIP
Download RVLCDIP first and change the path
For OCR, you might need to customize your code
```
bash scripts/finetune_rvlcdip.sh # Finetuning on RVLCDIP
```
Q1. wh…
-
Description:
Following up after gaining valuable knowledge from '[OCR0027 Font Style Transfer Research](https://github.com/orgs/OpenPecha/projects/56/views/7?pane=issue&itemId=65728918)', we learn the…
-
-
Hello Dear Mr. Stéphane Charette,
I tried the DarkPlate executable app with the config files and weghts you provided and it works! But if I replace them with the files and weights from this url (h…
-
I found the best performance in Cityscapes leaderboard(83.7). How can I reproduce this result?
-
Is there an example code integrating this with FasterRCNN as mentioned in the paper?
It seems to me like this solution has potential impact on localization tasks applied to OCR. I'd be curious to s…
-
**Describe the bug**
I am evaluating the UnstructuredClient for processing PDF documents and am encountering an issue with the Greek language text extraction. When I attempt to extract text from PDF …
-
**Describe**
when I use the LayoutLM v2 base model to reproduce the result reported in [LayoutLMv2 paper, Table 6, row 7](https://arxiv.org/pdf/2012.14740.pdf),the result is 74,and I find there is ov…
-
我在观察Qwen2-vl的SFT数据格式时发现似乎和Qwen-vl的格式差别比较大,重点是没有给出定位框的标注示例了,还有就是0-1000的归一化问题,再Qwen2-vl中还需要操作么?求解答
When observing the SFT data format of Qwen2-vl , I found that there seems to be a big difference with …
-
您好!这份工作真的很棒,我正在寻找OCR的SOTA离线模型。如题所述,我想在自己的demo中使用这个模型,就之前我尝试的模型中,Azure的OCR效果最好,请问VimTS与Azure的对比效果如何呢?https://portal.vision.cognitive.azure.com/demo/extract-text-from-images
如果我进行领域内微调的话,可以直接使用Azure的OC…