AdvancedLiterateMachinery

AdvancedLiterateMachinery copied to clipboard

Has anyone reproduced the CORD dataset using GeoLayoutLM? Could we discuss it?

Ashu7788-alt

GeoLayoutLM: Warning about mismatched tokenizer class: BrosTokenizer vs BertTokenizer

1

Hi, I encountered this warning when running the code: The tokenizer class you load from this checkpoint is not the same type as the class this function is called from....

vodatvan01

DocHieNet Model and dataset not found

3

The links of dataset and model weights in the README of DocHieNet are pointed to the page itself. And I search in modelscope with keywords DocHieNet , got nothing. So,...

qianyue76

Code for omniparser V2

2

Thanks for the great work, this is super interesting and really useful! Just wondering, is the Omniparser v2 code already in the repo, or is it still on the way?...

cooleel

我使用如下命令进行多卡分布式训练： CUDA_VISIBLE_DEVICES=5,6 python -m torch.distributed.run \ main.py \ --data_root ./text_spotting_datasets/ \ --output_folder ./output/pretrain/stage1/ \ --train_dataset totaltext_train mlt_train ic13_train ic15_train syntext1_train syntext2_train \ --lr 0.0005 \ --max_steps 400000 \ --warmup_steps 5000...

zlf0307

Omniparser表格识别部分代码未公布？

5

Omniparser是一篇很有用的工作，但是我在复现时，在训练和推理的代码中都没有都没有找到有关表格识别的部分。请问这部分代码是还未开源呢？还是因为我的疏漏没有找到相关代码？

WaiBiBaBolmc

I can run VGT to correctly identify tables on my pdfs, but I'm unable to figure out how to get its contents.

vabatista

When identifying the following files，loss 申请单位 only on have this question

pengbo1234

```py The line 9 from rapid_latex_ocr import LatexOCR should likely be replaced wtih from rapid_latex_ocr import LaTeXOCR and thus, line 34 should be updated as well, to properly call LaTeXOCR

ApatheticMioz

Why are my trained weights 5.0GB, while the pre-trained weights are only 1.7GB?

1

I trained the GeoLayoutLM model and noticed that the weights I trained are 5.0GB in size, while the pre-trained weights are only 1.7GB. The large size of my trained weights...

nhatet1ht